Medical image segmentation plays a vital role in numerous applications and has gained significant attention since the introduction of the U-Net model, which enabled convolutional neural networks to achieve high performance with manageable computational costs. Recently, attention mechanisms have emerged as a promising approach to enhance model performance by emphasizing relevant features while suppressing irrelevant ones. This study explores the integration of channel and spatial attention mechanisms into the U-Net architecture, evaluating their impact on segmentation performance and computational cost. Experiments conducted on six public medical imaging datasets demonstrated performance improvements, with Intersection over Union (IoU) gains ranging from 1.62% to 33.66% compared to the original U-Net. These results highlight the potential of attention mechanisms to significantly improve the efficiency and effectiveness of medical image segmentation models.

Autonomous vehicles must be capable of driving safely and having some level of social compliance with human drivers. Acting egoistically can make other drivers to take undesirable actions, such as performing hard brakes to avoid collisions. Designing a proper behavior involves dealing with antagonistic objectives, such as increasing speed and avoiding rear-end collisions. However, weighting those objectives in a reward or cost function is an error-prone and time-consuming task, and can become very hard as more features are added to the problem. In this regard, the main objective of this paper is to use learning from demonstration to compute trajectories that mimic human expert behavior without the need of manually tuning a reward function. On this subject, we present a variation of the well-known Maximum Entropy Inverse Reinforcement Learning algorithm in order to deal with continuous state spaces: instead of exactly computing the gradients, they are estimated by sampling trajectories in regions with higher rewards using a Monte Carlo Tree Search based sampler. The sampler is applied to solve an interaction-aware Markov Decision Problem capable of dealing with the inherent interaction and uncertainty present in surrounding vehicles motion. Experiments are performed in a merging scenario considering real data, showing that the proposed method can generate trajectories similar to the ones executed by human drivers. Additionally, favorable results are achieved when compared to traditional baseline methods and also to a variant of Inverse Reinforcement Learning that uses a polynomial-curve trajectory sampler.

Intention prediction (IP) is a challenging task for intelligent vehicle’s perception systems. IP provides the likelihood, or probability, of a target vehicle to perform a maneuver subjected to a finite set of possibilities. There are many factors that influence the decision-making process of a driver, which should be considered in a prediction framework. In addition, the lack of labeled large-scale dataset with maneuver annotation imposes another challenge to the task. This paper proposes an Interaction-aware Maneuver Prediction framework, called IAMP, using interaction graphs to extract complex interaction features from traffic scenes. In addition, we explored a semi-supervised approach called Noisy Student to take advantage of unlabeled data in the training step. Experimental results show relevant improvement when using unlabeled data, increasing the average performance of a classifier by 7.17% of accuracy. Moreover, this approach also made it possible to obtain an intention predictor with similar results to a classifier., even when using a shorter observation horizon.

Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization. A common way to learn multiple tasks is through the hard parameter sharing approach, in which a single architecture is used to share the same subset of parameters, creating an inductive bias between them during the training process. Due to its simplicity, potential to improve generalization, and reduce computational cost, it has gained the attention of the scientific and industrial communities. However, tasks often conflict with each other, which makes it challenging to define how the gradients of multiple tasks should be combined to allow simultaneous learning. To address this problem, we use the idea of multi-objective optimization to propose a method that takes into account temporal behaviour of the gradients to create a dynamic bias that adjusts the importance of each task during backpropagation. The result of this method is to give more attention to tasks that are diverging or not being benefited during the last iterations, ensuring that the simultaneous learning is heading to the performance maximization of all tasks. As a result, we empirically show that the proposed method outperforms the state-of-the-art approaches on learning conflicting tasks. Unlike the adopted baselines, our method ensures that all tasks reach good generalization performances.

To autonomously navigate in traffic roads, an Autonomous Vehicle must take into account perception information, as well as the topological and geometric structure of the environment it is inserted in. Specifically in urban scenarios, the vehicle has to plan its path across intersections, roundabouts and perform lane changes to obey traffic rules. In addition, the planning algorithm must also consider the kinematics constraints of the vehicle and comfort parameters to the passengers. This paper proposes a road network model based on clothoids, which embraces the geometric and topological representation of the environment in a compact data structure. Piecewise linear continuous-curvature paths composed of clothoids, circular arcs, and straight lines are used for this purpose. The proposed approaches are evaluated in an urban scenario composed of curved and straight roads with single and double lanes, roundabouts, and intersections. As a result, a navigation architecture for Autonomous Vehicles was developed using the model, including global planning with continuous-curvature paths.

