arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.15724cs.ROcs.AIcs.LGcs.MA
收藏

MAPPER:混合动态环境下基于进化强化学习的多智能体路径规划

MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments

Carnegie Mellon University(卡内基梅隆大学);Tsinghua University(清华大学)

Zuxin Liu, Baiming Chen, Hongyi Zhou, Guru Koushik, Martial Hebert, Ding Zhao

摘要:

动态环境下的多智能体导航在大规模机器人部署到实际应用中具有重要的工业价值。提出了一种基于进化强化学习(MAPPER)的分散式部分可观测多智能体路径规划方法,用于在混合动态环境中学习有效的局部规划策略.基于强化学习的方法通常会在具有目标条件的稀疏奖励的长时间任务上性能下降,因此我们在全局规划器的指导下将长距离导航任务分解为许多更容易的子任务,这提高了智能体在大环境中的性能。此外,大多数现有的多智能体规划方法假设周围环境的完美信息或附近的动态代理的同质性,这在实践中可能不成立。我们的方法模型动态障碍物的行为与基于图像的表示和训练的政策在混合动态环境中没有同质性假设。为了确保多智能体训练的稳定性和性能,我们提出了一种进化的训练方法,可以很容易地扩展到大型和复杂的环境。实验表明,与传统的基于反应的规划器LRA* 和最先进的基于学习的方法相比,MAPPER在面对大量非合作动态障碍物时能够获得更高的成功率和更稳定的性能。

英文摘要:

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method to learn an effective local planning policy in mixed dynamic environments. Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks under the guidance of a global planner, which increases agents' performance in large environments. Moreover, most existing multi-agent planning approaches assume either perfect information of the surrounding environment or homogeneity of nearby dynamic agents, which may not hold in practice. Our approach models dynamic obstacles' behavior with an image-based representation and trains a policy in mixed dynamic environments without homogeneity assumption. To ensure multi-agent training stability and performance, we propose an evolutionary training approach that can be easily scaled to large and complex environments. Experiments show that MAPPER is able to achieve higher success rates and more stable performance when exposed to a large number of non-cooperative dynamic obstacles compared with traditional reaction-based planner LRA* and the state-of-the-art learning-based method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