Fabric manipulation is a long-standing challenge in robotics due to the enormous state space and complex dynamics. Learning approaches stand out as promising for this domain as they allow us to learn behaviours directly from data. Most prior methods however rely heavily on simulation, which is still limited by the large sim-to-real gap of deformable objects or rely on large datasets. A promising alternative is to learn fabric manipulation directly from watching humans perform the task. In this work, we explore how demonstrations for fabric manipulation tasks can be collected directly by humans, providing an extremely natural and fast data collection pipeline. Then, using only a handful of such demonstrations, we show how a pick-and-place policy can be learned and deployed on a real robot, without any robot data collection at all. We demonstrate our approach on a fabric smoothing and folding task, showing that our policy can reliably reach folded states from crumpled initial configurations. Code, video and data are available on the project website: https://sites.google.com/view/foldingbyhand

Workpiece placement with respect to an industrial robot plays an important role in robotic manufacturing due to its influence on the configuration-dependent properties of industrial robots. Suboptimal placements of the workpiece may increase the required joint torques and decrease the dexterity of the robot. The focus of this work is to identify an optimal workpiece pose that enables a robot to carry out surface finishing with configurations that require the lowest possible joint torques while having maximum possible manipulability. We present a non-linear optimization-based algorithm to solve this problem and demonstrate the algorithm's capability on dif-ferent workpieces which we share to facilitate further research in this area.

We present a generalised architecture for reactive mobile manipulation while a robot's base is in motion toward the next objective in a high-level task. By performing tasks on-the-move, overall cycle time is reduced compared to methods where the base pauses during manipulation. Reactive control of the manipulator enables grasping objects with unpredictable motion while improving robustness against perception errors, environmental disturbances, and inaccurate robot control compared to open-loop, trajectory-based planning approaches. We present an example implementation of the architecture and investigate the performance on a series of pick and place tasks with both static and dynamic objects and compare the performance to baseline methods. Our method demonstrated a real-world success rate of over 99%, failing in only a single trial from 120 attempts with a physical robot system. The architecture is further demonstrated on other mobile manipulator platforms in simulation. Our approach reduces task time by up to 48%, while also improving reliability, gracefulness, and predictability compared to existing architectures for mobile manipulation. See benburgesslimerick.github.io/ManipulationOnTheMove for supplementary materials.

Finger-tip tactile sensors are increasingly used for robotic sensing to establish stable grasps and to infer object properties. Promising performance has been shown in a number of works for inferring adjectives that describe the object, but there remains a question about how each taxel contributes to the performance. This paper explores this question with empirical experiments, leading insights for future finger-tip tactile sensor usage and design: one tactile sensor instead of a pair of sensors is sufficient for symmetric objects and interaction motions; dense taxels are beneficial for texture-related adjectives, but can be distracting to non-texture-related ones; and a frame-rate much lower than the BioTac sensor can satisfy the demand of inferring object adjectives in the PHAC-2 dataset.

Robotic vision, otherwise known as computer vision for robots, is a critical process for robots to collect and interpret detailed information related to human actions, goals, and preferences, enabling robots to provide more useful services to people. This survey and systematic review presents a comprehensive analysis on robotic vision in human-robot interaction and collaboration (HRI/C) over the past 10 years. From a detailed search of 3,850 articles, systematic extraction and evaluation was used to identify and explore 310 papers in depth. These papers described robots with some level of autonomy using robotic vision for locomotion, manipulation, and/or visual communication to collaborate or interact with people. This article provides an in-depth analysis of current trends, common domains, methods and procedures, technical processes, datasets and models, experimental testing, sample populations, performance metrics, and future challenges. Robotic vision was often used in action and gesture recognition, robot movement in human spaces, object handover and collaborative actions, social communication, and learning from demonstration. Few high-impact and novel techniques from the computer vision field had been translated into HRI/C. Overall, notable advancements have been made on how to develop and deploy robots to assist people.

Navigating natural environments with deformable terrain is a difficult challenge in robotics. Understanding the interaction dynamics between robots and such terrain is an important first step in enabling them to explore these environments. Terramechanics models are largely developed and tested on wheeled and tracked platforms, but with the advent of readily available lightweight legged robots, developing an understanding of how robot feet interact with the terrain becomes increasingly important. Works on estimating terramechanical properties of deformable sands and soils use an underlying assumption that translation of the robot foot along the surface of the terrain is due to internal shear deformation of the soil. We show that for lightweight legged robots, this is not the case. Shear forces acting on the foot of a robot during a stride are not accurately predicted by the widely-used Janosi-Hanamoto formula. We propose a new model in which two forces acting on the foot dominate the foot-terrain interaction - gross sliding friction and bulldozing resistance - and propose a model of how these forces act on the foot. We test this model on multiple soil types with different foot materials. Experimental data, collected on a testbench equipped with actuators and sensors identical to those deployed on a robot in the field, is used to validate our proposed model.

This paper introduces DGBench, a fully reproducible open-source testing system to enable benchmarking of dynamic grasping in environments with unpredictable relative motion between robot and object. We use the proposed benchmark to compare several visual perception arrangements. Traditional perception systems developed for static grasping are unable to provide feedback during the final phase of a grasp due to sensor minimum range, occlusion, and a limited field of view. A multi-camera eye-in-hand perception system is presented that has advantages over commonly used camera configurations. We quantitatively evaluate the performance on a real robot with an image-based visual servoing grasp controller and show a significantly improved success rate on a dynamic grasping task.

For 25 years the Robotics Toolbox for MATLAB®has been used for teaching and research worldwide. This paper describes its successor – the Robotics Toolbox for Python. More than just a port, it takes advantage of popular open-source packages and resources to provide platform portability, fast browser-based 3D graphics, quality documentation, fast numerical and symbolic operations, powerful IDEs, shareable and web-browseable notebooks all powered by GitHub and the open-source community. The new Toolbox provides well-known functionality for spatial mathematics (homogeneous transformations, quaternions, triple angles and twists), trajectories, kinematics (zeroth to second order), dynamics and a rich assortment of robot models. In addition, we’ve taken the opportunity to add new capabilities such as branched mechanisms, collision checking, URDF import, and interfaces to ROS. With familiar, simple yet powerful functions; the clarity of Python syntax; but without the complexity of ROS; users from beginner to advanced will find this a powerful open-source toolset for ongoing robotics education and research.

We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections. Given the lack of methods capable of assessing such probabilistic object detections, we present the new Probability-based Detection Quality measure (PDQ). Unlike AP-based measures, PDQ has no arbitrary thresholds and rewards spatial and label quality, and foreground/background separation quality while explicitly penalising false positive and false negative detections. We contrast PDQ with existing mAP and moLRP measures by evaluating state-of-the-art detectors and a Bayesian object detector based on Monte Carlo Dropout. Our experiments indicate that conventional object detectors tend to be spatially overconfident and thus perform poorly on the task of probabilistic object detection. Our paper aims to encourage the development of new object detection approaches that provide detections with accurately estimated spatial and label uncertainties and are of critical importance for deployment on robots and embodied AI systems in the real world.

Camera viewpoint selection is an important aspect of visual grasp detection, especially in clutter where many occlusions are present. Where other approaches use a static camera position or fixed data collection routines, our Multi-View Picking (MVP) controller uses an active perception approach to choose informative viewpoints based directly on a distribution of grasp pose estimates in real time, reducing uncertainty in the grasp poses caused by clutter and occlusions. In trials of grasping 20 objects from clutter, our MVP controller achieves 80% grasp success, outperforming a single-viewpoint grasp detector by 12%. We also show that our approach is both more accurate and more efficient than approaches which consider multiple fixed viewpoints.

We present a deep neural network-based method to perform high-precision, robust and real-time 6 DOF positioning tasks by visual servoing. A convolutional neural network is fine-tuned to estimate the relative pose between the current and desired images and a pose-based visual servoing control law is considered to reach the desired pose. The paper describes how to efficiently and automatically create a dataset used to train the network. We show that this enables the robust handling of various perturbations (occlusions and lighting variations). We then propose the training of a scene-agnostic network by feeding in both the desired and current images into a deep network. The method is validated on a 6 DOF robot.

This year a record number of papers were submitted directly to ICRA (1981) and to RA-L with the ICRA option (605). This represents an increase of 4% and 48% over last year respectively - clearly the RA-L/ICRA option is growing in popularity. The long-term average is a growth rate of around 60 papers per year. The submission process accommodated, as much as possible, the hardships inflicted on authors by hurricanes and earthquakes in the days prior to the deadline.

We present our approach for robotic perception in cluttered scenes that led to winning the recent Amazon Robotics Challenge (ARC) 2017. Next to small objects with shiny and transparent surfaces, the biggest challenge of the 2017 competition was the introduction of unseen categories. In contrast to traditional approaches which require large collections of annotated data and many hours of training, the task here was to obtain a robust perception pipeline with only few minutes of data acquisition and training time. To that end, we present two strategies that we explored. One is a deep metric learning approach that works in three separate steps: semantic-agnostic boundary detection, patch classification and pixel-wise voting. The other is a fully-supervised semantic segmentation approach with efficient dataset collection. We conduct an extensive analysis of the two methods on our ARC 2017 dataset. Interestingly, only few examples of each class are sufficient to fine-tune even very deep convolutional neural networks for this specific task.

The Amazon Robotics Challenge enlisted sixteen teams to each design a pick-and-place robot for autonomous warehousing, addressing development in robotic vision and manipulation. This paper presents the design of our custom-built, cost-effective, Cartesian robot system Cartman, which won first place in the competition finals by stowing 14 (out of 16) and picking all 9 items in 27 minutes, scoring a total of 272 points. We highlight our experience-centred design methodology and key aspects of our system that contributed to our competitiveness. We believe these aspects are crucial to building robust and effective robotic systems.

