SACBP: Belief Space Planning for Continuous-Time Dynamical Systems via Stochastic Sequential Action Control
This work addresses planning under uncertainty for continuous-time systems, which is crucial for robotics and control applications, representing a novel method rather than an incremental improvement.
The paper tackled belief space planning for continuous-time dynamical systems by proposing SACBP, a novel technique based on stochastic sequential action control that avoids discretization and operates in near real-time, showing significant outperformance over existing methods like approximate dynamic programming and local trajectory optimization in active sensing and Bayesian reinforcement learning scenarios.
We propose a novel belief space planning technique for continuous dynamics by viewing the belief system as a hybrid dynamical system with time-driven switching. Our approach is based on the perturbation theory of differential equations and extends Sequential Action Control to stochastic dynamics. The resulting algorithm, which we name SACBP, does not require discretization of spaces or time and synthesizes control signals in near real-time. SACBP is an anytime algorithm that can handle general parametric Bayesian filters under certain assumptions. We demonstrate the effectiveness of our approach in an active sensing scenario and a model-based Bayesian reinforcement learning problem. In these challenging problems, we show that the algorithm significantly outperforms other existing solution techniques including approximate dynamic programming and local trajectory optimization.