Advanced driver assistance systems are responsible for assisting decision making and can play an important role in safety and traffic efficiency. Such systems require robust perception methods to handle complex urban scenes, and one way to achieve this is through instance segmentation. However, due to the difficulty in separating overlapping objects into different instances, this task becomes very challenging. For this, several authors proposed CNN-based methods and used depth information to enhance the instance segmentation performance. A promising way to explore this information is by adopting a multi-task learning approach, in which multiple tasks are learned simultaneously by sharing the same architecture. Usually, this combination is made by the weighted sum of loss functions, in which the weight of each task is defined manually. Nonetheless, when tasks have different natures with variation in the order of magnitude, performing this combination during training so that all tasks converge towards their optimal solution is not trivial. Aiming to get the best possible solution, we modeled the multi-task learning as a multiobjective optimization problem and, as the main contribution of this paper, we proposed a greedy approach to find the weighting coefficients for each task, performing a trade-off between tasks that allow the optimization of multiple loss functions. Experimental results showed that it is possible to enhance instance segmentation when depth information is properly explored. Moreover, not only did depth information help instance segmentation, but also did the instance segmentation help the depth estimations, achieving better performance compared to single-task models.

Deep Reinforcement Learning (DRL) represents an interesting class of algorithms, since its objective is to learn a behavioral policy through interaction with the environment, leveraging the function approximation properties of neural net-works. Nonetheless, for episodic problems, it is usually modeled to deal with a unique goal. In this sense, some works showed that it is possible to learn multiple goals when using a Universal Value Function Approximator (UVFA), i.e. a method to learn a universal policy by taking information about the current state of the agent and the goal. Their results are promising but show that there is still space for new contributions regarding the integration of the goal information into the model. For this reason, we propose using the Hadamard product or the Gated-Attention module in the UVFA architecture for visual-based problems. Also, we propose a hybrid exploration strategy based on the ε-greedy and the categorical probability distribution, namely ε-categorical. By systematically comparing different architectures of UVFA for different exploration strategies, and applying or not the Trust Region Policy Optimization (TRPO), we demonstrate through experiments that, for visual topologic navigation, combining visual information of the current and goal states through Hadamard product or Gated-Attention module allows the network learning near-optimal navigation policies. Also, we empirically show that the ε-categorical policy helps to avoid local minimums during the training, which facilitates the convergence to better results.

The present work demonstrates how an autonomous navigation system of `End-to-End' deep learning principles is directly improved in its response process, depending on the information obtained by different input images configurations. For this, a methodology was developed to allow working with RGB and depth images, which were obtained through a Microsoft Kinect V2 sensor device. Three cameras were used for this experiment. The images of the different cameras were concatenated or grouped, generating new and different input configurations from the vision system. To develop the presented methodology, two support and validation systems were implemented. Through the process of computer simulation, it was able to test the first approaches and define the most important ones. In order to validate the proposed methodology and solutions in real world situations, a 1/4 scale automotive vehicle was prototyped. Finally, the experiments shows the importance of the use of multi-cameras systems for a better performance of autonomous navigation systems based on End-to-End learning approach, heaving an average error of 2.41 degrees in the best configuration tested, with three RGB cameras.

The recent precision increase in image-based depth estimation encourages to use this type of data for mapping. Recent work proposes different approaches to deal with the problem of occlusion generated by different scene perspectives of stereo cameras. However, there is less attention to depth estimation and inpainting for object removal and object occlusion. In this paper, we study recent inpainting approaches for RGB images and apply these methods on depth maps. We propose a Generative Adversarial Network (GAN) for depth feature extraction to estimate the depth inside a masked area, in order to remove objects on disparity images. Our results show that using depth features on the loss function and on the network architecture, increase the result precision and give to the generated image a depth distribution close to the real data. Our main contribution is a GAN, which estimates depth information in a masked area inside a disparity image.

Pedestrians and vehicles often share the road in complex inner city traffic. This leads to interactions between the vehicle and pedestrians, with each affecting the other's motion. In order to create robust methods to reason about pedestrian behavior and to design interfaces of communication between self-driving cars and pedestrians we need to better understand such interactions. In this paper, we present a data-driven approach to implicitly model pedestrians' interactions with vehicles, to better predict pedestrian behavior. We propose a Long Short-Term Memory (LSTM) model that takes as input the past trajectories of the pedestrian and ego-vehicle, and pedestrian head orientation, and predicts the future positions of the pedestrian. Our experiments based on a real-world, inner city dataset captured with vehicle mounted cameras, show that the usage of such cues improve pedestrian prediction when compared to a baseline that purely uses the past trajectory of the pedestrian.

