Abstract Triangulation refers to the problem of finding a 3D point from its 2D projections on multiple images taken at different camera poses. For solving this problem, it is a common practice to use the so‐called optimal triangulation method. But, the method can be optimal only if we assume no uncertainty in the camera parameters. In this paper, an extensive comparison between various existing methods for the calibrated cameras is performed, in which different poses are considered. Furthermore, uncertainty sensitivity analysis is conducted for extrinsic parameters of cameras. The results show that the optimal triangulation method is actually not the best choice when there is uncertainty in extrinsic parameters. Interestingly, it can be observed that the simple midpoint method works equally well or outperforms the optimal triangulation and many other methods. Apart from its high performance, the midpoint method has a simple closed form solution for multiple views while the optimal triangulation method is hard to be used for more than two views. Therefore, in contrast to the common practice, we argue that the simple midpoint method can be a good choice in the structure‐from‐motion process where there is uncertainty in extrinsic camera parameters.

Pose graph optimization (PGO), or equivalently pose synchronization, that is synchronizing rotations and positions, is the state-of-the-art formulation for simultaneous localization and mapping in robotics. In this article, we first present a new manifold Gauss-Newton method for solving the rotation synchronization problem. In this article, we derive an efficient implementation of the method and develop a convergence theory thereof. A structural parameter appears in the proof, which has a significant influence on the convergence basin. In this article, we show that this structural parameter is the norm of the inverse of the reduced graph Laplacian and obtains the explicit relation of this parameter for special graph structures. We also present another method that directly solves the pose synchronization using both relative rotation and translation observations. Experimental results show that our rotation synchronization method can be successfully used to initialize iterative PGO solvers. Furthermore, we show that our pose synchronization algorithm outperforms state-of-the-art solvers in high-noise cases.

Pose Graph Optimization (PGO) is an important optimization problem arising in robotics and machine vision applications like 3D reconstruction and 3D SLAM. Each node of pose graph corresponds to an orientation and a location. The PGO problem finds orientations and locations of the nodes from relative noisy observation between nodes. Recent investigations show that well-known iterative PGO solvers need good initialization to converge to good solutions. However, we observed that state-of-the-art initialization methods obtain good initialization only in low noise problems, and they fail in challenging problems having more measurement noise. Consequently, iterative methods may converge to bad solutions in high noise problems. In this paper, a new method for obtaining orientations in the PGO optimization problem is presented. Like other well-known methods the initial locations are obtained from the result of a least-squares problem. The proposed method iteratively approximates the problem around current estimation and converts it to a least-squares problem. Therefore, the method can be seen as an iterative least-squares method which is computationally efficient. Simulation results show that the proposed initialization method helps the most well-known iterative solver to obtain better optima and significantly outperform other solvers in some cases.

In a wheeled-tip manipulation system, the wheels at the tip of robot fingers grasp objects and manipulate them by rolling over their boundaries. In this paper, we introduce a 2-D kinematic modeling for wheeled-tip manipulation systems in order to handle rolling over objects' corners in the manipulation. The modeling facilitates motion planning through projecting grasp stability conditions into configuration space, which unifies the planning of the grasp stability and obstacle avoidance. It is done through defining a static force closure map independent of the obstacles and the robot mechanism. This results in a straightforward planning in PRM framework. The simulation and experimental results support the approach.

Accurate depth perception serves as a valuable piece of information for environmental understanding. Ground plane estimation is considered as an important part of a complete depth perception algorithm. In this paper, we devise a method to estimate a ground plane from a single static image. We introduce an ensemble of features to be extracted on predicted ground pixels and follow a different, but simpler, approach from the previous works to estimate the depths. Powerful gradient boosting regression instead of linear parameter estimation yields fascinating results as baseline depth estimation. Finally, our RANSAC based depth smoothing with the ability to reject outliers achieves current state of the art results.

