Robust Combination of Local Controllers
This addresses the problem of robust planning under uncertainty for robotics and control systems, offering incremental improvements by combining existing local controllers with new formulations.
The paper tackles the difficulty of solving high-dimensional continuous Markov Decision Processes (MDPs) under uncertainty by proposing a method to nonparametrically combine local controllers for global solutions, applied to motion planning and discounted MDPs, with results including a proof that a polynomial number of samples suffices for high-probability paths in motion planning.
Planning problems are hard, motion planning, for example, isPSPACE-hard. Such problems are even more difficult in the presence of uncertainty. Although, Markov Decision Processes (MDPs) provide a formal framework for such problems, finding solutions to high dimensional continuous MDPs is usually difficult, especially when the actions and time measurements are continuous. Fortunately, problem-specific knowledge allows us to design controllers that are good locally, though having no global guarantees. We propose a method of nonparametrically combining local controllers to obtain globally good solutions. We apply this formulation to two types of problems : motion planning (stochastic shortest path) and discounted MDPs. For motion planning, we argue that usual MDP optimality criterion (expected cost) may not be practically relevant. Wepropose an alternative: finding the minimum cost path,subject to the constraint that the robot must reach the goal withhigh probability. For this problem, we prove that a polynomial number of samples is sufficient to obtain a high probability path. For discounted MDPs, we propose a formulation that explicitly deals with model uncertainty, i.e., the problem introduced when transition probabilities are not known exactly. We formulate the problem as a robust linear program which directly incorporates this type of uncertainty.