This paper describes the dynamic window approach to reactive collision avoidance for mobile robots equipped with synchro-drives. The approach is derived directly from the motion dynamics of the robot and is therefore particularly well-suited for robots operating at high speed. It differs from previous approaches in that the search for commands controlling the translational and rotational velocity of the robot is carried out directly in the space of velocities. The advantage of our approach is that it correctly and in an elegantway incorporates the dynamics of the robot. This is done by reducing the search space to the dynamic window, which consists of the velocities reachable within a short time interval. Within the dynamic window the approach only considers admissible velocities yielding a trajectory on which the robot is able to stop safely. Among these velocities the combination of translational and rotational velocity is chosen by maximizing an objective function. The objective function includes a measure of progress towards a goal location, the forward velocity of the robot, and the distance to the next obstacle on the trajectory. In extensive experiments the approach presented here has been found to safely control our mobile robot RHINO with speeds of up to 95 cm/sec, in populated and dynamic environments.

Research on mobile robot navigation has produced two major paradigms for mapping indoor environments: grid-based and topological. While grid-based methods produce accurate metric maps, their complexity often prohibits efficient planning and problem solving in large-scale indoor environments. Topological maps, on the other hand, can be used much more efficiently, yet accurate and consistent topological maps are considerably difficult to learn in large-scale environments. This paper describes an approach that integrates both paradigms: grid-based and topological. Grid-based maps are learned using artificial neural networks and Bayesian integration. Topological maps are generated on top of the grid-based maps, by partitioning the latter into coherent regions. By combining both paradigms—grid-based and topological—, the approach presented here gains the best of both worlds: accuracy/consistency and efficiency. The paper gives results for autonomously operating a mobile robot equipped with sonar sensors in populated multi-room environments.

This chapter surveys basic methods for learning maps and high speed autonomous navigation for indoor mobile robots. The methods have been developed in our lab over the past few years, and most of them have been tested thoroughly in various indoor environments. The chapter is targeted towards researchers and engineers who attempt to build reliable mobile robot navigation software.

Autonomous robots must be able to learn and maintain models of their environments. Research on mobile robot navigation has produced two major paradigms for mapping indoor environments: grid-based and topological. While grid-based methods produce accurate metric maps, their complexity often prohibits efficient planning and problem solving in large-scale indoor environments. Topological maps, on the other hand, can be used much more efficiently, yet accurate and consistent topological maps are often difficult to learn and maintain in large-scale environments, particularly if momentary sensor data is highly ambiguous. This paper describes an approach that integrates both paradigms: grid-based and topological. Grid-based maps are learned using artificial neural networks and naive Bayesian integration. Topological maps are generated on top of the grid-based maps, by partitioning the latter into coherent regions. By combining both paradigms, the approach presented here gains advantages from both worlds: accuracy/consistency and efficiency. The paper gives results for autonomous exploration, mapping and operation of a mobile robot in populated multi-room environments.

To operate successfully in indoor environments, mobile robots must be able to localize themselves. Over the past few years, localization based on landmarks has become increasingly popular. Virtually all existing approaches to landmark-based navigation, however, rely on the human designer to decide what constitutes appropriate landmarks. This paper presents an approach that enables mobile robots to select their landmarks by themselves. Landmarks are chosen based on their utility for localization. This is done by training neural network landmark detectors so as to minimize the a posteriori localization error that the robot is expected to make after querying its sensors. An empirical study illustrates that self-selected landmarks are superior to landmarks carefully selected by a human. The Bayesian approach is also applied to control the direction of the robot's camera, and empirical data demonstrates the appropriateness of this approach for active perception. The author is also affiliate...

This paper describes practical, effective approaches to stereo perception and dead reckoning, and presents results from systems implemented for a prototype lunar rover operating in natural, outdoor environments. The stereo perception hardware includes a binocular head mounted on a motion-averaging mast. This head provides images to a normalized correlation matcher, that intelligently selects what part of the image to process (saving time), and subsamples the images (again saving time) without subsampling disparities (which would reduce accuracy). The implementation has operated successfully during long-duration field exercises, processing streams of thousands of images. The dead reckoning approach employs encoders, inclinometers, a compass, and a turn-rate sensor to maintain the position and orientation of the rover as it traverses. The approach integrates classical odometry with inertial guidance. The implementation succeeds in the face of significant sensor noise by virtue of senso...

Abstract. We present an approach to the landmark-based robot localization problem for environments, such as RoboCup middle-size soccer, that provide limited or low-quality information for localization. This approach allows use of different types of measurements on potential landmarks in order to increase landmark availability. Some sensors or landmarks might provide only range (such as field walls) or only bearing measurements (such as goals). The approach makes use of inexpensive sensors (color vision) using fast, simple updates robust to low landmark visibility and high noise. This localization method has been demonstrated in laboratory experiments and RoboCup 2001. Experimental analysis of the relative benefits of the approach is provided. 1

New soft-computing architectures and approaches are de- manded for the control and operating systems of service robots [1]. In this paper, a fuzzy logic controlled autonomous vehicle - MORIA -, is presented. For achieving sophisticated guiding and controlling properties, local actions and global strategies are combined within the fuzzy controller. Local perceptions and global commands influence the recurrent fuzzy state variables, which on their turn activate different fuzzy rule sets. Thus, the fuzzy controller has a context dependent behaviour. Key words: mobile robots; recurrent fuzzy systems; goal-oriented navigation; collision avoidance; real-time control; autonomous vehicles I Objectives of the Research Project The main goal of our current research project is the development of a collision-free autonomous vehicle for unknown indoor environments. One of the main feature of such a service robot is its ability to locate itself on an existing map [2]. Therefore it has to create a map of its local surroundings based on the information recorded by its sensors. This local map is then steadily compared to the global map previously stored in memory. Furthermore, a global path planning system generates local instructions for the navigation system, in order to reach predefined goals. Based on this approach, the planner and the navigator are robust against uncertainties und unpredictable situations, which come up during the exploration or goal-oriented navigation of the system.

An important function for wearable computers is the recognition of places and locations. This paper proposes an image sequence matching technique for the recognition of previously visited places. Similar in spirit to single word recognition in speech recognition, a dynamic programming algorithm is proposed for the calculation of dissimilarities of video sequences. Such video sequences represent not only the place itself but also the approaching trajectory. The algorithm uses a simple and robust representation of a single frame without compromising the discrimination between different places. Preliminary experimental results demonstrate the discrimination and the robustness of the approach with respect to the angle of the approaching trajectory. 1. Introduction Computers and cameras are becoming small enough to wear. Computers are being equipped with cameras, microphones and other sensors, which can be used to interpret what people are doing, where they are and with whom they are inte...

This paper addresses path planning with uncertainty for a carlike robot subject to conguration uncertainty. The robot estimates its configuration with odometry and an absolute localization device based on environmental feature matching. The issue is to compute safe paths that guarantee that the goal will be reached in spite of the uncertainty. The solution proposed relies upon the automatic construction of a set of landmarks characterized by (1) a region of the configuration space, (2) the `best' features for localization in this region, and (3) a perception uncertainty field that measures how well a feature is perceived at each configuration in the region. The landmarks are used within an efficient roadmap-based path planning algorithm that returns a safe motion plan that alternates motion along safe paths and localization operations.