ESCoT: An Enhanced Step-based Coordinate Trajectory Planning Method for Multiple Car-like Robots

TL;DR

ESCoT is a novel trajectory planning method for multiple car-like robots that enhances solution quality and success rates through collaborative planning and replanning strategies, validated by extensive experiments and real-world tests.

Contribution

The paper introduces ESCoT, an improved step-based MVTP method with collaborative planning and replanning, significantly outperforming baseline methods in various scenarios.

Findings

Achieves up to 70% improvement in conflict scenarios

Maintains over 50% success rate in dense, challenging environments

Validated through extensive experiments and real-world robot tests

Abstract

Multi-vehicle trajectory planning (MVTP) is one of the key challenges in multi-robot systems (MRSs) and has broad applications across various fields. This paper presents ESCoT, an enhanced step-based coordinate trajectory planning method for multiple car-like robots. ESCoT incorporates two key strategies: collaborative planning for local robot groups and replanning for duplicate configurations. These strategies effectively enhance the performance of step-based MVTP methods. Through extensive experiments, we show that ESCoT 1) in sparse scenarios, significantly improves solution quality compared to baseline step-based method, achieving up to 70% improvement in typical conflict scenarios and 34% in randomly generated scenarios, while maintaining high solving efficiency; and 2) in dense scenarios, outperforms all baseline methods, maintains a success rate of over 50% even in the most challenging configurations. The results demonstrate that ESCoT effectively solves MVTP, further extending the capabilities of step-based methods. Finally, practical robot tests validate the algorithm's applicability in real-world scenarios.