This paper addresses the problem of grasping arbitrarily shaped objects, observed as partial point-clouds, without requiring: models of the objects, physics parameters, training data, or other a-priori knowledge. A grasp metric is proposed based on Local Contact Moment (LoCoMo). LoCoMo combines zero-moment shift features, of both hand and object surface patches, to determine local similarity. This metric is then used to search for a set of feasible grasp poses with associated grasp likelihoods. LoCoMo overcomes some limitations of both classical grasp planners and learning-based approaches. Unlike force-closure analysis, LoCoMo does not require knowledge of physical parameters such as friction coefficients, and avoids assumptions about fingertip contacts, instead enabling robust contacts of large areas of hand and object surface. Unlike more recent learning-based approaches, LoCoMo does not require training data, and does not need any prototype grasp configurations to be taught by kinesthetic demonstration. We present results of real-robot experiments grasping 21 different objects, observed by a wrist-mounted depth camera. All objects are grasped successfully when presented to the robot individually. The robot also successfully clears cluttered heaps of objects by sequentially grasping and lifting objects until none remain.

This paper represents a step towards vision-based manipulation of plastic materials. Manipulating deformable objects is made challenging by: 1) the absence of a model for the object deformation, 2) the inherent difficulty of visual tracking of deformable objects, 3) the difficulty in defining a visual error and 4) the difficulty in generating control inputs to minimise the visual error. We propose a novel representation of the task of manipulating deformable objects. In this preliminary case study, the shaping of kinetic sand, we assume a finite set of actions: pushing, tapping and incising. We consider that these action types affect only a subset of the state, i.e., their effect does not affect the entire state of the system (specialized actions). We report the results of a user study to validate these hypotheses and release the recorded dataset. The actions (pushing, tapping and incising) are clearly adopted during the task, although it is clear that 1) participants use also mixed actions and 2) actions' effects can marginally affect the entire state, requesting a relaxation of our specialized actions hypothesis. Moreover, we compute task errors and corresponding control inputs (in the image space) using image processing. Finally, we show how machine learning can be applied to infer the mapping from error to action on the data extracted from the user study.

Minimally invasive arthroscopic surgery is a very challenging procedure that requires the manipulation of instruments in limited intraarticular space using distorted and sometimes uninformative images. Localizing the arthroscope reliably and at all times w.r.t. surrounding tissue is of fundamental importance to prevent unintended injury to patients. However, even highly-trained surgeons can struggle to localize the arthro-scope using poor image feedback. In this paper, we propose and demonstrate for the first time a visual Simultaneous Localisation and Mapping (SLAM) system, termed ArthroSLAM, capable of robustly and reliably localizing an arthroscope inside a human knee joint. The proposed system fuses the information obtained from the arthroscope, an external camera mounted on an arthroscope holder, and the odometry of a robotic arm manipulating the scope, in an Extended Kalman Filter framework. Also for the first time, we implement five alternative strategies for localization and compare them to our method in a realistic setup with a human cadaver knee joint. ArthroSLAM is shown to outperform the alternative strategies under various challenging conditions, localizing reliably and at all times with a mean Relative Pose Error of up to 1.4mm and 0.7°. Additional experiments conducted with degraded odometry data also validate the robustness of the method. An initial evaluation of the sparse map of a knee section computed by our method exhibits good morphological agreement. All results suggest that ArthroSLAM is a viable component for the robotic orthopedic surgical assistant of the future.

This paper presents the design and implementation of an assisted control technology for a small multirotor platform for aerial inspection of fixed energy infrastructure. Sensor placement is supported by a theoretical analysis of expected sensor performance and constrained platform behaviour to speed up implementation. The optical sensors provide relative position information between the platform and the asset, which enables human operator inputs to be autonomously adjusted to ensure safe separation. The assisted control approach is designed to reduced operator workload during close proximity inspection tasks, with collision avoidance and safe separation managed autonomously. The energy infrastructure includes single vertical wooden poles and crossarm with attached overhead wires. Simulated and real experimental results are provided.

Robotic challenges like the Amazon Picking Challenge (APC) or the DARPA Challenges are an established and important way to drive scientific progress. They make research comparable on a well-defined benchmark with equal test conditions for all participants. However, such challenge events occur only occasionally, are limited to a small number of contestants, and the test conditions are very difficult to replicate after the main event. We present a new physical benchmark challenge for robotic picking: the ACRV Picking Benchmark. Designed to be reproducible, it consists of a set of 42 common objects, a widely available shelf, and exact guidelines for object arrangement using stencils. A well-defined evaluation protocol enables the comparison of complete robotic systems - including perception and manipulation - instead of sub-systems only. Our paper also describes and reports results achieved by an open baseline system based on a Baxter robot.

Robotic vision is limited by line of sight and on-board camera capabilities. Robots can acquire video or images from remote cameras, but processing additional data has a computational burden. This paper applies the Distributed Robotic Vision Service, DRVS, to robot path planning using data outside line-of-sight of the robot. DRVS implements a distributed visual object detection service to distributes the computation to remote camera nodes with processing capabilities. Robots request task-specific object detection from DRVS by specifying a geographic region of interest and object type. The remote camera nodes perform the visual processing and send the high-level object information to the robot. Additionally, DRVS relieves robots of sensor discovery by dynamically distributing object detection requests to remote camera nodes. Tested over two different indoor path planning tasks DRVS showed dramatic reduction in mobile robot compute load and wireless network utilization.

In this paper we focus on the challenging problem of place categorization and semantic mapping on a robot without environment-specific training. Motivated by their ongoing success in various visual recognition tasks, we build our system upon a state-of-the-art convolutional network. We overcome its closed-set limitations by complementing the network with a series of one-vs-all classifiers that can learn to recognize new semantic classes online. Prior domain knowledge is incorporated by embedding the classification system into a Bayesian filter framework that also ensures temporal coherence. We evaluate the classification accuracy of the system on a robot that maps a variety of places on our campus in real-time. We show how semantic information can boost robotic object detection performance and how the semantic map can be used to modulate the robot's behaviour during navigation tasks. The system is made available to the community as a ROS module.

Robotic vision, unlike computer vision, typically involves processing a stream of images from a camera with time varying pose operating in an environment with time varying lighting conditions and moving objects. Repeating robotic vision experiments under identical conditions is often impossible, making it difficult to compare different algorithms. For machine learning applications a critical bottleneck is the limited amount of real world image data that can be captured and labelled for both training and testing purposes. In this paper we investigate the use of a photo-realistic simulation tool to address these challenges, in three specific domains: robust place recognition, visual SLAM and object recognition. For the first two problems we generate images from a complex 3D environment with systematically varying camera paths, camera viewpoints and lighting conditions. For the first time we are able to systematically characterise the performance of these algorithms as paths and lighting conditions change. In particular, we are able to systematically generate varying camera viewpoint datasets that would be difficult or impossible to generate in the real world. We also compare algorithm results for a camera in a real environment and a simulated camera in a simulation model of that real environment. Finally, for the object recognition domain, we generate labelled image data and characterise the viewpoint dependency of a current convolution neural network in performing object recognition. Together these results provide a multi-domain demonstration of the beneficial properties of using simulation to characterise and analyse a wide range of robotic vision algorithms.

We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.

Visual place recognition is a challenging problem due to the vast range of ways in which the appearance of real-world places can vary. In recent years, improvements in visual sensing capabilities, an ever-increasing focus on long-term mobile robot autonomy, and the ability to draw on state-of-the-art research in other disciplines-particularly recognition in computer vision and animal navigation in neuroscience-have all contributed to significant advances in visual place recognition systems. This paper presents a survey of the visual place recognition research landscape. We start by introducing the concepts behind place recognition-the role of place recognition in the animal kingdom, how a “place” is defined in a robotics context, and the major components of a place recognition system. Long-term robot operations have revealed that changing appearance can be a significant factor in visual place recognition failure; therefore, we discuss how place recognition solutions can implicitly or explicitly account for appearance change within the environment. Finally, we close with a discussion on the future of visual place recognition, in particular with respect to the rapid advances being made in the related fields of deep learning, semantic scene understanding, and video description.

We propose a novel method to improve fine-grained bird species classification based on hierarchical subset learning. We first form a similarity tree where classes with strong visual correlations are grouped into subsets. An expert local classifier with strong discriminative power to distinguish visually similar classes is then learnt for each subset. On the challenging Caltech200-2011 bird dataset we show that using the hierarchical approach with features derived from a deep convolutional neural network leads to the average accuracy improving from 64.5% to 72.7%, a relative improvement of 12.7%.

We propose a local modelling approach using deep convolutional neural networks (CNNs) for fine-grained image classification. Recently, deep CNNs trained from large datasets have considerably improved the performance of object recognition. However, to date there has been limited work using these deep CNNs as local feature extractors. This partly stems from CNNs having internal representations which are high dimensional, thereby making such representations difficult to model using stochastic models. To overcome this issue, we propose to reduce the dimensionality of one of the internal fully connected layers, in conjunction with layer-restricted retraining to avoid retraining the entire network. The distribution of low-dimensional features obtained from the modified layer is then modelled using a Gaussian mixture model. Comparative experiments show that considerable performance improvements can be achieved on the challenging Fish and UEC FOOD-100 datasets.

This paper presents a framework for synchronising multiple triggered sensors with respect to a local clock using standard computing hardware. Providing sensor measurements with accurate and meaningful timestamps is important for many sensor fusion, state estimation and control applications. Accurately synchronising sensor timestamps can be performed with specialised hardware, however, performing sensor synchronisation using standard computing hardware and non-real-time operating systems is difficult due to inaccurate and temperature sensitive clocks, variable communication delays and operating system scheduling delays. Results show the ability of our framework to estimate time offsets to sub-millisecond accuracy. We also demonstrate how synchronising timestamps with our framework results in a tenfold reduction in image stabilisation error for a vehicle driving on rough terrain. The source code will be released as an open source tool for time synchronisation in ROS.

