Motion Planning in Non-Gaussian Belief Spaces
نویسندگان
چکیده
In environments with information symmetry, uncertain or ambiguous data associations can lead to a multi-modal hypothesis on the robot’s state. Thus, a planner cannot simply base actions on the most-likely state. We propose an algorithm that uses a Receding Horizon Planning approach to plan actions that sequentially disambiguate a multi-modal belief to a uni-modal Gaussian and achieve tight localization on the true state of a mobile robot. We call this algorithm Multi-Modal Motion Planner (M3P). We prove that our planner is guaranteed to drive a multi-modal belief to a uni-modal Gaussian under certain assumptions. Simulation results for a 2D ground robot navigation problem are presented that demonstrate our method’s performance.
منابع مشابه
Motion Planning in Non-Gaussian Belief Spaces for Mobile Robots
In this paper we propose a method for motion planning under uncertainty that can deal with situations where ambiguous data associations result in a multimodal hypothesis in belief space. Unlike conventional methods, planning based on the most-likely hypothesis is no longer possible in such cases. We adopt a Gaussian Mixture Model (GMM) for belief representation and use a Receding Horizon Planni...
متن کاملMotion Planning in Non-Gaussian Belief Spaces (M3P): The Case of a Kidnapped Robot
Planning under uncertainty is a key requirement for physical systems due to the noisy nature of actuators and sensors. Using a belief space approach, planning solutions tend to generate actions that result in information seeking behavior which reduce state uncertainty. While recent work has dealt with planning for Gaussian beliefs, for many cases, a multimodal belief is a more accurate represen...
متن کاملGaussian Belief Space Planning for Imprecise Articulated Robots
For many emerging applications, actuators are being developed to avoid injuring humans and actuation and sensing precision is reduced to keep costs down. For planning and control of such robots, belief space and POMDP-based methods show great promise but have primarily been applied to cases where robots can be approximated as points or spheres. We extend this framework to non-spherical articula...
متن کاملMotion planning under uncertainty using iterative local optimization in belief space
We present a new approach to motion planning under sensing and motion uncertainty by computing a locally optimal solution to a continuous partially observable Markov decision process (POMDP). Our approach represents beliefs (the distributions of the robot’s state estimate) by Gaussian distributions and is applicable to robot systems with non-linear dynamics and observation models. The method fo...
متن کاملScaling up Gaussian Belief Space Planning Through Covariance-Free Trajectory Optimization and Automatic Differentiation
Belief space planning provides a principled framework to compute motion plans that explicitly gather information from sensing, as necessary, to reduce uncertainty about the robot and the environment. We consider the problem of planning in Gaussian belief spaces, which are parameterized in terms of mean states and covariances describing the uncertainty. In this work, we show that it is possible ...
متن کامل