Interaction among vehicles based on wireless communication technologies is an efficient way to improve traffic conditions and safety. In this context, The Grand Cooperative Driving Challenge (GCDC) is an event that aims at developing cooperative systems for intelligent vehicles. Although the two editions of the event (2011 and 2016) have provided conditions for a series of experiments such as platoon stability and lane-merging, the traffic flow in lane-merging scenarios didn't receive so much attention. This paper presents a preliminary study on traffic flow using GCDC 2016 interaction protocol for lane-merging by varying the driver imperfection model and the number of vehicles. We also propose an extension of the standard protocol. We evaluated three lane-merging interaction protocols using the Simulation of Urban Mobility (SUMO). The first protocol is very similar to the GCDC 2016, the second is the default lane change model commonly used in SUMO and the third is a variation of the GCDC interaction protocol. The experiments were conducted using similar conditions and number of vehicles of the event. We analyzed the lane-merging total time for all vehicles to complete the maneuver, the maximum string platoon length and the average platoon speed. Therefore, we could observe that the interaction protocol extension proposed decreased the duration time to complete the lane-merging maneuver of all vehicles without drastically compromising maximum string length and average platoon speed. The flexibility of this extension is closer to real traffic scenario, in which vehicles can perform the merge without having a pre-defined order.

The instance segmentation problem intends to precisely detect and delineate objects in images. Most of the current solutions rely on deep convolutional neural networks but despite this fact proposed solutions are very diverse. Some solutions approach the problem as a network problem, where they use several networks or specialize a single network to solve several tasks. A different approach tries to solve the problem as an annotation problem, where the instance information is encoded in a mathematical representation. This work proposes a solution based in the DCME technique to solve the instance segmentation with a single segmentation network. Different from others, the segmentation network decoder is not specialized in a multi-task network. Instead, the network encoder is repurposed to classify image objects, reducing the computational cost of the solution.

Semantic segmentation of images is an important issue for intelligent vehicles and mobile robotics because it offers basic information which can be used for complex reasoning and safe navigation. Different solutions have been proposed for this problem along the last two decades, where recent deep neural networks approaches have shown very promising results in the context of urban navigation. One of the main problems when comparing different semantic segmentation solutions is how to select an appropriate metric to evaluate their accuracy. On the one hand, classic metrics do not measure properly the accuracy on the object contours, which is important in urban driving to differentiate road from sidewalk for instance. On the other hand, contour-based metrics [1] disregard the information far from class contours. This paper explores the problem multi-modal image segmentation, and presents a new metric to leverage global and contour accuracy in a simple formulation. This metric is validated with the evaluation of several semantic segmentation solutions that exploit RGB-D images to rank these solutions taking into account the quality of the segmented contours. We also present a comparative analysis of several commonly used metrics together with a statistical analysis of their correlation.

Map-aided localization methods have been employed for vehicle localization to overcome the limitations of global navigation satellite system (GNSS) devices. In this solution, sensor information is matched to the environment map to determine the vehicle position. Occupancy grid maps (OGMs) have been adapted for map-aided localization. However, there are known drawbacks of OGM, such as the environment discretization, the assumption of independence between grid cells, and the need for dense measurements. In recent years, Gaussian process occupancy map (GPOM) was developed to suppress some of the OGM limitations. GPOM enables the computation of the likelihood of occupancy at any location, even if not directly observed by the sensor, thus representing the environment in a continuous manner. Taking into account the superiority of GPOM over OGM, we devise a novel vehicle localization technique for urban environments. This solution enables more accurate localization due to the use of a representation that better models the real environment. The development of the proposed method is based on Monte Carlo localization, which is a popular map-aided localization method. Two road features commonly found in urban cities were chosen to build the maps: road curbs and road markings. Specifically, the proposed localization method relies on a GPOM constructed with curb data and an OGM built with road marking data. Experiments were performed in real urban environments. Maps were intentionally generated using sparse light detection and ranging (LIDAR) data to verify the localization in non-observed areas. The localization system was evaluated by comparing the results with a high precision GNSS device.