Robustness to variations in environmental conditions and camera viewpoint is essential for long-term place recognition, navigation and SLAM. Existing systems typically solve either of these problems, but invariance to both remains a challenge. This paper presents a training-free approach to lateral viewpoint- and condition-invariant, vision-based place recognition. Our successive frame patch-tracking technique infers average scene depth along traverses and automatically rescales views of the same place at different depths to increase their similarity. We combine our system with the condition-invariant SMART algorithm and demonstrate place recognition between day and night, across entire 4-lane-plus-median-strip roads, where current algorithms fail.

This paper presents a novel online unsupervised vision system for obstacle detection in field environments which detects many obstacles pathological to appearance- or structure-only obstacle detection systems. Robust obstacle detection in field environments is challenging as it is infeasible to train on all possible obstacles in all conditions, and many obstacles are camouflaged in their appearance or structure. The proposed system combines novelty in structure and appearance cues to detect obstacles, can adapt over time to changes in the environment, and is suitable for long-term operation over changing lighting conditions in various environments. After an initial learning period the method exhibits very few false positives, while successfully detecting most obstacles over both daytime and nighttime datasets including challenging obstacles such as a person lying down in grass.

In this paper we present for the first time a complete symbolic navigation system that performs goal-directed exploration to unfamiliar environments on a physical robot. We introduce a novel construct called the abstract map to link provided symbolic spatial information with observed symbolic information and actual places in the real world. Symbolic information is observed using a text recognition system that has been developed specifically for the application of reading door labels. In the study described in this paper, the robot was provided with a floor plan and a destination. The destination was specified by a room number, used both in the floor plan and on the door to the room. The robot autonomously navigated to the destination using its text recognition, abstract map, mapping, and path planning systems. The robot used the symbolic navigation system to determine an efficient path to the destination, and reached the goal in two different real-world environments. Simulation results show that the system reduces the time required to navigate to a goal when compared to random exploration.

This paper presents a novel vision-based underwater robotic system for the identification and control of Crown- Of-Thorns starfish (COTS) in coral reef environments. COTS have been identified as one of the most significant threats to Australia's Great Barrier Reef. These starfish literally eat coral, impacting large areas of reef and the marine ecosystem that depends on it. Evidence has suggested that land-based nutrient runoff has accelerated recent outbreaks of COTS requiring extensive use of divers to manually inject biological agents into the starfish in an attempt to control population numbers. Facilitating this control program using robotics is the goal of our research. In this paper we introduce a vision-based COTS detection and tracking system based on a Random Forest Classifier (RFC) trained on images from underwater footage. To track COTS with a moving camera, we embed the RFC in a particle filter detector and tracker where the predicted class probability of the RFC is used as an observation probability to weight the particles, and we use a sparse optical flow estimation for the prediction step of the filter. The system is experimentally evaluated in a realistic laboratory setup using a robotic arm that moves a camera at different speeds and heights over a range of real-size images of COTS in a reef environment.

This paper describes a vision-based method of guiding autonomous vehicles within crop rows in agricultural fields where the crop rows are challenging to detect or their appearance is not known a-priori. The location of the crop rows is estimated with an SVM regression algorithm using colour, texture and 3D structure descriptors from a forward facing stereo camera pair. Our system rapidly learns a model online with minimal user input, and then uses this model to track crop rows. Results demonstrate our method is able to learn and track a wide variety of crops with an RMS error of less than 3cm. We also present online control results demonstrating our system autonomously steering a robot for 3km.

This paper describes a novel vision based texture tracking method to guide autonomous vehicles in agricultural fields where the crop rows are challenging to detect. Existing methods require sufficient visual difference between the crop and soil for segmentation, or explicit knowledge of the structure of the crop rows. This method works by extracting and tracking the direction and lateral offset of the dominant parallel texture in a simulated overhead view of the scene and hence abstracts away crop-specific details such as colour, spacing and periodicity. The results demonstrate that the method is able to track crop rows across fields with extremely varied appearance during day and night. We demonstrate this method can autonomously guide a robot along the crop rows.

This paper is concerned with how a localised and energy-constrained robot can maximise its time in the field by taking paths and tours that minimise its energy expenditure. A significant component of a robot's energy is expended on mobility and is a function of terrain traversability. We estimate traversability online from data sensed by the robot as it moves, and use this to generate maps, explore and ultimately converge on minimum energy tours of the environment. We provide results of detailed simulations and parameter studies that show the efficacy of this approach for a robot moving over terrain with unknown traversability as well as a number of a priori unknown hard obstacles. We also present preliminary experimental results to show the feasibility of this approach in natural terrain.

This paper presents a method to enable a mobile robot working in non-stationary environments to plan its path and localize within multiple map hypotheses simultaneously. The maps are generated using a long-term and short-term memory mechanism that ensures only persistent configurations in the environment are selected to create the maps. In order to evaluate the proposed method, experimentation is conducted in an office environment. Compared to navigation systems that use only one map, our system produces superior path planning and navigation in a non-stationary environment where paths can be blocked periodically, a common scenario which poses significant challenges for typical planners.

We propose and evaluate a novel methodology to identify the rolling shutter parameters of a real camera. We also present a model for the geometric distortion introduced when a moving camera with a rolling shutter views a scene. Unlike previous work this model allows for arbitrary camera motion, including accelerations, is exact rather than a linearization and allows for arbitrary camera projection models, for example fisheye or panoramic. We show the significance of the errors introduced by a rolling shutter for typical robot vision problems such as structure from motion, visual odometry and pose estimation.

This paper presents Sequence Matching Across Route Traversals (SMART); a generally applicable sequence-based place recognition algorithm. SMART provides invariance to changes in illumination and vehicle speed while also providing moderate pose invariance and robustness to environmental aliasing. We evaluate SMART on vehicles travelling at highly variable speeds in two challenging environments; firstly, on an all-terrain vehicle in an off-road, forest track and secondly, using a passenger car traversing an urban environment across day and night. We provide comparative results to the current state-of-the-art SeqSLAM algorithm and investigate the effects of altering SMART's image matching parameters. Additionally, we conduct an extensive study of the relationship between image sequence length and SMART's matching performance. Our results show viable place recognition performance in both environments with short 10-metre sequences, and up to 96% recall at 100% precision across extreme day-night cycles when longer image sequences are used.

This paper describes a novel obstacle detection system for autonomous robots in agricultural field environments that uses a novelty detector to inform stereo matching. Stereo vision alone erroneously detects obstacles in environments with ambiguous appearance and ground plane such as in broad-acre crop fields with harvested crop residue. The novelty detector estimates the probability density in image descriptor space and incorporates image-space positional understanding to identify potential regions for obstacle detection using dense stereo matching. The results demonstrate that the system is able to detect obstacles typical to a farm at day and night. This system was successfully used as the sole means of obstacle detection for an autonomous robot performing a long term two hour coverage task travelling 8.5 km.

This paper presents a novel method to rank map hypotheses by the quality of localization they afford. The highest ranked hypothesis at any moment becomes the active representation that is used to guide the robot to its goal location. A single static representation is insufficient for navigation in dynamic environments where paths can be blocked periodically, a common scenario which poses significant challenges for typical planners. In our approach we simultaneously rank multiple map hypotheses by the influence that localization in each of them has on locally accurate odometry. This is done online for the current locally accurate window by formulating a factor graph of odometry relaxed by localization constraints. Comparison of the resulting perturbed odometry of each hypothesis with the original odometry yields a score that can be used to rank map hypotheses by their utility. We deploy the proposed approach on a real robot navigating a structurally noisy office environment. The configuration of the environment is physically altered outside the robots sensory horizon during navigation tasks to demonstrate the proposed approach of hypothesis selection.

We present an approach for the inspection of vertical pole-like infrastructure using a vertical take-off and landing (VTOL) unmanned aerial vehicle and shared autonomy. Inspecting vertical structures, such as light and power distribution poles, is a time consuming, dangerous and expensive task with high operator workload. To address these issues, we propose a VTOL platform that can operate at close-quarters, whilst maintaining a safe stand-off distance and rejecting environmental disturbances. We adopt an Image based Visual Servoing (IBVS) technique using only two line features to stabilise the vehicle with respect to a pole. Visual, inertial and sonar data are used, making the approach suitable for indoor or GPS-denied environments. Results from simulation and outdoor flight experiments demonstrate the system is able to successfully inspect and circumnavigate a pole.

Object classification is plagued by the issue of session variation. Session variation describes any variation that makes one instance of an object look different to another, for instance due to pose or illumination variation. Recent work in the challenging task of face verification has shown that session variability modelling provides a mechanism to overcome some of these limitations. However, for computer vision purposes, it has only been applied in the limited setting of face verification. In this paper we propose a local region based intersession variability (ISV) modelling approach, and apply it to challenging real-world data. We propose a region based session variability modelling approach so that local session variations can be modelled, termed Local ISV. We then demonstrate the efficacy of this technique on a challenging real-world fish image database which includes images taken underwater, providing significant real-world session variations. This Local ISV approach provides a relative performance improvement of, on average, 23% on the challenging MOBIO, Multi-PIE and SCface face databases. It also provides a relative performance improvement of 35% on our challenging fish image dataset.

