Distributionally Robust RRT with Risk Allocation

TL;DR

This paper introduces a distributionally robust risk allocation method integrated into sampling-based motion planning, enabling robots to generate safer trajectories in uncertain environments by decomposing risk constraints.

Contribution

It proposes a novel risk allocation technique that decomposes joint risk constraints into individual constraints, improving safety and efficiency in motion planning under uncertainty.

Findings

Guarantees conservative, risk-feasible trajectories

Enhances state space exploration efficiency

Provides a systematic risk management framework

Abstract

An integration of distributionally robust risk allocation into sampling-based motion planning algorithms for robots operating in uncertain environments is proposed. We perform non-uniform risk allocation by decomposing the distributionally robust joint risk constraints defined over the entire planning horizon into individual risk constraints given the total risk budget. Specifically, the deterministic tightening defined using the individual risk constraints is leveraged to define our proposed exact risk allocation procedure. Our idea of embedding the risk allocation technique into sampling based motion planning algorithms realises guaranteed conservative, yet increasingly more risk feasible trajectories for efficient state space exploration.