Road traffic crashes have been the leading cause of death among young people. Most of these accidents occur when the driver becomes distracted due to fatigue or external factors. Vehicle platooning systems, as cooperative adaptive cruise control, are one of the results of efforts devoted to the development of technologies for decreasing the number of road crashes and fatalities. Previous studies have suggested that such systems improve up to 273% highway traffic throughput and over 15% of fuel consumption if the clearance between vehicles in this class of roads can be reduced to 2 m. In this paper, we propose an approach that guarantees a minimum safety distance between vehicles taking into account the overall system delays and braking capacity of each vehicle. An l∞-norm robust model predictive controller has been developed to guarantee the minimum safety distance is not violated due to uncertainties on the preceding vehicle behavior. A formulation for a lower bound clearance of vehicles inside a platoon is also proposed. Simulation results show the performance of the approach compared to a nominal controller when the system is subject to both modeled and unmodeled disturbances.

Road detection is a crucial task in autonomous navigation systems. It is responsible for delimiting the road area and hence the free and valid space for maneuvers. In this paper, we consider the visual road detection problem where, given an image, the objective is to classify every of its pixels into road or non-road. We address this task by proposing a convolutional neural network architecture. We are especially interested in a model that takes advantage of a large contextual window while maintaining a fast inference. We achieve this by using a Network-in-Network (NiN) architecture and by converting the model into a fully convolutional network after training. Experiments have been conducted to evaluate the effects of different contextual window sizes (the amount of contextual information) and also to evaluate the NiN aspect of the proposed architecture. Finally, we evaluated our approach using the KITTI road detection benchmark achieving results in line with other state-of-the-art methods while maintaining real-time inference. The benchmark results also reveal that the inference time of our approach is unique at this level of accuracy, being two orders of magnitude faster than other methods with similar performance.

The mapping of agricultural crops by capturing images obtained with UAVs enables fast environmental monitoring and diagnosis in large areas. Airborne monitoring in agriculture can a substantially impacts on the identification of diseases and produce accurate information on affected areas. The problem can be formulated as a classification task on aerial images with significant opportunities to impact other fields. This paper presents an active learning method through route planning for improvements in the knowledge on visited areas and minimization uncertainties about the classification of diseases in crops. Binary Logistic Regression and Gaussian Process were used for the detection of pathologies and map interpolation, respectively. A Bayesian optimization strategy is also proposed for the planning of an informative trajectory, which resulted in a maximized search for affected areas in an initially unknown environment.

Localization is an important component of autonomous vehicles, as it enables the accomplishment of tasks, such as path planning and navigation. Although vehicle position can be obtained by GNSS devices, they are susceptible to errors and satellite signal unavailability in urban scenarios. Several map-aided localization solution methods have been proposed in the literature, but mostly for indoor environments. Maps used for localization store relevant environmental features that are extracted by a detection method. However, many feature detection methods do not consider the presence of dynamic obstacles or occlusions in the environment, which can impair the localization performance. In order to detect curbs even in occluding scenes, we developed a method based on ring compression analysis and least trimmed squares. For road marking detection, we developed a modified version of the Otsu thresholding method to segment road painting from road surfaces. Finally, the feature detection methods were integrated with a Monte Carlo localization method to estimate the vehicle position. Experimental tests in urban streets have been used to validate the proposed approach with favorable results.

One of the challenges in precision agriculture is the detection of diseased crops in agricultural environments. This paper presents a methodology to detect the Ceratocystis wilt disease in Eucalyptus crops. An unmanned aerial vehicle is used to obtain high-resolution RGB images of a predefined area. The methodology enables the extraction of visual features from image regions and uses several supervised machine learning (ML) techniques to classify regions into three classes: ground, healthy and diseased plants. Several learning techniques were compared using data obtained from a commercial Eucalyptus plantation. Experimental results show that the GP learning model is more reliable than the other learning methods for accurately identifying diseased trees.

A key challenge for long-term autonomy is to enable a robot to automatically model properties of the environment while actively searching for better decisions to accomplish its task. This amounts to the problem of exploration-exploitation in the context of active perception. This paper addresses active perception and presents a technique to incrementally model the roughness of the terrain a robot navigates on while actively searching for waypoints that reduce the overall vibration experienced during travel. The approach employs Gaussian processes in conjunction with Bayesian optimisation for decision making. The algorithms are executed in real-time on the robot while it explores the environment. We present experiments with an outdoor vehicle navigating over several types of terrains demonstrating the properties and effectiveness of the approach.