This paper deals with constrained image-based visual servoing of circular and conical spiral motion about an unknown object approximating a single image point feature. Effective visual control of such trajectories has many applications for small unmanned aerial vehicles, including surveillance and inspection, forced landing (homing), and collision avoidance. A spherical camera model is used to derive a novel visual-predictive controller (VPC) using stability-based design methods for general nonlinear model-predictive control. In particular, a quasi-infinite horizon visual-predictive control scheme is derived. A terminal region, which is used as a constraint in the controller structure, can be used to guide appropriate reference image features for spiral tracking with respect to nominal stability and feasibility. Robustness properties are also discussed with respect to parameter uncertainty and additive noise. A comparison with competing visual-predictive control schemes is made, and some experimental results using a small quad rotor platform are given.

In this paper we demonstrate passive vision-based localization in environments more than two orders of magnitude darker than the current benchmark using a $100 webcam and a $500 camera. Our approach uses the camera's maximum exposure duration and sensor gain to achieve appropriately exposed images even in unlit night-time environments, albeit with extreme levels of motion blur. Using the SeqSLAM algorithm, we first evaluate the effect of variable motion blur caused by simulated exposures of 132 ms to 10000 ms duration on localization performance. We then use actual long exposure camera datasets to demonstrate day-night localization in two different environments. Finally we perform a statistical analysis that compares the baseline performance of matching unprocessed grayscale images to using patch normalization and local neighborhood normalization - the two key SeqSLAM components. Our results and analysis show for the first time why the SeqSLAM algorithm is effective, and demonstrate the potential for cheap camera-based localization systems that function across extreme perceptual change.

This paper addresses the problem of automatically estimating the relative pose between a push-broom LIDAR and a camera without the need for artificial calibration targets or other human intervention. Further we do not require the sensors to have an overlapping field of view, it is enough that they observe the same scene but at different times from a moving platform. Matching between sensor modalities is achieved without feature extraction. We present results from field trials which suggest that this new approach achieves an extrinsic calibration accuracy of millimeters in translation and deci-degrees in rotation.

We introduce a new image-based visual navigation algorithm that allows the Cartesian velocity of a robot to be defined with respect to a set of visually observed features corresponding to previously unseen and unmapped world points. The technique is well suited to mobile robot tasks such as moving along a road or flying over the ground. We describe the algorithm in general form and present detailed simulation results for an aerial robot scenario using a spherical camera and a wide angle perspective camera, and present experimental results for a mobile ground robot.

In outdoor environments shadows are common. These typically strong visual features cause considerable change in the appearance of a place, and therefore confound vision-based localisation approaches. In this paper we describe how to convert a colour image of the scene to a greyscale invariant image where pixel values are a function of underlying material property not lighting. We summarise the theory of shadow invariant images and discuss the modelling and calibration issues which are important for non-ideal off-the-shelf colour cameras. We evaluate the technique with a commonly used robotic camera and an autonomous car operating in an outdoor environment, and show that it can outperform the use of ordinary greyscale images for the task of visual localisation.

This paper presents a mapping and navigation system for a mobile robot, which uses vision as its sole sensor modality. The system enables the robot to navigate autonomously, plan paths and avoid obstacles using a vision based topometric map of its environment. The map consists of a globally-consistent pose-graph with a local 3D point cloud attached to each of its nodes. These point clouds are used for direction independent loop closure and to dynamically generate 2D metric maps for locally optimal path planning. Using this locally semi-continuous metric space, the robot performs shortest path planning instead of following the nodes of the graph - as is done with most other vision-only navigation approaches. The system exploits the local accuracy of visual odometry in creating local metric maps, and uses pose graph SLAM, visual appearance-based place recognition and point clouds registration to create the topometric map. The ability of the framework to sustain vision-only navigation is validated experimentally, and the system is provided as open-source software.

This paper presents practical vision-based collision avoidance for objects approximating a single point feature. Using a spherical camera model, a visual predictive control scheme guides the aircraft around the object along a conical spiral trajectory. Visibility, state and control constraints are considered explicitly in the controller design by combining image and vehicle dynamics in the process model, and solving the nonlinear optimization problem over the resulting state space. Importantly, range is not required. Instead, the principles of conical spiral motion are used to design an objective function that simultaneously guides the aircraft along the avoidance trajectory, whilst providing an indication of the appropriate point to stop the spiral behaviour. Our approach is aimed at providing a potential solution to the See and Avoid problem for unmanned aircraft and is demonstrated through a series of experimental results using a small quadrotor platform.

This paper describes the theory and practice for a stable haptic teleoperation of a flying vehicle. It extends passivity-based control framework for haptic teleoperation of aerial vehicles in the longest intercontinental setting that presents great challenges. The practicality of the control architecture has been shown in maneuvering and obstacle-avoidance tasks over the internet with the presence of significant time-varying delays and packet losses. Experimental results are presented for teleoperation of a slave quadrotor in Australia from a master station in the Netherlands. The results show that the remote operator is able to safely maneuver the flying vehicle through a structure using haptic feedback of the state of the slave and the perceived obstacles.

GPS is a commonly used and convenient technology for determining absolute position in outdoor environments, but its high power consumption leads to rapid battery depletion in mobile devices. An obvious solution is to duty cycle the GPS module, which prolongs the device lifetime at the cost of increased position uncertainty while the GPS is off. This article addresses the trade-off between energy consumption and localization performance in a mobile sensor network application. The focus is on augmenting GPS location with more energy-efficient location sensors to bound position estimate uncertainty while GPS is off. Empirical GPS and radio contact data from a large-scale animal tracking deployment is used to model node mobility, radio performance, and GPS. Because GPS takes a considerable, and variable, time after powering up before it delivers a good position measurement, we model the GPS behavior through empirical measurements of two GPS modules. These models are then used to explore duty cycling strategies for maintaining position uncertainty within specified bounds. We then explore the benefits of using short-range radio contact logging alongside GPS as an energy-inexpensive means of lowering uncertainty while the GPS is off, and we propose strategies that use RSSI ranging and GPS back-offs to further reduce energy consumption. Results show that our combined strategies can cut node energy consumption by one third while still meeting application-specific positioning criteria.

This paper describes system identification, estimation and control of translational motion and heading angle for a cost effective open-source quadcopter - the MikroKopter. The dynamics of its built-in sensors, roll and pitch attitude controller, and system latencies are determined and used to design a computationally inexpensive multi-rate velocity estimator that fuses data from the built-in inertial sensors and a low-rate onboard laser range finder. Control is performed using a nested loop structure that is also computationally inexpensive and incorporates different sensors. Experimental results for the estimator and closed-loop positioning are presented and compared with ground truth from a motion capture system.

This paper presents a reactive collision avoidance method for small unmanned rotorcraft using spherical image-based visual servoing. Only a single point feature is used to guide the aircraft in a safe spiral like trajectory around the target, whilst a spherical camera model ensures the target always remains visible. A decision strategy to stop the avoidance control is derived based on the properties of spiral like motion, and the effect of accurate range measurements on the control scheme is discussed. We show that using a poor range estimate does not significantly degrade the collision avoidance performance, thus relaxing the need for accurate range measurements. We present simulated and experimental results using a small quad rotor to validate the approach.

Probabilistic costmaps provide a means of maintaining a representation of the uncertainty in the robot's model of the environment; in contrast to the ubiquitous assumptive costmaps which abstract this uncertainty away. In this work we show for the first time how probabilistic costmaps can be learned in a self-supervised manner by a robot navigating in an outdoor environment. Traversability estimates garnered from onboard sensing are used in conjunction with colour information from a-priori available overhead imagery to extrapolate the traversability of locations previously traversed by the robot to a much larger area. Gaussian processes are used to predict the traversability at unknown locations in the 2D map, and a number of techniques to deal with heteroscedastic noise and varying confidence in the training data are evaluated. A prior technique to exploit the probabilistic nature of the map in a probabilistic heuristic for A* search demonstrates that planning over these maps can also be done efficiently.

We present a technique for estimating the 6DOF pose of a PTZ camera by tracking a single moving target in the image with known 3D position. This is useful in situations where it is not practical to measure the camera pose directly. Our application domain is estimating the pose of a PTZ camera so that it can be used for automated GPS-based tracking and filming of UAV flight trials. We present results which show the technique is able to localize a PTZ after a short vision-trackshort vision-tracked flight,ed flight, and that the estimated pose is sufficiently accurate for the PTZ to then actively track a UAV based on GPS position data.

Micro aerial vehicles (MAVs) are a rapidly growing area of research and development in robotics. For autonomous robot operations, localization has typically been calculated using GPS, external camera arrays, or onboard range or vision sensing. In cluttered indoor or outdoor environments, onboard sensing is the only viable option. In this paper we present an appearance-based approach to visual SLAM on a flying MAV using only low quality vision. Our approach consists of a visual place recognition algorithm that operates on 1000 pixel images, a lightweight visual odometry algorithm, and a visual expectation algorithm that improves the recall of place sequences and the precision with which they are recalled as the robot flies along a similar path. Using data gathered from outdoor datasets, we show that the system is able to perform visual recognition with low quality, intermittent visual sensory data. By combining the visual algorithms with the RatSLAM system, we also demonstrate how the algorithms enable successful SLAM.

This work examines the effect of landmark placement on the efficiency and accuracy of risk-bounded searches over probabilistic costmaps for mobile robot path planning. In previous work, risk-bounded searches were shown to offer in excess of 70% efficiency increases over normal heuristic search methods. The technique relies on precomputing distance estimates to landmarks which are then used to produce probability distributions over exact heuristics for use in heuristic searches such as A* and D*. The location and number of these landmarks therefore influence greatly the efficiency of the search and the quality of the risk bounds. Here four new methods of selecting landmarks for risk based search are evaluated. Results are shown which demonstrate that landmark selection needs to take into account the centrality of the landmark, and that diminishing rewards are obtained from using large numbers of landmarks.

