This paper proposes a learning-from-demonstration method using probability densities on the workspaces of robot manipulators. The method, named "PRobabilistically-Informed Motion Primitives (PRIMP)", learns the probability distribution of the end effector trajectories in the 6D workspace that includes both positions and orientations. It is able to adapt to new situations such as novel via poses with uncertainty and a change of viewing frame. The method itself is robot-agnostic, in which the learned distribution can be transferred to another robot with the adaptation to its workspace density. The learned trajectory distribution is then used to guide an optimization-based motion planning algorithm to further help the robot avoid novel obstacles that are unseen during the demonstration process. The proposed methods are evaluated by several sets of benchmark experiments. PRIMP runs more than 5 times faster while generalizing trajectories more than twice as close to both the demonstrations and novel desired poses. It is then combined with our robot imagination method that learns object affordances, illustrating the applicability of PRIMP to learn tool use through physical experiments.

翻译：本文提出一种基于机器人工作空间概率密度的示教学习方法。该方法名为“概率化运动基元（PRIMP）”，通过学习包含位置与姿态的六维工作空间中末端执行器轨迹的概率分布，能够适应新场景（如存在不确定性的新颖途径位姿及观察坐标系变更）。该方法具有机器人无关性，可将其学习到的分布迁移至另一台机器人，并适配其工作空间密度。随后，该轨迹分布被用于指导基于优化的运动规划算法，进一步帮助机器人规避示教过程中未见过的新障碍物。通过多组基准实验对所提方法进行评估：PRIMP在运行速度提升5倍以上的同时，生成的轨迹与示教轨迹及新目标位姿的距离均缩短至两倍以内。最终，该方法与学习物体功能属性的机器人想象方法相结合，通过物理实验验证了PRIMP在工具使用学习中的实用性。