SEA-Nav: 高效安全敏捷四足机器人在密集环境中导航的策略学习
SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments
AI总结:
SEA-Nav通过安全、高效和敏捷的强化学习框架,实现了在密集环境中四足机器人导航的高效训练,仅需分钟级训练时间。
摘要:
在密集障碍环境中高效训练四足机器人导航仍是一个重大挑战。现有方法要么受限于简单障碍分布中安全性和敏捷性的不足,要么在复杂环境中表现出缓慢的移动速度,往往需要过长的训练阶段。为此,我们提出了SEA-Nav(安全、高效和敏捷导航),一种用于四足导航的强化学习框架。在多样且密集的障碍环境中,可微分的控制屏障函数(CBF)基于的屏蔽约束将导航策略限制为输出安全的速度命令。引入了自适应碰撞回放机制和危险探索奖励,以增加从关键经验中学习的概率,引导高效的探索和利用。最后,加入运动学动作约束以确保安全的速度命令,促进成功的物理部署。据我们所知,这是首个在现实世界中实现极具挑战性的四足导航的方法,仅需分钟级的训练时间。
英文摘要:
Efficiently learning safe and agile quadruped navigation in densely cluttered environments remains difficult: existing methods often lack safety and agility, or become conservative in complex scenes and require long training schedules. We propose SEA-Nav (Safe, Efficient, and Agile Navigation), a safe reinforcement learning framework for quadruped navigation in cluttered environments. A differentiable control barrier function (CBF) shield constrains the policy to produce safe velocity commands. An adaptive collision-state initialization mechanism increases the probability of learning from safety-critical near-collision experience. An action regularization term further suppresses infeasible commands for physical deployment. The policy converges after about one hour of training on a single RTX 4090 and transfers zero-shot to real-world cluttered scenes.
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。