We describe and evaluate a new programming and communications framework that eases the creation of complex heterogeneous systems comprising robots and sensor networks. We use a light-weight RPC-based service framework that allows robots and static sensor nodes to be considered as services, accessible to an internet connected end-user, or to each other. We present experimental results for a very large environmental monitoring application comprising a floating sensor network and a robotic boat.

This paper presents a formulation of image-based visual servoing (IBVS) for a spherical camera where coordinates are parameterized in terms of colatitude and longitude: IBVS-Sph. The image Jacobian is derived and simulation results are presented for canonical rotational, translational as well as general motion. Problems with large rotations that affect the planar perspective form of IBVS are not present on the sphere, whereas the desirable robustness properties of IBVS are shown to be retained. We also describe a structure from motion (SfM) system based on camera-centric spherical coordinates and show how a recursive estimator can be used to recover structure. The spherical formulations for IBVS and SfM are particularly suitable for platforms, such as aerial and underwater robots, that move in SE(3).

We present a novel, simple and effective approach for tele-operation of aerial robotic vehicles with haptic feedback. Such feedback provides the remote pilot with an intuitive feel of the robot's state and perceived local environment that will ensure simple and safe operation in cluttered 3D environments common in inspection and surveillance tasks. Our approach is based on energetic considerations and uses the concepts of network theory and port-Hamiltonian systems. We provide a general framework for addressing problems such as mapping the limited stroke of a `master' joystick to the infinite stroke of a `slave' vehicle, while preserving passivity of the closed-loop system in the face of potential time delays in communications links and limited sensor data.

International audience

The world we live in is labeled extensively for the benefit of humans. Yet, to date, robots have made little use of human readable text as a resource. In this paper we aim to draw attention to text as a readily available source of semantic information in robotics by implementing a system which allows robots to read visible text in natural scene images and to use this knowledge to interpret the content of a given scene. The reliable detection and parsing of text in natural scene images is an active area of research and remains a non-trivial problem. We extend a commonly adopted approach based on boosting for the detection and optical character recognition (OCR) for the parsing of text by a probabilistic error correction scheme incorporating a sensor-model for our pipeline. In order to interpret the scene content we introduce a generative model which explains spotted text in terms of arbitrary search terms. This allows the robot to estimate the relevance of a given scene with respect to arbitrary queries such as, for example, whether it is looking at a bank or a restaurant. We present results from images recorded by a robot in a busy cityscape.

This paper addresses the tradeoff between energy consumption and localization performance in a mobile sensor network application. The focus is on augmenting GPS location with more energy-efficient location sensors to bound position estimate uncertainty in order to prolong node lifetime. We use empirical GPS and radio contact data from a large-scale animal tracking deployment to model node mobility, GPS and radio performance. These models are used to explore duty cycling strategies for maintaining position uncertainty within specified bounds. We then explore the benefits of using short-range radio contact logging alongside GPS as an energy-inexpensive means of lowering uncertainty while the GPS is off, and we propose a versatile contact logging strategy that relies on RSSI ranging and GPS lock back-offs for reducing the node energy consumption relative to GPS duty cycling. Results show that our strategy can cut the node energy consumption by half while meeting application-specific positioning criteria.

This paper is concerned with the application of wireless sensor network (WSN) technology to long-duration and large-scale environmental monitoring. The holy grail is a system that can be deployed and operated by domain specialists not engineers, but this remains some distance into the future. We present our views as to why this field has progressed less quickly than many envisaged it would over a decade ago. We use real examples taken from our own work in this field to illustrate the technological difficulties and challenges that are entailed in meeting end-user requirements for information gathering systems. Reliability and productivity are key concerns and influence the design choices for system hardware and software. We conclude with a discussion of long-term challenges for WSN technology in environmental monitoring and outline our vision of the future.

This article presents the design and implementation of a trusted sensor node that provides Internet-grade security at low system cost. We describe trustedFleck, which uses a commodity Trusted Platform Module (TPM) chip to extend the capabilities of a standard wireless sensor node to provide security services such as message integrity, confidentiality, authenticity , and system integrity based on RSA public-key and XTEA-based symmetric-key cryptography. In addition trustedFleck provides secure storage of private keys and provides platform configuration registers (PCRs) to store system configurations and detect code tampering. We analyze system performance using metrics that are important for WSN applications such as computation time, memory size, energy consumption and cost. Our results show that trustedFleck significantly outperforms previous approaches (e.g., TinyECC) in terms of these metrics while providing stronger security levels. Finally, we describe a number of examples, built on trustedFleck, of symmetric key management, secure RPC, secure software update, and remote attestation .

This paper proposes a generic decoupled image-based control scheme for cameras obeying the unified projection model. The scheme is based on the spherical projection model. Invariants to rotational motion are computed from this projection and used to control the translational degrees of freedom (DOFs). Importantly, we form invariants that decrease the sensitivity of the interaction matrix to object-depth variation. Finally, the proposed results are validated with experiments using a classical perspective camera as well as a fisheye camera mounted on a 6-DOF robotic platform.

We present a technique for high-dynamic range stereo for outdoor mobile robot applications. Stereo pairs are captured at a number of different exposures (exposure bracketing), and combined by projecting the 3D points into a common coordinate frame, and building a 3D occupancy map. We present experimental results for static scenes with constant and dynamic lighting as well as outdoor operation with variable and high contrast lighting conditions.

This paper proposes the use of optical flow from a moving robot to provide force feedback to an operator's joystick to facilitate collision free teleoperation. Optic flow is measured by wide angle cameras on board the vehicle and used to generate a virtual environmental force that is reflected to the user through the joystick, as well as feeding back into the control of the vehicle. The coupling between optical flow (velocity) and force is modelled as an impedance - in this case an optical impedance. We show that the proposed control is dissipative and prevents the vehicle colliding with the environment as well as providing the operator with a natural feel for the remote environment. The paper focuses on applications to aerial robotics vehicles, however, the ideas apply directly to other force actuated vehicles such as submersibles or space vehicles, and the authors believe the approach has potential for control of terrestrial vehicles and even teleoperation of manipulators. Experimental results are provided for a simulated aerial robot in a virtual environment controlled by a haptic joystick.

In this paper a generic decoupled imaged-based control scheme for calibrated cameras obeying the unified projection model is proposed. The proposed decoupled scheme is based on the surface of object projections onto the unit sphere. Such features are invariant to rotational motions. This allows the control of translational motion independently from the rotational motion. Finally, the proposed results are validated with experiments using a classical perspective camera as well as a fisheye camera mounted on a 6 dofs robot platform.

Image-based visual servo (IBVS) is a simple, efficient and robust technique for vision-based control. Although technically a local method in practice it demonstrates almost global convergence. However IBVS performs very poorly for cases that involve large rotations about the optical axis. It is well known that re-parameterizing the problem by using polar, instead of Cartesian coordinates, of feature points overcomes this limitation. First, simulation and experimental results are presented to show the complementarity of these two parameterizations. We then describe a new hybrid visual servo strategy based on combining polar and Cartesian image Jacobians.

The programming and retasking of sensor nodes could benefit greatly from the use of a virtual machine (VM) since byte code is compact, can be loaded on demand, and interpreted on a heterogeneous set of devices. The challenge is to ensure good programming tools and a small footprint for the virtual machine to meet the memory constraints of typical WSN platforms. To this end we propose Darjeeling, a virtual machine modelled after the Java VM and capable of executing a substantial subset of the Java language, but designed specifically to run on 8- and 16-bit microcontrollers with 2--10 KB of RAM.

In this paper, we describe the design and the implementation of a management system called SRM for controlling data reliability in Wireless Sensor Networks. SRM is based on a hierarchical management architecture and policy-based network management paradigm. SRM consists of four modules: a user policy specification module, an evaluation module, a decision making module and an action module. The interaction among these modules ensures that the network provides adequate information to the users while reducing energy consumption. To demonstrate the effectiveness of the management framework, we design a policy for balancing energy consumption and data reliability. Our experimental results show that SRM can meet the reliability requirements, and reduces energy consumption by up to 50% compared to the case of no management.

The Java programming language has potentially significant advantages for wireless sensor nodes but there is currently no feature-rich, open source virtual machine available. In this paper we present Darjeeling, a system comprising offline tools and a memory efficient run-time. The offline post-compiler tool analyzes, links and consolidates Java class files into loadable modules. The runtime implements a modified Java VM that supports multithreading and is designed specifically to operate in constrained execution environments such as wireless sensor network nodes and supports inheritance, threads, garbage collection, and loadable modules. We have demonstrated Java running on AVR128 and MSP430 microcontrollers at speeds of up to 70,000 JVM instructions per second.

Communication security for wireless sensor networks (WSN) is a challenge due to the limited computation and energy resources available at nodes. We describe the design and implementation of a public-key (PK) platform based on a standard Trusted Platform Module (TPM) chip that extends the capability of a standard node. The result facilitates message security services such as confidentiality, authenticity and integrity. We present results including computation time, energy consumption and cost.

We present the design and deployment results for PosNet - a large-scale, long-duration sensor network that gathers summary position and status information from mobile nodes. The mobile nodes have a fixed-sized memory buffer to which position data is added at a constant rate, and from which data is downloaded at a non-constant rate. We have developed a novel algorithm that performs online summarization of position data within the buffer, where the algorithm naturally accommodates data input and output rate mismatch, and also provides a delay-tolerant approach to data transport. The algorithm has been extensively tested in a large-scale long-duration cattle monitoring and control application.