Robust and stable control is a requirement for navigation of self-driving cars. Some approaches in the literature depend on a high number of parameters that are often difficult to estimate. A poor selection of these parameters often reduces considerably the efficiency of the control algorithms. In this paper we propose a simplified control system for autonomous vehicles that depends on a reduced number of parameters that can be easily set. This control system is composed of longitudinal and lateral controllers. The longitudinal controller is responsible for regulating the vehicle's cruise velocity while the lateral controller steers the vehicle's wheels for path tracking. Simulated and experimental tests have been carried out with the CaRINA II platform in the university campus with positive results.

The detection of a traffic light on the road is important for the safety of persons who occupy a vehicle, in a normal vehicles or an autonomous land vehicle. In normal vehicle, a system that helps a driver to perceive the details of traffic signals, necessary to drive, could be critical in a delicate driving manoeuvre (i.e crossing an intersection of roads). Furthermore, traffic lights detection by an autonomous vehicle is a special case of perception, because it is important for the control that the autonomous vehicle must take. Multiples authors have used image processing as a base for achieving traffic light detection. However, the image processing presents a problem regarding conditions for capturing scenes, and therefore, the traffic light detection is affected. For this reason, this paper proposes a method that links the image processing with an estimation state routine formed by Hidden Markov Models (HMM). This method helps to determine the current state of the traffic light detected, based on the obtained states by image processing, aiming to obtain the best performance in the determination of the traffic light states. With the proposed method in this paper, we obtained 90.55% of accuracy in the detection of the traffic light state, versus a 78.54% obtained using solely image processing. The recognition of traffic lights using image processing still has a large dependence on the capture conditions of each frame from the video camera. In this context, the addition of a pre-processing stage before image processing could contribute to improve this aspect, and could provide a better results in determining the traffic light state.

An autonomous car must have a robust perception system to navigate safely in urban streets. An important issue of environment perception is the road (navigable area) detection and the identification of the road geometry. The road geometry information can be used to determine the vehicle control according to the street and also for topological localization. Existing road geometry identifiers only work with a limited number of classes and, due to the use of cameras, some solutions depend on filters to deal with shadows and light variations. This paper presents a road detector that extracts curb and navigable surface information from a multilayer laser sensor data. The road data was trained with an artificial neural network (ANN) and classified into eight road geometries: straight road, left turn, right turn, left side road, right side road, T intersection, Y intersection and crossroad. The main advantage of our method is its robustness to light variations for detecting distinct roads even in the presence of noisy data thanks to the ANN. In order to determine which road information has the best features for ANN training, three approaches were explored: ANN trained with curb data, ANN trained with surface data and ANN trained with both curb and surface data. Performed experiments resulted in the superiority of the network trained with both curb and surface data, with an accuracy of 0.91799. The trained ANN was validated in different urban scenarios and, evaluating a 1 Km track, we obtained a 94.48% of correct classifications. These results are superior than other works that detect fewer number of road shapes.

Curb detection is an important capability for autonomous ground vehicles in urban environments. It is particularly useful for path planning and safe navigation. Another important task that can benefit from curb detection is localization, which is also a major requirement for self-driving cars. There are several approaches for identifying curbs using stereo cameras and 2D LIDARs in the literature. Stereo cameras depend on image pair matching methods to obtain depth information. Although 2D LIDARs being able to directly return this information, only few curb points can be detected using this sensor. In this work we propose the use of a 3D LIDAR which provides a dense point cloud and thus make possible to detect a larger extent of the curb. Our approach introduces the use of robust regression method named least trimmed squares (LTS) to deal with occluding scenes in contrast of temporal filters and spline fitting methods. We also used the curb detector as an input of a Monte Carlo localization algorithm, which is capable to estimate the pose of the vehicle without an accurate GPS sensor. We conducted experiments in urban environments to validate both the curb detector and the localization algorithm. Both method delivered successful results in different traffic situations and an average lateral localization error of 0.52655 m in a 800 m track.

Obstacle detection is a fundamental task for Advanced Driver Assistance Systems (ADAS) and Self-driving cars. Several commercial systems like Adaptive Cruise Controls and Collision Warning Systems depend on them to notify the driver about a risky situation. Several approaches have been presented in the literature in the last years. However, most of them are limited to specific scenarios and restricted conditions. In this paper we propose a robust sensor fusion-based method capable of detecting obstacles in a wide variety of scenarios using a minimum number of parameters. Our approach is based on the spatial-relationship on perspective images provided by a single camera and a 3D LIDAR. Experimental tests have been carried out in different conditions using the standard ROAD-KITTI benchmark, obtaining positive results.

