Robust online belief space planning in changing environments: Application to physical mobile robots

Abstract

Abstract-Motion planning in belief space (under motion and sensing uncertainty) is a challenging problem due to the computational intractability of its exact solution. The Feedback-based Information RoadMap (FIRM) framework made an important theoretical step toward enabling roadmap-based planning in belief space and provided a computationally tractable version of belief space planning. However, there are still challenges in applying belief space planners to physical systems, such as the discrepancy between computational models and real physical models. In this paper, we propose a dynamic replanning scheme in belief space to address such challenges. Moreover, we present techniques to cope with changes in the environment (e.g., changes in the obstacle map), as well as unforeseen large deviations in the robot's location (e.g., the kidnapped robot problem). We then utilize these techniques to implement the first online replanning scheme in belief space on a physical mobile robot that is robust to changes in the environment and large disturbances. This method demonstrates that belief space planning is a practical tool for robot motion planning.

Control Theory Meets POMDPs: A Hybrid Systems Approach

“…Therefore, (20) is satisfied with B = co{B i } m i=1 . Similarly, we can show that if (29) is satisfied, B = co{B i } m i=1 satisfies (21).…”

“…Yet, the problem lies in the fact that the reachable belief space is not known a priori and therefore it is hard to make judgements on the convergence rate of a given approximate method. Several techniques have been proposed for estimating the reachable belief space mainly based on heuristics [17], [18], "smarter" sampling methods, such as importance sampling [19], and graph search [20], [21]. However, these methods are difficult to adapt from one problem setting to another and are often ad hoc.…”

Periodic-Node Graph-Based Framework for Stochastic Control of Small Aerial Vehicles

“…On roadmaps in belief space, the situation is even more complicated, since the controller has to drive the probability distribution over the state to the -neighborhood of a belief node in belief space. Again, if the linearized system in (2) is controllable, using a linear stochastic controller such as the stationary LQG controller, one can drive the robot belief to the belief node [5]. However, if the system is non-stoppable and/or its linearized model is not controllable, the belief stabilization, if possible, is much more difficult than state stabilization.…”

“…In [5] first FIRM is presented as an abstract framework for graph-based planning in belief space and then Stationary Linear Quadratic Gaussian-FIRM (SLQG-FIRM) is presented as a concrete instantiation of the abstract FIRM framework. The performance of FIRM has been demonstrated on physical mobile robots in changing environments [2]. However, SLQG-FIRM is limited to the systems that are stabilizable to stationary fixed points (with zero velocity) in the state space.…”

Where to Map? Iterative Rover-Copter Path Planning for Mars Exploration

“…For example, the works in [8], [9] improved the performance of VO localization by actively choosing timing and camera direction to obtain an optimal image sequence using the predictive perception technique. This problem is typically approached by Partially Observable Markov Decision Process (POMDP), or belief-space planning [10], [11], [12], [13], [14], where the planner chooses optimal actions under motion and sensing uncertainty.…”