利用自主真实世界强化学习持续改进移动操作
Continuously Improving Mobile Manipulation with Autonomous Real-World RL
AI总结：
本文提出一种完全自主的真实世界强化学习框架，通过任务相关自主性、行为先验和通用奖励设计，使Spot机器人在四项移动操作任务上持续提升，平均成功率达80%，比现有方法提高3到4倍。
摘要：
我们提出了一个完全自主的真实世界强化学习框架，用于移动操作，该框架能够在无需大量仪器设备或人类监督的情况下学习策略。这得益于：1）任务相关自主性，它引导探索朝向物体交互，并防止在目标状态附近停滞；2）通过在行为先验中利用基本任务知识实现高效策略学习；3）制定通用奖励，将人类可解释的语义信息与低层细粒度观测相结合。我们证明，我们的方法使Spot机器人在四项具有挑战性的移动操作任务上持续提升性能，跨任务平均成功率达到80%，相比现有方法提高了3到4倍。视频可在https://continual-mobile-manip.github.io/查看。
英文摘要：
We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision. This is enabled by 1) task-relevant autonomy, which guides exploration towards object interactions and prevents stagnation near goal states, 2) efficient policy learning by leveraging basic task knowledge in behavior priors, and 3) formulating generic rewards that combine human-interpretable semantic information with low-level, fine-grained observations. We demonstrate that our approach allows Spot robots to continually improve their performance on a set of four challenging mobile manipulation tasks, obtaining an average success rate of 80% across tasks, a 3-4 improvement over existing approaches. Videos can be found at https://continual-mobile-manip.github.io/
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。
