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.

翻译：接触密集型操作涉及任务运动中的运动学约束，通常伴随这些约束在任务执行过程中的离散转换。让机器人能够检测并推理这些接触约束，有助于实现稳健且动态的操作，但如何高效学习这些接触模型？纯视觉观测是一种有吸引力的数据源，可以在不修改物体的情况下进行被动任务演示。现有的纯视觉学习演示方法在拾取-放置应用和平面任务中效果显著，但在接触密集型操作中，精度/遮挡和未观测到的任务动态可能限制其鲁棒性。为将视觉演示应用于接触密集型机器人任务，我们考虑演示具有完整运动学约束间转换的位姿轨迹：首先将轨迹聚类为离散接触模式，然后为每个模式拟合运动学约束。拟合后的约束用于（i）通过力/力矩测量在线检测接触，以及（ii）基于当前活动约束规划机器人策略。我们通过电缆插接和耙取任务的实际实验验证了该方法，结果表明该方法能通过接触转换实现稳健操作。