IJCAI-99 Workshop on
Reasoning with Uncertainty in Robot NavigationStockholm, Sweden, August 2, 1999
Uncertainty plays an important role in robot navigation at many levels, such as sensor interpretation, sensor fusion, map making, path planning, self-localization, and control. Dealing with uncertainty also constitutes the focus of a large research effort in AI, which has led to the development of a number of new theories and new techniques. However, it is only recently that the field of robot navigation has started to import some of these techniques in order to address the issues of uncertainty in robot navigation. These techniques use probabilistic representations or fuzzy set theory to model uncertainty in sensor information and the outcome of actions taken by the robot. Example of these techniques include occupancy grids, intelligent sensor fusion, decision-theoretic procedures like POMDPs, and extensions to Kalman filtering. Recent successes of mobile robots in practical areas such as robotic museum tour-guides showed that these techniques have reached a level of robustness which allows robots to operate even in crowded environments.
The first workshop on ``Reasoning with Uncertainty in Robotics'' (RUR '95) was held in Amsterdam, NL, in 1995. This second workshop in the series is devoted to discuss current topics in mobile robotics and uncertainty. The workshop will bring together researchers working in advanced methods of dealing with sensor and movement uncertainty in mobile robots. We especially welcome those who have ideas about how to extend current theories to deal with more challenging environments, or those who have competing approaches, e.g., landmark-based, behavioral, or "topological" navigation. The workshop will provide an opportunity to critically examine these various approaches, and to discuss their strengths and weaknesses in various types of environments.
This workshop will interest all people working in mobile robotics, both from academy and from industry. It will also interest researchers working in the area of uncertainty in AI, since it will offer them the possibility to apply their techniques to real and challenging problems.