通过触摸泛化：面向机器人家具组装的触觉集成技能迁移
Generalize by Touching: Tactile Ensemble Skill Transfer for Robotic Furniture Assembly
AI总结：
本文提出TEST框架，通过引入触觉反馈的离线强化学习方法学习技能转移模型与自适应策略，解决机器人家具组装的长周期任务泛化问题，实现90%成功率且效率提升4倍以上。
摘要：
家具组装由于具有长任务周期和不可泛化的操作计划，在机器人操作中仍是一个未解决的问题。本文提出了Tactile Ensemble Skill Transfer (TEST)框架，这是一种开创性的将触觉反馈纳入控制回路的离线强化学习(RL)方法。TEST的核心设计是学习一个用于高层规划的技能转移模型，以及一组自适应的技能内目标达成策略。该设计旨在以更具泛化性的方式解决机器人家具组装问题，促进该长周期任务中技能的无缝衔接。我们首先从一组启发式策略和由随机子技能片段组成的轨迹中采样演示数据，从而获取丰富的机器人轨迹，这些轨迹捕捉了技能阶段、机器人状态、视觉指标以及至关重要的触觉信号。利用这些轨迹，我们的离线RL方法能够识别技能终止条件并协调技能转移。我们的评估突出了TEST在分布内家具组装上的熟练度、对未见家具配置的适应性，以及对视觉干扰的鲁棒性。消融研究进一步强调了两个算法组件的关键作用：技能转移模型和触觉集成策略。结果表明，TEST能够达到90%的成功率，并且在分布内和泛化设置下均比启发式策略的效率高出4倍以上，为富接触操作提出了一种可扩展的技能迁移方法。
英文摘要：
Furniture assembly remains an unsolved problem in robotic manipulation due to its long task horizon and nongeneralizable operations plan. This paper presents the Tactile Ensemble Skill Transfer (TEST) framework, a pioneering offline reinforcement learning (RL) approach that incorporates tactile feedback in the control loop. TEST's core design is to learn a skill transition model for high-level planning, along with a set of adaptive intra-skill goal-reaching policies. Such design aims to solve the robotic furniture assembly problem in a more generalizable way, facilitating seamless chaining of skills for this long-horizon task. We first sample demonstration from a set of heuristic policies and trajectories consisting of a set of randomized sub-skill segments, enabling the acquisition of rich robot trajectories that capture skill stages, robot states, visual indicators, and crucially, tactile signals. Leveraging these trajectories, our offline RL method discerns skill termination conditions and coordinates skill transitions. Our evaluations highlight the proficiency of TEST on the in-distribution furniture assemblies, its adaptability to unseen furniture configurations, and its robustness against visual disturbances. Ablation studies further accentuate the pivotal role of two algorithmic components: the skill transition model and tactile ensemble policies. Results indicate that TEST can achieve a success rate of 90\% and is over 4 times more efficient than the heuristic policy in both in-distribution and generalization settings, suggesting a scalable skill transfer approach for contact-rich manipulation.
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。
