Probabilistic inference methods in robotics — filling the gap between high-level reasoning and low-level motion control

@inproceedings{Toussaint2007ProbabilisticIM,
  title={Probabilistic inference methods in robotics — filling the gap between high-level reasoning and low-level motion control},
  author={Marc Toussaint},
  year={2007}
}
Cognitive robotics is one of the topics of the new PASCAL 2 project. While classical AI approaches can achieve outstanding performances on abstract and symbolic reasoning problems, one of the core problems in robotics is the grounding of high-level planning and reasoning techniques in the low-level motor and sensor context. Machine Learning techniques can tackle exactly this grounding problem. In this paper we discuss a new approach that uses probabilistic inference techniques to solve low… CONTINUE READING