This paper considers an application of scale-invariant feature detection using scale-space analysis suitable for use with wide field of view cameras. Rather than obtain scale- space images via convolution with the Gaussian function on the image plane, we map the image to the sphere and obtain scale-space images as the solution to the heat (diffusion) equation on the sphere which is implemented in the frequency domain using spherical harmonics. The percentage correlation of scale-invariant features that may be matched between any two wide-angle images subject to change in camera pose is then compared using each of these methods. We also present a means by which the required sampling bandwidth may be determined and propose a suitable anti-aliasing filter which may be used when this bandwidth exceeds the maximum permissible due to computational requirements. The results show improved performance using scale-space images obtained as the solution of the diffusion equation on the sphere, with additional improvements observed using the anti-aliasing filter.

This paper describes a novel experiment in which two very different methods of underwater robot localization are compared. The first method is based on a geometric approach in which a mobile node moves within a field of static nodes, and all nodes are capable of estimating the range to their neighbours acoustically. The second method uses visual odometry, from stereo cameras, by integrating scaled optical flow. The fundamental algorithmic principles of each localization technique is described. We also present experimental results comparing acoustic localization with GPS for surface operation, and a comparison of acoustic and visual methods for underwater operation.

This paper investigates a mobile, wireless sensor/actuator network application for use in the cattle breeding industry. Our goal is to prevent fighting between bulls in on-farm breeding paddocks by autonomously applying appropriate stimuli when one bull approaches another bull. This is an important application because fighting between high-value animals such as bulls during breeding seasons causes significant financial loss to producers. Furthermore, there are significant challenges in this type of application because it requires dynamic animal state estimation, real-time actuation and efficient mobile wireless transmissions. We designed and implemented an animal state estimation algorithm based on a state-machine mechanism for each animal. Autonomous actuation is performed based on the estimated states of an animal relative to other animals. A simple, yet effective, wireless communication model has been proposed and implemented to achieve high delivery rates in mobile environments. We evaluated the performance of our design by both simulations and field experiments, which demonstrated the effectiveness of our autonomous animal control system.

Numerous scale-invariant feature matching algorithms using scale-space analysis have been proposed for use with perspective cameras, where scale-space is defined as convolution with a Gaussian. The contribution of this work is a method suitable for use with wide angle cameras. Given an input image, we map it to the unit sphere and obtain scale-space images by convolution with the solution of the spherical diffusion equation on the sphere which we implement in the spherical Fourier domain. Using such an approach, the scale-space response of a point in space is independent of its position on the image plane for a camera subject to pure rotation. Scale-invariant features are then found as local extrema in scale-space. Given this set of scale-invariant features, we then generate feature descriptors by considering a circular support region defined on the sphere whose size is selected relative to the feature scale. We compare our method to a naive implementation of SIFT where the image is treated as perspective, where our results show an improvement in matching performance.

This paper investigates a wireless sensor network deployment - monitoring water quality, e.g. salinity and the level of the underground water table - in a remote tropical area of northern Australia. Our goal is to collect real time water quality measurements together with the amount of water being pumped out in the area, and investigate the impacts of current irrigation practice on the environments, in particular underground water salination. This is a challenging task featuring wide geographic area coverage (mean transmission range between nodes is more than 800 meters), highly variable radio propagations, high end-to-end packet delivery rate requirements, and hostile deployment environments. We have designed, implemented and deployed a sensor network system, which has been collecting water quality and flow measurements, e.g., water flow rate and water flow ticks for over one month. The preliminary results show that sensor networks are a promising solution to deploying a sustainable irrigation system, e.g., maximizing the amount of water pumped out from an area with minimum impact on water quality.

This short-paper presents the design and experimental validation of model-based, mobile routing protocol for a delay tolerant network (DTN), where herds of animals are utilised as message ferries. We develop a novel routing protocol that utilises knowledge of the predicted behaviour of each ferry in order to choose optimal ferries for carrying messages from source to sink nodes, as well as minimise routing overhead of the network via adaptive beaconing based on current behaviour.

This paper presents a simple and intuitive approach to determining the kinematic parameters of a serial-link robot in Denavit-Hartenberg (DH) notation. Once a manipulator's kinematics is parameterized in this form, a large body of standard algorithms and code implementations for kinematics, dynamics, motion planning, and simulation are available. The proposed method has two parts. The first is the ldquowalk through,rdquo a simple procedure that creates a string of elementary translations and rotations, from the user-defined base coordinate to the end-effector. The second step is an algebraic procedure to manipulate this string into a form that can be factorized as link transforms, which can be represented in standard or modified DH notation. The method allows for an arbitrary base and end-effector coordinate system as well as an arbitrary zero joint angle pose. The algebraic procedure is amenable to computer algebra manipulation and a Java program is available as supplementary downloadable material.

This research is investigating the feasibility of using computer vision to provide a level of situational awareness suitable for the task of UAV "sense and avoid." This term is used to describe the capability of a UAV to detect airborne traffic and respond with appropriate avoidance maneuvers in order to maintain minimum separation distances. As reflected in regulatory requirements such as FAA Order 7610.4, this capability must demonstrate a level of performance which meets or exceeds that of an equivalent human pilot. Presented in this paper is a comparison of two initial image processing algorithms that have been designed to detect small, point-like features (potentially corresponding to distant, collision-course aircraft) from image streams, and a discussion of their detection performance in processing a real-life collision scenario. This performance is compared against the stated benchmark of equivalent human performance, specifically the measured detection times of an alerted human observer. The two algorithms were used to process a series of image streams featuring real collision-course aircraft against a variety of daytime backgrounds. Preliminary analysis of this data set has yielded encouraging results, achieving first detection times at distances of approximately 6.5 km (3.5 nmi), which are 35-40% greater than those of the alerted human observer. Comparisons were also drawn between the two separate detection algorithms, and have demonstrated that a new approach designed to increase resilience to image noise achieves a lower rate of false alarms, particularly in tests featuring more sensitive detection thresholds

We present algorithms, systems, and experimental results for underwater data muling. In data muling a mobile agent interacts with static agents to upload, download, or transport data to a different physical location. We consider a system comprising an autonomous underwater vehicle (AUV) and many static underwater sensor nodes (USN) networked together optically and acoustically. The AUV can locate the static nodes using vision and hover above the static nodes for data upload. We describe the hardware and software architecture of this underwater system, as well as experimental data

Agriculture accounts for a significant portion of the GDP in most developed countries. However, managing farms, particularly large-scale extensive farming systems, is hindered by lack of data and increasing shortage of labour. We have deployed a large heterogeneous sensor network on a working farm to explore sensor network applications that can address some of the issues identified above. Our network is solar powered and has been running for over 6 months. The current deployment consists of over 40 moisture sensors that provide soil moisture profiles at varying depths, weight sensors to compute the amount of food and water consumed by animals, electronic tag readers, up to 40 sensors that can be used to track animal movement (consisting of GPS, compass and accelerometers), and 20 sensor/actuators that can be used to apply different stimuli (audio, vibration and mild electric shock) to the animal. The static part of the network is designed for 24/7 operation and is linked to the Internet via a dedicated high-gain radio link, also solar powered. The initial goals of the deployment are to provide a testbed for sensor network research in programmability and data handling while also being a vital tool for scientists to study animal behavior. Our longer term aim is to create a management system that completely transforms the way farms are managed.

The use of UAVs in civilian and domestic applications is highly demanding, requiring a high-level of capability from the vehicles. This work addresses the task in which a UAV is performing an inspection on a set of power lines and an emergency situation occurs requiring the UAV to avoid the lines and then find a safe landing area (a forced landing). This problem is approached using vision, where the vision system acts as the overall controller sending velocity commands to a low-level controller. The use of vision here allows the 2D position of the UAV to be updated by an image-based signal where the error to minimize is the location of a feature or set of features in the image. The system has been tested in a air vehicle simulator (AVS) - a cable array robot which allows to simulate and control three DOF (translation) of a UAV. Results obtained from tests in a scale scenario show the feasibility of this approach

This paper presents research that is being conducted by the Commonwealth Scientific and Industrial Research Organisation (CSIRO) with the aim of investigating the use of wireless sensor networks for automated livestock monitoring and control. It is difficult to achieve practical and reliable cattle monitoring with current conventional technologies due to challenges such as large grazing areas of cattle, long time periods of data sampling, and constantly varying physical environments. Wireless sensor networks bring a new level of possibilities into this area with the potential for greatly increased spatial and temporal resolution of measurement data. CSIRO has created a wireless sensor platform for animal behaviour monitoring where we are able to observe and collect information of animals without significantly interfering with them. Based on such monitoring information, we can identify each animal's behaviour and activities successfully

The highly unstructured nature of coral reef environments makes them difficult for current robotic vehicles to efficiently navigate. Typical research and commercial platforms have limited autonomy within these environments and generally require tethers and significant external infrastructure. This paper outlines the development of a new robotic vehicle for underwater monitoring and surveying in highly unstructured environments and presents experimental results illustrating the vehicle’s performance. The hybrid AUV design developed by the CSIRO robotic reef monitoring team realises a compromise between endurance, manoeuvrability and functionality. The vehicle represents a new era in AUV design specifically focused at providing a truly low-cost research capability that will progress environmental monitoring through unaided navigation, cooperative robotics, sensor network distribution and data harvesting.

The development of autonomous air vehicles can be an expensive research pursuit. To alleviate some of the financial burden of this process, we have constructed a system consisting of four winches each attached to a central pod (the simulated air vehicle) via cables — a cable-array robot. The system is capable of precisely controlling the three dimensional position of the pod allowing effective testing of sensing and control strategies before experimentation on a free-flying vehicle. In this paper, we present a brief overview of the system and provide a practical control strategy for such a system.

