Near-Optimal Belief Space Planning via T-LQG
This addresses the computational challenge of belief space planning for robotics, offering a near-optimal method that is incremental in improving efficiency over existing approaches.
The paper tackles the problem of planning under uncertainty for nonlinear robotics systems, which is computationally intractable as a POMDP, by proposing a T-LQG approach that yields quantifiably near-optimal solutions with polynomial-order calculations.
We consider the problem of planning under observation and motion uncertainty for nonlinear robotics systems. Determining the optimal solution to this problem, generally formulated as a Partially Observed Markov Decision Process (POMDP), is computationally intractable. We propose a Trajectory-optimized Linear Quadratic Gaussian (T-LQG) approach that leads to quantifiably near-optimal solutions for the POMDP problem. We provide a novel "separation principle" for the design of an optimal nominal open-loop trajectory followed by an optimal feedback control law, which provides a near-optimal feedback control policy for belief space planning problems involving a polynomial order of calculations of minimum order.