Stochastic Motion Planning under Partial Observability for Mobile Robots with Continuous Range Measurements

TL;DR

This paper introduces POMCP++, a novel Monte Carlo Tree Search algorithm designed for stochastic motion planning of mobile robots with continuous range measurements, effectively handling partial observability and improving success rates.

Contribution

The paper develops POMCP++, an extension of POMCP, capable of managing continuous observations in POMDPs for robotic navigation, addressing limitations of existing methods.

Findings

POMCP++ outperforms existing methods in success rate.

The algorithm effectively handles continuous measurement spaces.

Theoretical validation confirms POMCP++ as a Monte Carlo Tree Search method.

Abstract

In this paper, we address the problem of stochastic motion planning under partial observability, more specifically, how to navigate a mobile robot equipped with continuous range sensors such as LIDAR. In contrast to many existing robotic motion planning methods, we explicitly consider the uncertainty of the robot state by modeling the system as a POMDP. Recent work on general purpose POMDP solvers is typically limited to discrete observation spaces, and does not readily apply to the proposed problem due to the continuous measurements from LIDAR. In this work, we build upon an existing Monte Carlo Tree Search method, POMCP, and propose a new algorithm POMCP++. Our algorithm can handle continuous observation spaces with a novel measurement selection strategy. The POMCP++ algorithm overcomes over-optimism in the value estimation of a rollout policy by removing the implicit perfect state assumption at the rollout phase. We validate POMCP++ in theory by proving it is a Monte Carlo Tree Search algorithm. Through comparisons with other methods that can also be applied to the proposed problem, we show that POMCP++ yields significantly higher success rate and total reward.