Sampling-based Task and Kinodynamic Motion Planning under Semantic Uncertainty

TL;DR

This paper introduces a sampling-based algorithm for integrated task and kinodynamic motion planning in uncertain, partially observable environments, ensuring soundness and asymptotic optimality.

Contribution

It models the problem as a Partially Observable Stochastic Hybrid System and develops an anytime algorithm that outperforms baseline methods.

Findings

Algorithm is effective in uncertain environments.

Proven to be sound and asymptotically optimal.

Outperforms baseline methods in experiments.

Abstract

This paper tackles the problem of integrated task and kinodynamic motion planning in uncertain environments. We consider a robot with nonlinear dynamics tasked with a Linear Temporal Logic over finite traces ($\ltlf$) specification operating in a partially observable environment. Specifically, the uncertainty is in the semantic labels of the environment. We show how the problem can be modeled as a Partially Observable Stochastic Hybrid System that captures the robot dynamics, $\ltlf$ task, and uncertainty in the environment state variables. We propose an anytime algorithm that takes advantage of the structure of the hybrid system, and combines the effectiveness of decision-making techniques and sampling-based motion planning. We prove the soundness and asymptotic optimality of the algorithm. Results show the efficacy of our algorithm in uncertain environments, and that it consistently outperforms baseline methods.