人机协同数据高效模仿学习
Human-Robot Copilot for Data-Efficient Imitation Learning
AI总结：
本文提出人机协同框架，通过调整缩放因子实现灵活远程操作，同时兼容多种工业和研究机械臂，实验显示在相同演示轨迹数下性能更优，数据收集更高效。
摘要：
通过遥控收集人类示范是教机器人特定技能的常见方法。然而，当只有有限的示范可用时，策略容易因累积误差或环境随机性进入分布外状态。现有交互模仿学习或人机交互方法通过遵循人类门控DAgger（HG-DAgger）范式来解决此问题，即通过选择性的人类干预在策略执行期间增强示范。然而，这些方法难以平衡灵巧性和通用性：要么提供精细的修正但局限于特定运动学结构，要么为通用性牺牲精确控制。为克服这一限制，我们提出了人机协同框架，该框架可以利用缩放因子实现灵巧的远程操作，同时保持与广泛工业和研究机械臂的兼容性。实验结果表明，我们的框架在相同数量的演示轨迹下实现了更高的性能。此外，由于纠正干预仅需间歇性进行，因此整体数据收集过程更加高效且耗时更少。
英文摘要：
Collecting human demonstrations via teleoperation is a common approach for teaching robots task-specific skills. However, when only a limited number of demonstrations are available, policies are prone to entering out-of-distribution (OOD) states due to compounding errors or environmental stochasticity. Existing interactive imitation learning or human-in-the-loop methods try to address this issue by following the Human-Gated DAgger (HG-DAgger) paradigm, an approach that augments demonstrations through selective human intervention during policy execution. Nevertheless, these approaches struggle to balance dexterity and generality: they either provide fine-grained corrections but are limited to specific kinematic structures, or achieve generality at the cost of precise control. To overcome this limitation, we propose the Human-Robot Copilot framework that can leverage a scaling factor for dexterous teleoperation while maintaining compatibility with a wide range of industrial and research manipulators. Experimental results demonstrate that our framework achieves higher performance with the same number of demonstration trajectories. Moreover, since corrective interventions are required only intermittently, the overall data collection process is more efficient and less time-consuming.
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。
