通过约束提取从视觉演示中教授富接触任务
Teaching contact-rich tasks from visual demonstrations by constraint extraction
AI总结：
针对富接触操作任务，提出从视觉演示中提取运动学约束的方法，通过聚类轨迹为离散接触模式并拟合约束，实现接触在线检测与机器人策略规划，实验证明其在接触转换中具有鲁棒性。
摘要：
富接触操作涉及任务运动的运动学约束，通常在任务过程中这些约束之间存在离散转换。允许机器人检测并推理这些接触约束可以支持鲁棒和动态的操作，但如何高效学习这些接触模型？纯视觉观测是一种极具吸引力的数据源，允许使用未修改的物体进行被动任务演示。现有的纯视觉演示学习方法在拾取与放置应用和平面任务中很有效。然而，精度/遮挡和未观测到的任务动力学会限制它们在富接触操作中的鲁棒性。为了将视觉演示用于富接触机器人任务，我们考虑了具有完整运动学约束之间转换的姿态轨迹演示，首先将轨迹聚类为离散接触模式，然后为每种模式拟合运动学约束。拟合的约束随后用于（i）通过力/力矩测量在线检测接触，以及（ii）相对于活动约束规划机器人策略。我们通过真实实验（在布线和耙子任务上）验证了该方法，表明该方法能在接触转换中实现鲁棒操作。
英文摘要：
Contact-rich manipulation involves kinematic constraints on the task motion, typically with discrete transitions between these constraints during the task. Allowing the robot to detect and reason about these contact constraints can support robust and dynamic manipulation, but how can these contact models be efficiently learned? Purely visual observations are an attractive data source, allowing passive task demonstrations with unmodified objects. Existing approaches for vision-only learning from demonstration are effective in pick-and-place applications and planar tasks. Nevertheless, accuracy/occlusions and unobserved task dynamics can limit their robustness in contact-rich manipulation. To use visual demonstrations for contact-rich robotic tasks, we consider the demonstration of pose trajectories with transitions between holonomic kinematic constraints, first clustering the trajectories into discrete contact modes, then fitting kinematic constraints per each mode. The fit constraints are then used to (i) detect contact online with force/torque measurements and (ii) plan the robot policy with respect to the active constraint. We demonstrate the approach with real experiments, on cabling and rake tasks, showing the approach gives robust manipulation through contact transitions.
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。
