从机群经验中学习：机器人集体学习范式
原标题：Paper page - Learning from Fleet Experience: A Collective Learning Paradigm for Robots
AI 摘要
该论文提出集体经验学习（CEL）范式，让部署中的机器人共享执行经验以改进共同策略，无需额外专家纠正。其算法 FERT 利用失败上下文从机群共享的成功经验中检索相关轨迹片段作为监督信号，配套的容错异步训练系统 FATS 可在机群局部中断时维持学习。在五项真实操作任务上，策略成功率达 93.3%-99.2%；在多阶段手机包装任务中，使用 96 台机器人将成功率从 79.2% 提升至 98.3%。
正文节选
Learning from Fleet Experience: A Collective Learning Paradigm for Robots Abstract Robots share execution experience across fleets to improve policies via failure-guided retrieval and asynchronous training, achieving high success without extra expert corrections. Experience generated during deployment offers an opportunity for robots to improve policy reliability through learning from their own executions. However, learning through human corrections requires teleoperators to monitor execution an