Dual-Quadruped Collaborative Transportation in Narrow Environments via Safe Reinforcement Learning

2026-02-18

AI Summary

This work addresses the challenges of constrained feasible regions and high collision risks in multi-legged robot cooperative transport within narrow environments. The authors model the collaborative transport task using two quadrupedal robots as a fully cooperative constrained Markov game and propose a safe reinforcement learning framework. By leveraging a cost-advantage decomposition, the framework ensures that the team’s total constraint violations remain below a prescribed threshold, while a novel constraint allocation mechanism incentivizes autonomous role specialization among the robots. The approach effectively balances safety and task efficiency, significantly outperforming existing methods in both simulation and real-world experiments, achieving higher task success rates and improved coordination performance.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Coordination and Collaboration
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Collaborative transportation, where multiple robots collaboratively transport a payload, has garnered significant attention in recent years. While ensuring safe and high-performance inter-robot collaboration is critical for effective task execution, it is difficult to pursue in narrow environments where the feasible region is extremely limited. To address this challenge, we propose a novel approach for dual-quadruped collaborative transportation via safe reinforcement learning (RL). Specifically, we model the task as a fully cooperative constrained Markov game, where collision avoidance is formulated as constraints. We introduce a cost-advantage decomposition method that enforces the sum of team constraints to remain below an upper bound, thereby guaranteeing task safety within an RL framework. Furthermore, we propose a constraint allocation method that assigns shared constraints to individual robots to maximize the overall task reward, encouraging autonomous task-assignment among robots, thereby improving collaborative task performance. Simulation and real-time experimental results demonstrate that the proposed approach achieves superior performance and a higher success rate in dual-quadruped collaborative transportation compared to existing methods.

Problem

• collaborative transportation
• narrow environments
• collision avoidance
• quadruped robots
• safe reinforcement learning

Innovation

• safe reinforcement learning
• constrained Markov game
• cost-advantage decomposition
• constraint allocation
• dual-quadruped collaboration