Learning Multi-Agent Local Collision-Avoidance for Collaborative Carrying tasks with Coupled Quadrupedal Robots

TL;DR

This paper introduces a reinforcement learning approach for multi-agent collision avoidance in collaborative carrying tasks with coupled quadrupedal robots, enabling obstacle navigation using onboard sensing without precomputed maps.

Contribution

It presents a hierarchical RL-based policy with a game-inspired curriculum for obstacle avoidance in multi-robot systems, validated on real hardware.

Findings

Successful obstacle avoidance in unknown environments

Outperforms optimization-based and decentralized RL baselines

Operates without precomputed maps or path planners

Abstract

Robotic collaborative carrying could greatly benefit human activities like warehouse and construction site management. However, coordinating the simultaneous motion of multiple robots represents a significant challenge. Existing works primarily focus on obstacle-free environments, making them unsuitable for most real-world applications. Works that account for obstacles, either overfit to a specific terrain configuration or rely on pre-recorded maps combined with path planners to compute collision-free trajectories. This work focuses on two quadrupedal robots mechanically connected to a carried object. We propose a Reinforcement Learning (RL)-based policy that enables tracking a commanded velocity direction while avoiding collisions with nearby obstacles using only onboard sensing, eliminating the need for precomputed trajectories and complete map knowledge. Our work presents a hierarchical architecture, where a perceptive high-level object-centric policy commands two pretrained locomotion policies. Additionally, we employ a game-inspired curriculum to increase the complexity of obstacles in the terrain progressively. We validate our approach on two quadrupedal robots connected to a bar via spherical joints, benchmarking it against optimization-based and decentralized RL baselines. Our hardware experiments demonstrate the ability of our system to locomote in unknown environments without the need for a map or a path planner. The video of our work is available in the multimedia material.