无需微调，直接让机器人用磁力触觉传感器完成插入任务
Zero-shot Sim2Real Transfer for Magnet-Based Tactile Sensor on Insertion Tasks
- 提出GCS方法，实现密集三维触觉信号的零样本仿真到现实迁移
- 在盲插任务中成功实现强化学习策略的零样本跨域迁移
- 适合需高精度触觉反馈的复杂抓取与插入场景
触觉感知是机器人操作中的关键传感模态。在各类触觉传感器中，磁力传感器（如u-skin）在耐用性与触觉密度之间取得了良好平衡。然而，触觉传感器存在显著的仿真到现实差距，阻碍了机器人从仿真数据中学习有效的触觉驱动操作技能——而这一方法在复杂控制策略训练中已被证明有效。以往工作采用二值化处理以缓解仿真到现实的差距，但该方法会丢失大量对插入等任务至关重要的信息。本文提出GCS，一种新的仿真到现实迁移技术，用于学习富含接触信息的技能，支持密集、分布式、三轴触觉读数。我们在盲插任务上评估该方法，展示了基于原始触觉输入的强化学习策略实现零样本仿真到现实迁移。
原文摘要 · Abstract (English)
Tactile sensing is an important sensing modality for robot manipulation. Among different types of tactile sensors, magnet-based sensors, like u-skin, balance well between high durability and tactile density. However, the large sim-to-real gap of tactile sensors prevents robots from acquiring useful tactile-based manipulation skills from simulation data, a recipe that has been successful for achieving complex and sophisticated control policies. Prior work has implemented binarization techniques to bridge the sim-to-real gap for dexterous in-hand manipulation. However, binarization inherently loses much information that is useful in many other tasks, e.g., insertion. In our work, we propose GCS, a novel sim-to-real technique to learn contact-rich skills with dense, distributed, 3-axis tactile readings. We evaluate our approach on blind insertion tasks and show zero-shot sim-to-real transfer of RL policies with raw tactile reading as input.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。