Multi-Risk-RRT: An Efficient Motion Planning Algorithm for Robotic Autonomous Luggage Trolley Collection at Airports

TL;DR

This paper introduces Multi-Risk-RRT, a novel multi-directional sampling algorithm for robotic motion planning in dynamic, crowded environments like airports, improving speed and robustness over existing risk-based methods.

Contribution

The paper presents a new multi-tree sampling approach that enhances planning efficiency and robustness in dynamic environments, addressing limitations of traditional risk-based algorithms.

Findings

Outperforms existing algorithms in simulation tests

Demonstrates robustness in real-world airport scenarios

Achieves faster planning times with higher success rates

Abstract

Robots have become increasingly prevalent in dynamic and crowded environments such as airports and shopping malls. In these scenarios, the critical challenges for robot navigation are reliability and timely arrival at predetermined destinations. While existing risk-based motion planning algorithms effectively reduce collision risks with static and dynamic obstacles, there is still a need for significant performance improvements. Specifically, the dynamic environments demand more rapid responses and robust planning. To address this gap, we introduce a novel risk-based multi-directional sampling algorithm, Multi-directional Risk-based Rapidly-exploring Random Tree (Multi-Risk-RRT). Unlike traditional algorithms that solely rely on a rooted tree or double trees for state space exploration, our approach incorporates multiple sub-trees. Each sub-tree independently explores its surrounding environment. At the same time, the primary rooted tree collects the heuristic information from these sub-trees, facilitating rapid progress toward the goal state. Our evaluations, including simulation and real-world environmental studies, demonstrate that Multi-Risk-RRT outperforms existing unidirectional and bi-directional risk-based algorithms in planning efficiency and robustness.