We present a novel vision-based technique for navigating an unmanned aerial vehicle (UAV) through urban canyons. Our technique relies on both optic flow and stereo vision information. We show that the combination of stereo and optic flow (stereo flow) is more effective at navigating urban canyons than either technique alone. Optic flow from a pair of sideways looking cameras is used to stay centered in a canyon and initiate turns at junctions, while stereo vision from a forward facing stereo head is used to avoid obstacles to the front. The technique was tested in full on an autonomous tractor at CSIRO and in part on the USC autonomous helicopter. Experimental results are presented from these two robotic platforms operating in outdoor environments. We show that the autonomous tractor can navigate urban canyons using stereo-flow, and that the autonomous helicopter can turn away from obstacles to the side using optic flow. In addition, preliminary results show that a single pair of forward facing fisheye cameras can be used for both stereo and optic flow. The center portions of the fisheye images are used for stereo, while flow is measured in the periphery of the images.

In this paper we present a novel platform for underwater sensor networks to be used for long-term monitoring of coral reefs and fisheries. The sensor network consists of static and mobile underwater sensor nodes. The nodes communicate point-to-point using a novel high-speed optical communication system integrated into the TinyOS stack, and they broadcast using an acoustic protocol integrated in the TinyOS stack. The nodes have a variety of sensing capabilities, including cameras, water temperature, and pressure. The mobile nodes can locate and hover above the static nodes for data muling, and they can perform network maintenance functions such as deployment, relocation, and recovery. In this paper we describe the hardware and software architecture of this underwater sensor network. We then describe the optical and acoustic networking protocols and present experimental networking and data collected in a pool, in rivers, and in the ocean. Finally, we describe our experiments with mobility for data muling in this network.

We describe a moving virtual fence algorithm for herding cows. Each animal in the herd is given a smart collar consisting of a GPS, PDA, wireless networking and a sound amplifier. Using the GPS, the animal's location can be verified relative to the fence boundary. When approaching the perimeter, the animal is presented with a sound stimulus whose effect is to move away. We have developed the virtual fence control algorithm for moving a herd. We present simulation results and data from experiments with 8 cows equipped with smart collars.

We describe a sensor network deployment method using autonomous flying robots. Such networks are suitable for tasks such as large-scale environmental monitoring or for command and control in emergency situations. We describe in detail the algorithms used for deployment and for measuring network connectivity and provide experimental data we collected from field trials. A particular focus is on determining gaps in connectivity of the deployed network and generating a plan for a second, repair, pass to complete the connectivity. This project is the result of a collaboration between three robotics labs (CSIRO, USC, and Dartmouth.).

The mechanisms of helicopter flight create a unique, high-vibration environment which can play havoc with the accurate operation of on-board sensors. Vibration isolation of electronic sensors from structural borne oscillations is paramount to their reliable and accurate use. Effective isolation is achieved by realising a trade-off between the properties of the suspended instrument package, and the isolation mechanism. This is made more difficult as the weight and size of the sensors and computing hardware decreases with advances in technology. This paper presents a history of the design, challenges, constraints and construction of an integrated isolated vision and sensor platform and landing gear for the CSIRO autonomous X-Cell helicopter. The results of isolation performance and in-flight tests of the platform in autonomous flight are presented.

Ensuring the long term viability of reef environments requires essential monitoring of many aspects of these ecosystems. However, the sheer size of these unstructured environments (for example Australia's Great Barrier Reef) pose a number of challenges for current monitoring platforms which are typically remote operated and required significant resources and infrastructure. Therefore, a primary objective of the CSIRO robotic reef monitoring project is to develop and deploy a large number of AUV teams to perform broadscale reef surveying. In order to achieve this, the platforms must be cheap, even possibly disposable. This work presents the results of a preliminary investigation into the performance of a low-cost sensor suite and associated processing techniques for vision and inertial-based navigation within a highly unstructured reef environment.

In this paper, we outline the sensing system used for the visual pose control of our experimental car-like vehicle, the Autonomous Tractor. The sensing system consists of a magnetic compass, an omnidirectional camera and a low-resolution odometry system. In this work, information from these sensors is fused using complementary filters. Complementary filters provide a means of fusing information from sensors with different characteristics in order to produce a more reliable estimate of the desired variable. Here, the range and bearing of landmarks observed by the vision system are fused with odometry information and a vehicle model, providing a more reliable estimate of these states. We also present a method of combining a compass sensor with odometry and a vehicle model to improve the heading estimate.

Position estimation for planetary rovers has been typically limited to odometry based on proprioceptive measurements such as the integration of distance traveled and measurement of heading change. Here we present and compare two methods of online visual odometry suited for planetary rovers. Both methods use omnidirectional imagery to estimate motion of the rover. One method is based on robust estimation of optical flow and subsequent integration of the flow. The second method is a full structure-from-motion solution. To make the comparison meaningful we use the same set of raw corresponding visual features for each method. The dataset is an sequence of 2000 images taken during a field experiment in the Atacama desert, for which high resolution GPS ground truth is available.

Maintenance is a time consuming and expensive task for any golf course or driving range manager. For a golf course the primary tasks are grass mowing and maintenance (fertilizer and herbicide spreading), while for a driving range mowing, maintenance and ball collection are required. All these tasks require an operator to drive a vehicle along paths, which are generally predefined. This paper presents some preliminary in-field testing results for an automated tractor vehicle performing golf ball collection on an actual driving range, and mowing on difficult unstructured terrain.

ElectricCOW is a network, animal behaviour and agent simulator designed to allow detailed simulation of an ad-hoc model network built from small mote-like devices called flecks. Detailed radio communications, cattle behaviour and sensor and actuator network modelling allows a closed-loop environment, where the network can influence the behaviour of its mobile platforms.

The paper describes some new wireless sensor hardware developed for pastoral and environmental applications. From our early experiments with Mote hardware, we were inspired to develop our devices with improved radio range, solar power capability, mechanical and electrical robustness, and with unique combinations of sensors. Here we describe the design and evolution of a small family of devices: radio/processor board; a soil moisture sensor interface; a single board multisensor unit for animal tracking experiments.

In this paper we describe a low-cost flight control system for a small (60 class) helicopter which is part of a larger project to develop an autonomous flying vehicle. Our approach differs from that of others in not using an expensive inertial/GPS sensing system. The primary sensors for vehicle stabilization are a low-cost inertial sensor and a pair of CMOS cameras. We describe the architecture of our flight control system, the inertial and visual sensing subsystems and present some flight control results.

In this paper, we develop the switching controller presented by Lee et al. for the pose control of a car-like vehicle, to allow the use of an omnidirectional vision sensor. To this end we incorporate an extension to a hypothesis on the navigation behaviour of the desert ant, cataglyphis bicolor, which leads to a correspondence free landmark based vision technique. The method we present allows positioning to a learnt location based on feature bearing angle and range discrepancies between the robot's current view of the environment, and that at a learnt location. We present simulations and experimental results, the latter obtained using our outdoor mobile platform.

This paper presents a technique for tracking road edges in a panoramic image sequence. The major contribution is that instead of unwarping the image to find parallel lines representing the road edges, we choose to warp the parallel groundplane lines into the image plane of the equiangular panospheric camera. Updating the parameters of the line thus involves searching a very small number of pixels in the panoramic image, requiring considerably less computation than unwarping. Results using real-world images, including shadows, intersections and curves, are presented.

This paper describes the implementation of an autonomous navigation system onto a 30 tonne Load-Haul-Dump truck. The control architecture is based on a robust reactive wall-following behaviour. To make it purposeful we provide driving hints derived from an approximate nodal-map. For most of the time, the vehicle is driven with weak localization (odometry). This need only be improved at intersections where decisions must be made-a technique we refer to as opportunistic localization. The truck has achieved full-speed autonomous operation at an artificial test mine, and subsequently, at a operational underground mine.

This paper discusses similarities and differences in autonomous helicopters developed at USC and CSIRO. The most significant differences are in the accuracy and sample rate of the sensor systems used for control. The USC vehicle, like a number of others, makes use of a sensor suite that costs an order of magnitude more than the vehicle. The CSIRO system, by contrast, utilizes low-cost inertial, magnetic, vision and GPS to achieve the same ends. We describe the architecture of both autonomous helicopters, discuss the design issues and present comparative results.

Visual servoing has been a viable method of robot manipulator control for more than a decade. Image-based visual servoing (IBVS), in particular, has seen considerable development in recent years. Recently, a number of researchers have reported tasks for which traditional IBVS methods fail, or experience serious difficulties. In response to these difficulties, several methods have been devised that partition the control scheme, allowing troublesome motions to be handled by methods that do not rely solely on the image Jacobian. To date, there has been little research that explores the relative strengths and weaknesses of these methods. In this paper we present such an evaluation. We have chosen three recent visual servo approaches for evaluation, in addition to the traditional IBVS approach. We posit a set of performance metrics that measure quantitatively the performance of a visual servo controller for a specific task. We then simulate each of the candidate visual servo methods for four canonical tasks, under perfect and nonideal experimental conditions.

Mobile phones are now ubiquitous and many of these now include micro-browsers. We explore the potential, and the limitations, of widely available WAP technology for online control and monitoring of a robot. A mobile phone interface for a 4 joint hydraulic manipulator has been developed and was successfully tested.

This paper is concerned with choosing image features for image based visual servo control and how this choice influences the closed-loop dynamics of the system. In prior work, image features tend to be chosen on the basis of image processing simplicity and noise sensitivity. In this paper we show that the choice of feature directly influences the closed-loop dynamics in task-space. We focus on the depth axis control of a visual servo system and compare analytically various approaches that have been reported recently in the literature. The theoretical predictions axe verified by experiment.

Model-based controllers have successfully been applied to many electric drive robotic manipulators to improve their tracking performance. The application to hydraulically actuated systems however is not straight forward, due to the nonlinear internal dynamics of the actuators. The paper presents the modelling of an experimental hydraulic robot arm and the implementation of a cascaded control scheme: a model-based motion controller that compensates for dynamic forces, such as friction and gravity, on top of underlying force controllers for the hydraulic actuators. Dynamic parameters, that are required by the position and the force controllers, are identified online using adaptation algorithms. Experimental results show the performance that this type of controller can achieve with the experimental hydraulic robot arms.

