STR: Spatial-Temporal RetNet for Distributed Multi-Robot Navigation

The core of multi-robot collision avoidance is to guide robots to avoid collisions with other robots and obstacles in a dynamic multi-robot environment, which has recently gained increasing interest among the main challenges of robotics. However, the current multi-robot navigation policy neural network exhibits weak position encoding capabilities for spatial environmental features in mapping environment states and robot actions, as well as an inability to recurrently infer information on dynamic environmental features in the temporal dimension, leading to insufficient safety and effectiveness in guiding robot motion. In this paper, we propose a novel spatial-temporal RetNet (STR) that encodes reciprocal collision avoidance states between robots in both spatial and temporal dimensions, aiming to enhance the safety and effectiveness of the policy neural network in guiding robots to accomplish specified tasks. The spatial state encoder module is developed based on parallel RetNet structure, which enhances the ability of the neural network in multi-robot navigation policies to extract reciprocal collision avoidance states between robots in spatial dimensions and overcomes the weak position encoding capability of advanced transformer-based multi-robot navigation policy neural networks. A temporal state encoder is designed by introducing the recurrent RetNet structure. This enhances the multi-robot navigation policy neural network’s ability to encode features in the temporal dimension of multi-robot movements and overcomes the transformer-based multi-robot navigation policy neural network’s inability to recurrently infer information in the time dimension. Simulation experiments were designed to demonstrate that the safety and effectiveness of our proposed method outperform the previous state-of-the-art approaches in guiding the robot to complete the task. Physical experiments illustrate that our policy can be effectively applied to real-world systems. Note to Practitioners—Multi-robot navigation has a wide range of real-world applications, such as multi-robot formation flying for search and rescue, autonomous warehouse operations, and robots navigating through human crowds. This paper introduces a novel Spatial-Temporal RetNet (STR) framework aimed at enhancing safety and effectiveness in multi-robot collision avoidance. STR addresses the limitations of existing methods by improving the neural network’s ability to extract reciprocal collision avoidance states in both spatial and temporal dimensions. The spatial state encoder strengthens the extraction of spatial features, while the temporal state encoder improves the handling of time-dependent information. Simulation and physical experiments demonstrate that STR enhances robot navigation in dynamic environments, making it suitable for real-world applications such as multi-robot coordination.

I. Introduction

Multi-robot collision avoidance has attracted considerable attention from researchers in recent years, as it finds extensive applications in scenarios such as autonomous driving, intelligent warehouse robotics, and crowd simulation [1], [2], [3], [4], [5], [6]. At its core, the robot avoids collisions in environments with multiple robots, including both static and dynamic obstacles [4], [7], [8], [9]. The existing multi-robot navigation methods are generally classified into centralized and decentralized approaches based on whether they rely entirely on a central server [8]. A central server is used in a centralized approach to plan the movement of each robot based on the information sensed by all robots.This process of planning the robot’s path first does not consider collisions, and then uses a scheduling scheme to avoid collisions at potential conflict locations [10]. However, the increasing number of robots results in a substantial rise in computational demands, leading to higher resource requirements and computation time costs, along with time delays in the control signals exchanged between each robot and the central server.