Symbolic planning methods have proved to be challenging in robotics due to partial observability and noise as well as unavoidable exceptions to rules that symbol semantics depend on. Often the symbols that a robot considers to support for planning are brittle, making them unsuited for even relatively short term use. Maturing probabilistic methods in robotics, however, are providing a sound basis for symbol grounding that supports using probabilistic distributions over symbolic entities as the basis for planning. In this paper, we describe a belief-space planner that stabilizes the semantics of feedback from the environment by actively interacting with a scene. When distributions over higher-level abstractions stabilize, powerful symbolic planning techniques can provide reliable guidance for problem solving. We present such an approach in a hybrid planning scheme that actively controls uncertainty and yields robust state estimation with bounds on uncertainty that can make effective use of powerful symbolic planning techniques. We illustrate the idea in a hybrid planner for autonomous construction tasks with a real robot system.

This paper describes a policy iteration algorithm for optimizing the performance of a harmonic function-based controller with respect to a user-defined index. Value functions are represented as potential distributions over the problem domain, being control policies represented as gradient fields over the same domain. All intermediate policies are intrinsically safe, i.e. collisions are not promoted during the adaptation process. The algorithm has efficient implementation in parallel SIMD architectures. One potential application - travel distance minimization - illustrates its usefulness.

This paper describes a policy iteration algorithm for optimizing the performance of a harmonic function-based controller with respect to a user-defined index. Value functions are represented as potential distributionsover the problem domain, being control policies represented as gradient fields over the same domain. All intermediate policiesare intrinsically safe, i.e. collisions are not promoted during the adaptation process. The algorithm has efficient implementation inparallel SIMD architectures. One potential application - travel distance minimization - illustrates its usefulness.