In general, imitation is imprecisely used to address different levels of social learning from high-level knowledge transfer to low-level regeneration of motor commands. However, true imitation is based on abstraction and conceptualization. This article presents a model for conceptual imitation through interaction with the teacher to abstract spatio-temporal demonstrations based on their functional meaning. Abstraction, concept acquisition, and self-organization of proto-symbols are performed through an incremental and gradual learning algorithm. In this algorithm, Hidden Markov Models (HMMs) are used to abstract perceptually similar demonstrations. However, abstract (relational) concepts emerge as a collection of HMMs irregularly scattered in the perceptual space but showing the same functionality. Performance of the proposed algorithm is evaluated in two experimental scenarios. The first one is a human-robot interaction task of imitating signs produced by hand movements. The second one is a simulated interactive task of imitating whole body motion patterns of a humanoid model. Experimental results show efficiency of our model for concept extraction, proto-symbol emergence, motion pattern recognition, prediction, and generation.

In this paper we present a Disaster Invariant Feature (DIF), which is used for localization of Unmanned Aerial Vehicles (UAV). There exist numerous researches that address the problem of localization of UAVs using aerial images. However, after a disaster such as a tornado or an earthquake many features in aerial images like monuments and unique buildings may change, and the image-based localization would become hard or even impossible. Consequently it is important to find features that remain unchanged or with fairly small changes, and can be detected both before and after a disaster. We have used a recent method for street detection from aerial images and shown that road networks and segments are disaster invariant and could be utilized for localization and mapping. The algorithm has been implemented and tested on satellite images from Google, with nearly equivalent resolution to aerial images. The successful result of detecting this DIF on Port-au-Prince, in Haiti, images before and after the recent earthquake is presented.

Most of the central pattern generator (CPG) models are based on defining explicit dynamical systems and finding the appropriate parameters. In this paper, we propose a novel CPG model that is based on altering a nonlinear oscillator to obtain desired limit cycle behavior. This CPG model benefits from an explicit basin of attraction and also fast convergence behavior. The presented CPG model is used in an imitation model that tries to learn the proper periodical behavior by looking at a mentor. First, a mentor performs the desired periodical behavior. Then, a hand-eye coordination process, inspired from infant babbling, is initiated to extract proper motor actions from what is observed. The extracted motor actions are finally embedded into the CPG model for smooth reproduction. This imitation model is implemented on a robotic marionette behavior learning task. The outcome of the final performance of the robotic marionette is behaviorally understandable smooth actions.

In this paper, we propose a fast algorithm for gesture recognition based on the saliency maps of visual attention. A tuned saliency-based model of visual attention is used to find potential hand regions in video frames. To obtain the overall movement of the hand, saliency maps of the differences of consecutive video frames are overlaid. An improved characteristic loci feature extraction method is introduced and used to code obtained hand movement. Finally, the extracted feature vector is used for training SVMs to classify the gestures. The proposed method along a hand-eye coordination model is used to play a robotic marionette and an approval/rejection phase is used to interactively correct the robotic marionette's behavior.

In this paper, we present a robotic pole climber that can be used for moving up lighting poles, telephone line poles, or similar poles for the purpose of cleaning, maintenance, or inspection. The proposed design is inspired from human climbers, which use a strap and their weight to stably climb poles. The major advantage of this design is in its capability of carrying high payloads and its natural stability. The other features of the robot are its simple design, ease of control, light weight, simple mechanism and fast climbing speed.

Presented in this paper is an approach to realtime spatial reasoning for manipulative robotic tasks. When a service robot is requested to manipulate an object, it should determine the directions along which it can access and remove the object. The potential accessible directions for the object are retrieved from the object database. Then, spatial reasoning with the surrounding environment and the gripper geometry is invoked to verify the directions. The verification process mainly utilizes the visibility test of the commodity graphics hardware. Then, the directions along which both of the object and gripper are translated without colliding with the surrounding obstacles are computed using Minkowski sum and cube map of the graphics hardware. The access and removal directions are passed to the potential field path planning algorithm to determine the robot arm's full path for accessing, removing and delivering the object. The experimental results show the feasibility of using graphics hardware for manipulative robotic tasks and further its performance gain in real-time manipulation.

