Motion Planning for Global Localization in Non-Gaussian Belief Spaces
This addresses the lost or kidnapped robot problem for robotics, providing a solution for scenarios with little initial pose information, though it appears incremental as it builds on existing motion planning and localization techniques.
The paper tackles the global localization problem for mobile robots with ambiguous data associations by developing a Receding Horizon motion planning method to disambiguate multimodal beliefs and achieve tight localization in finite time, demonstrating successful localization in two experimental runs in a maze-like environment without prior pose information.
This paper presents a method for motion planning under uncertainty to deal with situations where ambiguous data associations result in a multimodal hypothesis on the robot state. In the global localization problem, sometimes referred to as the "lost or kidnapped robot problem", given little to no a priori pose information, the localization algorithm should recover the correct pose of a mobile robot with respect to a global reference frame. We present a Receding Horizon approach, to plan actions that sequentially disambiguate a multimodal belief to achieve tight localization on the correct pose in finite time, i.e., converge to a unimodal belief. Experimental results are presented using a physical ground robot operating in an artificial maze-like environment. We demonstrate two runs wherein the robot is given no a priori information about its initial pose and the planner is tasked to localize the robot.