List of Figures. List of Tables. Preface. Acknowledgments. Foreword. 1. Introduction. 2. Superquadrics and their Geometric Properties. 3. Extensions of Superquadrics. 4. Recovery of Individual Superquadrics. 5. Segmentation with Superquadrics. 6. Experimental Results. 7. Applications of Superquadrics. 8. Conclusions. Appendices. References. Author Index. Topic Index.

Segmentation and recovery of superquadrics

In this paper, we focus on some perceptual functions required by a generic task "GOTO" in natural environments; in previous works, only geometrical modeling has been used to deal with two fundamental tasks: landmark extraction and recognition for sensor-based motion control or robot localization, and terrain modeling for motion planning. Geometrical representations alone lead to a bulky model, and, after some iterations, to a combinatorial explosion. We present here, higher level representations; from a range image, given some assumptions on the perceived scene (even ground with few objects), we propose a segmentation algorithm to extract simple semantical representations for the ground and the objects; then, we can analyze the relative positions of the objects to build a topological scene description. Both models constitute the scene model, needed for further incremental environment modeling. >

Natural scene understanding for mobile robot navigation

A map in mobile robotics plays an important role. The mobile robot is vested with a sense of geographical understanding by such a knowledge base for its intelligent behavior. This article is a short survey of map generation for mobile robots. The present author gives a summary of related research works in all the proceedings of IROS until now, and he presents nowadays trends.

Nowadays trends in map generation for mobile robots

In this paper we present the results obtained with a troup of small autonomous vehicles designed to cooperatively explore unknown environments. In order to improve the covering of the explored zone the vehicles show different behaviours. The host that controls the troup of vehicles generates the most plausible map of the environment from the information obtained by the different components of the troup, which at the end of their mission return back. To perform the map generation a two-step algorithm, fusion and completion, based on fuzzy techniques, is presented.

Cooperative Autonomous Low-Cost Robots for exploring Unknown Environments

In recent years, mobile robots have been required to become more and more autonomous in such a way that they are able to sense and recognize the three-dimensional space in which they live or work. In this paper, we deal with such an environment map building problem from three-dimensional sensing data for mobile robot navigation. In particular, the problem to be dealt with is how to extract and model obstacles which are not represented on the map but exist in the real environment, so that the map can be newly updated using the modeled obstacle information. To achieve this, we propose a three-dimensional map building method, which is based on a self-organizing neural network technique called “growing neural gas network.” Using the obstacle data acquired from the 3D data acquisition process of an active laser range finder, learning of the neural network is performed to generate a graphical structure that reflects the topology of the input space. For evaluation of the proposed method, a series of simulations and experiments are performed to build 3D maps of some given environments surrounding the robot. The usefulness and robustness of the proposed method are investigated and discussed in detail. © 2004 Wiley Periodicals, Inc.

Three-dimensional map building for mobile robot navigation environments using a self-organizing neural network

The modelling of a mobile robot environment is mainly motivated first to obtain a map of the free space (in order to compute safe trajectories for the vehicle) and second to provide the control loop with feed-back of obstacle information. Here, the authors only consider the problem of local representations for the displacements of a vehicle with two preoccupations: the environment models have to be adequate for the robot navigation algorithms, and the construction of these models have to be as fast as possible. The study is carried out at two levels: a low level based on the analysis of the free zones of the environment and a high level of obstacle modelling. According to local navigation, the obstacle modelling is based on the artificial potential field method. >

B. Jouvencel

Papers

The variable modelling of mobile robot environments