An accurate and efficient method for obstacle detection is a key component of a robotic navigation system. Concerning indoor environments, the ground surface can be modeled as a plane (or a set of) and once estimated it can be employed for obstacle detection, e.g. points lying above and below are considered obstacles. The same does not hold for off-road and urban scenarios where one cannot expect planar surfaces or obvious structural patterns. In 2002, Talukder et al. presented a method to deal with such environments. Their method is based on the height difference and “slope” between three-dimensional points. Despite having been used successfully on several occasions, the method has a high computational cost. We propose the use of a Graphics Processing Unit (GPU) to enable its execution in real time. Experiments were performed using a stereo camera and an RGB-D sensor, where the GPU implementation has been compared to multi-core and single-core CPU implementations. The results reveal a significant gain in computational performance, reaching a speedup of almost 80 times in a specific instance.

The development of autonomous vehicles is a highly relevant research topic in mobile robotics. Road recognition using visual information is an important capability for autonomous navigation in urban environments. Over the last three decades, a large number of visual road recognition approaches have been appeared in the literature. This paper proposes a novel visual road detection system based on multiple artificial neural networks that can identify the road based on color and texture. Several features are used as inputs of the artificial neural network such as: average, entropy, energy and variance from different color channels (RGB, HSV, YUV). As a result, our system is able to estimate the classification and the confidence factor of each part of the environment detected by the camera. Experimental tests have been performed in several situations in order to validate the proposed approach.

This paper presents the technical details of Tiriba, which is a small autonomous electrical airplane used into pre-defined missions and applications such as agricultural and environmental monitoring. This class of aircrafts has taken advantage of the miniaturization of electronic components and modules such as GPS receivers, digital cameras, wireless communication equipment, and other sensors. One of the main components of Tiriba is the autopilot module, which is capable to control the aircraft and keep it in a predefined route. This paper addresses the use of model driven development of the system and its multiprocessor platform to support the four components that compose the UAV control software architecture.

Robotic mapping is the process of automatically constructing an environment representation using mobile robots. We address the problem of semantic mapping, which consists of using mobile robots to create maps that represent not only metric occupancy but also other properties of the environment. Specifically, we develop techniques to build maps that represent activity and navigability of the environment. Our approach to semantic mapping is to combine machine learning techniques with standard mapping algorithms. Supervised learning methods are used to automatically associate properties of space to the desired classification patterns. We present two methods, the first based on hidden Markov models and the second on support vector machines. Both approaches have been tested and experimentally validated in two problem domains: terrain mapping and activity-based mapping.

This paper presents a new approach for terrain mapping and classification using mobile robots with 2D laser range finders. Our algorithm generates 3D terrain maps and classifies navigable and non-navigable regions on those maps using Hidden Markov models. The maps generated by our approach can be used for path planning, navigation, local obstacle avoidance, detection of changes in the terrain, and object recognition. We propose a map segmentation algorithm based on Markov Random Fields, which removes small errors in the classification. In order to validate our algorithms, we present experimental results using two robotic platforms.

This paper presents an approach to generating compact 3D maps of urban environments using mobile robots and laser range finders. Our algorithm extracts planar information from 3D point cloud maps. The planar representation is very efficient for representing building structures in urban environments when a high level of detail is not required. We also present preliminary results on 3D geometric mapping with incomplete data. Based on previously known models and incomplete data, our system is able to estimate parts of buildings which have never been seen before. As validation, we present experimental results using a Segway RMP vehicle in two environments, both approximately the size of a city block.

We propose an on-line algorithm for simultaneous localization and mapping of dynamic environments. Our algorithm is capable of differentiating static and dynamic parts of the environment and representing them appropriately on the map. Our approach is based on maintaining two occupancy grids. One grid models the static parts of the environment, and the other models the dynamic parts of the environment. The union of the two provides a complete description of the environment over time. We also maintain a third map containing information about static landmarks detected in the environment. These landmarks provide the robot with localization. Results in simulation and with physical robots show the efficiency of our approach and show how the differentiation of dynamic and static entities in the environment and SLAM can be mutually beneficial.

This paper describes work-in-progress aimed at generating dense 3D maps of urban environments using laser range data acquired from a moving platform. These maps display both fine-scale detail (resolving features only a few centimeters across) and large-scale consistency (typical maps are approximately 0.5 km on a side). In this paper, we sketch a basic 3D mapping algorithm (paying particular attention to practical engineering details) and present preliminary results acquired on the USC University Park campus using a Segway RMP vehicle.