Examines the feasibility of automation of dragline bucket excavators used to strip over-burden from open cut mines. In particular the automatic control of bucket carry angle and bucket trajectory are addressed. Open-loop dynamics of a 1:20 scale model dragline bucket are identified, through measurement of frequency response between carry angle and drag motor input voltage. A strategy for automatic control of carry angle is devised and implemented using bucket angle and rate feedback. System compensation and tuning are explained and closed loop frequency and time responses are measured.

In image-based visual servo control, where control is effected with respect to the image, there is no direct control over the Cartesian velocities of the robot end effector. As a result, the robot executes trajectories that are desirable in the image, but which can be indirect and seemingly contorted in Cartesian space. We introduce a partitioned approach to visual servo control that overcomes this problem. In particular, we decouple the x-axis rotational and translational components of the control from the remaining degrees of freedom. Then, to guarantee that all features remain in the image throughout the entire trajectory, we incorporate a potential function that repels feature points from the boundary of the image plane. We illustrate our control scheme with a variety of results.

This paper discusses the steering kinematics for a center-articulated mobile robot. Several models have been recently proposed in the literature and we use experimental data to compare and validate these models. The vehicle heading response to steering command is shown to include a dominant zero due a nonholonomic constraint, and this is verified by experiments conducted using a 30-t mobile vehicle at our laboratory. Simulation results are then used to show the significance of this zero and its effect on closed-loop heading angle control.

Provides a broad sketch of visual servoing, and the application of real-time vision, tracking and control for robot guidance. It outlines the basic theoretical approaches to the problem, describes a typical architecture, and discusses major milestones, applications and the significant vision sub-problems that must be solved.

This paper describes how many of the navigation techniques developed by the robotics research community over the last decade may be applied to a class of underground mining vehicles (local haul dump (LHD) and haul trucks). We review the current state of the art in this area and conclude that there are essentially two basic methods of navigation applicable. We describe an implementation of a reactive navigation system on a 30 tonne LHD which has achieved full-speed operation at a production mine.

The rank transform is a non-parametric technique which has been previously proposed for the stereo matching problem. The motivation behind its application to the matching problem is its invariance to certain types of image distortion and noise, as well as its amenability to real-time implementation. This paper derives an analytic expression for the process of matching using the rank transform, and then goes on to derive one constraint which must be satisfied for a correct match. This has been dubbed the rank order constraint or simply the rank constraint. Experimental work has shown that this constraint is capable of resolving ambiguous matches, thereby improving matching reliability. This constraint was incorporated into a new algorithm for matching using the rank transform. This modified algorithm resulted in an increased proportion of correct matches, for all test imagery used.

Modelling and experimental identification of friction has been carried out for an asymmetric hydraulic cylinder. A practical model of friction for this class of actuators is described. The model captures the magnitude and direction of friction forces without explicitly including a velocity-dependent term. Instead, it uses values of fluid pressure at the two cylinder ports, to yield a model that is less sensitive to load variation. Experimental parameter identification was undertaken in parallel for a classical viscous-Coulomb friction model. Two distinct friction regimes have been revealed, corresponding to "low" and "high" velocities. A comparison between the two models shows that the loss in accuracy in the pressure-based model is less than 1% when compared with the conventional one. Stiction analysis has also been performed. It has been found in this case that it is reasonable to assume invariance of stiction with piston position and rate of applied input. Friction was found to be highly dependent on the direction of piston motion in asymmetric hydraulic cylinders. Finally, computer simulation results show agreement with experimental data.

A frame-rate stereo vision system, based on non-parametric matching metrics, is described. Traditional metrics, such as normalized cross-correlation, are expensive in terms of logic. Non-parametric measures require only simple, parallelizable, functions such as comparators, counters and exclusive-or, and are thus very well suited to implementation in reprogrammable logic.

The camera calibration matrix captures the transformation of a 3D point onto a 2D image plane as occurs in the camera being used for imaging. Given the world coordinates of a number of precisely placed points in a 3D space, camera calibration requires the measurement of the 2D projection of those scene points on the image plane. While the coordinates of the points in 3D space can be measured precisely, the image coordinates that are determined from the digital image are not precise mainly because of the measurement noise. In this paper, we derive analytical relationships between the errors in the intrinsic camera parameters (ICPs) due to error in measurements. We show that the errors in the ICPs are Gaussian distributed when the measurement noise is Gaussian. We verify these results experimentally.

This paper describes a series of trials that were done at an underground mine in New South Wales, Australia. Experimental results are presented from the data obtained during the field trials and suitable sensor suites for an autonomous mining vehicle navigation system are evaluated.

This paper describes a software architecture for real-world robotic applications. We discuss issues of software reliability, testing and realistic off-line simulation that allows the majority of the automation system to be tested off-line in the laboratory before deployment in the field. A recent project, the automation of a very large mining machine is used to illustrate the discussion.

The mining industry is highly suitable for the application of robotics and automation technology since the work is arduous, dangerous and often repetitive. This paper discusses a robust sensing system developed to find and trade the position of the hoist ropes of a dragline. Draglines are large 'walking cranes' used in open-pit coal mining to remove the material covering the coal seam. The rope sensing system developed uses two time-of-flight laser scanners. The finding algorithm uses a novel data association and tracking strategy based on pairing rope data.

Electric walking draglines are physically large and powerful machines used in the mining industry. However with the addition of suitable sensors and a controller a dragline can be considered as a numerically controlled machine or robot which can then perform parts of the operating cycle automatically. This paper presents an analysis of the electromechanical system necessary precursor to automatic control.

A method for modelling an electrohydraulic system is presented in this paper. Without directly using the conventional linear models, accurate models for the electrohydraulic components have been constructed using the characterisation data provided by manufacturers and measurements obtained in the laboratory with a custom built electrohydraulic manipulator. A commonly available general-purpose simulation package, Simulink, has been used to solve the nonlinear differential equations.

This paper presents the results of an experimental program for evaluating sensors and sensing technologies in an underground mining applications. The objective of the experiments is to infer what combinations of sensors will provide reliable navigation systems for autonomous vehicles operating in a harsh underground environment. Results from a wide range of sensors are presented and analysed. A conclusion as to the best combination of sensors is drawn.

Draglines are very large machines that are used to remove overburden in open-cut coal mines. This paper outlines the design of a computer control system to implement an automated swing cycle on a production dragline. Subsystems and sensors have been developed to satisfy the constraints imposed by the task, the harsh operating environment and the mine's production requirements.

This paper describes an automated procedure for analysing the significance of each of the many terms in the equations of motion for a serial-link robot manipulator. Significance analysis provides insight into the rigid-body dynamic effects that are significant locally or globally in the manipulator's state space. Deleting those terms that do not contribute significantly to the total joint torque can greatly reduce the computational burden for online control, and a Monte-Carlo style simulation is used to investigate the errors thus introduced. The procedures described are a hybrid of symbolic and numeric techniques, and can be readily implemented using standard computer algebra packages.

In this paper we argue that the focus of much of the visual servoing literature has been on the kinematics of visual control and has ignored a number of fundamental and significant dynamic control issues. To this end the concept of visual dynamic control is introduced, which is concerned with dynamic effects due to the manipulator and machine vision sensor which limit the performance. These must be explicitly addressed in order to achieve high-performance control. The paper uses simulation and experiment to investigate the feedback control issues such as the choice of compensator, and the use of axis position, velocity or torque controlled inner-loops within the visual servo system. The limitations of visual feedback control lead to the investigation of target velocity feedforward control, which combined with axis velocity control, is shown to result in robust and high performance tracking.

This article provides a tutorial introduction to visual servo control of robotic manipulators. Since the topic spans many disciplines our goal is limited to providing a basic conceptual framework. We begin by reviewing the prerequisite topics from robotics and computer vision, including a brief review of coordinate transformations, velocity representation, and a description of the geometric aspects of the image formation process. We then present a taxonomy of visual servo control systems. The two major classes of systems, position-based and image-based systems, are then discussed in detail. Since any visual servo system must be capable of tracking image features in a sequence of images, we also include an overview of feature-based and correlation-based methods for tracking. We conclude the tutorial with a number of observations on the current directions of the research field of visual servo control.

Because a dragline bucket's rigging is flexible, its position cannot be inferred from knowledge of rope length and boom position only. Moreover, active devices cannot be placed on the bucket itself to sense position because of the risk of damage. This paper describes a new machine vision system which is being developed to sense bucket position remotely. It is based on a single camera observing the field in which the bucket moves. An image segmentation process is used to classify the bucket and to identify its position in the scene. This data is used to determine the angle between the bucket and the vertical boom plane, which is used as position feedback in a closed loop system to control bucket motion. The segmentation processes employed, based on colour and intensity are outlined, and experimental results are presented.>

The PUMA 560 robot is the white rat of robotics research - it has been studied and used in countless experiments over many years and in many laboratories. However, it remains a challenge to assemble the complete data needed for model-based control of the robot. This paper presents a numerical comparison of kinematic, dynamic and electrical parameters for the PUMA 560 robot which have been reported in the literature. For the first time, data from several experiments are presented in a single system of coordinates, which facilitates comparison. Differences in the data and the various methods of measurement are discussed. New data have been gathered and are presented where the record was incomplete.>

The authors discuss three dominant dynamic effects that are manifested in the use of robot end-mounted cameras for high-performance tracking and positioning tasks. They are time delay (or latency in the sensing and control blocks), time-varying loop gain due to perspective, and vibrations due to structural and drive compliance. Analysis of the dynamic is presented and compared with experimental results.>