This paper presents an effective and real-time approach for detecting walls in indoor environment. This approach relies on the fact that the rear of the opaque walls is not visible. Thus, to detect the walls in an indoor environment a set of hypothetical walls, based on the ceiling edges or ground level edges, are considered; and their validity is checked using point cloud, generated by a sensor. A certainty factor is calculated for each detected wall, which is updated continuously based on the newly gathered sensory information. Furthermore, the certainty of the walls can be updated using other source of information for better and more reliable wall detection. The novelty of this approach is in its capability to handle environments, with texture-less walls, in real-time. The algorithm has been implemented in simulation, and tested in real environment and has shown effective, reliable and real-time performance

This paper presents a novel approach to accessibility analysis for manipulative robotic tasks. The workspace is captured using a stereo camera, and heterogeneously modeled with the recognized plane features, recognized objects with complete solid models, and unrecognized 3D point clouds organized with a multi-resolution octree. When the service robot is requested to manipulate a recognized object, the local accessibility information for the object is retrieved from the object database. Then, accessibility analysis is done to verify the object accessibility and determine the global accessibility. The verification process utilizes the visibility query, which is accelerated by graphics hardware. The experimental results show the feasibility of real-time and behavior-oriented 3D modeling of workspace for robotic manipulative tasks, and also the performance gain of the hardware-accelerated accessibility analysis obtained using the commodity graphics card.

The design of an assembly line for a mechanical assembly has to satisfy all the geometrical and the physical constraints presented in the assembly such as blocking relation and contact forces. Given a desired final assembly, determining an appropriate assembly sequence which satisfies not only the blocking constraints but also the force constraints needs a proper model to directly provide the information needed to reason about assembly. We introduce a representation, the directional force graph, which explicitly describes how parts interact in the assembly. This representation is used to determine disassemblable parts that are naturally broken apart from an assembly by a decomposition force. A decomposition force is an external force applied to a held part(s) against a fixture part(s). The proposed approach provides a mechanism to explicitly incorporate the real-world constraints of assembly directions, fixturing, and tooling requirements into planning. We describe a complete planning algorithm and report the results.

Robot soccer competition provides an excellent opportunity for robotics research. In particular, robot players in a soccer game must perform real-time visual recognition, navigate in a dynamic field, track moving objects, collaborate with teammates, and strike the ball in the correct direction. All these tasks demand robots that are autonomous (sensing, thinking, and acting as independent creatures), efficient (functioning under time and resource constraints), cooperative (collaborating with each other to accomplish tasks that are beyond individual's capabilities), and intelligent (reasoning and planing actions and perhaps learning from experience). Furthermore, all these capabilities must be integrated into a single and complete system. To build such integrated robots, we should use different approaches from those employed in separate research disciplines. This paper describes our experience (problems and solutions) in this aspect for building soccer robots. Our robots share the same general architecture and basic hardware, but they have integrated abilities to play different roles and utilize different strategies in their behavior. Our philosophy in building these robots is to use the least possible sophistication to make them as robust as possible. In RoboCup97, our Dreamteam robots performed well (scored 8 of 9 goals of all teams in the league) and won the world championship in the middle-sized robot league.

In this paper a method for collision detection and collision avoidance for dual arm robots is proposed. The collision detection, a fast geometric approach based on link intersection, detects the collision and constructs the collision region for given trajectories. The time delay planning determines the minimum necessary time delay to avoid collisions using a potential field representation for collision regions. The planning is based on a flexible, massively parallel approach. It effectively avoids any local minima problems due to the potential field representation and can be used regardless of the complexity of the collision region (e.g., concave or complicated regions).

For high-volume assembly, "hard automation" systems consisting of a pipelined series of simple operations are often preferred over multi-axis robots for reasons of cost, speed, and precision. Given a desired final assembly, designing an appropriate assembly system requires the intuition of experienced designers who require up to six months to produce a design and may overlook a better design or fail to find a design when one exists. Thus there is a need for CAD tools that can assist the designers of assembly hardware and to give rapid feedback to product designers to facilitate design for assembly. We introduce a class of vertical assembly (VA) plans such that any valid VA plan can be "compiled" into a hard automation assembly system. VA plans consist of vertical insertions alternated with rotations such that parts and subassemblies at each stage sit stably on conveyor belts without fixtures. For an assembly with n vertices, we can decide if a VA plan exists in time O(n/sup 4/). We describe a complete and implemented planning algorithm that takes as input a 2D slice of an assembly consisting of polygonal parts and returns all valid VA plans ranked by a quality metric.