In recent decades, advancements in motion learning have enabled robots to acquire new skills and adapt to unseen conditions in both structured and unstructured environments. In practice, motion learning methods capture relevant patterns and adjust them to new conditions such as dynamic obstacle avoidance or variable targets. In this paper, we investigate the robot motion learning paradigm from a Riemannian manifold perspective. We argue that Riemannian manifolds may be learned via human demonstrations in which geodesics are natural motion skills. The geodesics are generated using a learned Riemannian metric produced by our novel variational autoencoder (VAE), which is especially intended to recover full-pose end-effector states and joint space configurations. In addition, we propose a technique for facilitating on-the-fly end-effector/multiple-limb obstacle avoidance by reshaping the learned manifold using an obstacle-aware ambient metric. The motion generated using these geodesics may naturally result in multiple-solution tasks that have not been explicitly demonstrated previously. We extensively tested our approach in task space and joint space scenarios using a 7-DoF robotic manipulator. We demonstrate that our method is capable of learning and generating motion skills based on complicated motion patterns demonstrated by a human operator. Additionally, we assess several obstacle avoidance strategies and generate trajectories in multiple-mode settings.

翻译：近几十年来，运动学习的进步使机器人能够在结构化和非结构化环境中习得新技能并适应未知条件。实践中，运动学习方法捕捉相关模式并将其调整为适应新条件（如动态避障或可变目标）。本文从黎曼流形视角研究机器人运动学习范式。我们提出，可通过人类示教学习黎曼流形，其中测地线即为自然运动技能。测地线通过我们新提出的变分自编码器（VAE）学习得到的黎曼度量生成，该编码器专用于恢复完整位姿的末端执行器状态及关节空间构型。此外，我们提出一种技术，通过利用障碍物感知的环境度量重塑已学习的流形，实现末端执行器/多肢体实时避障。基于这些测地线生成的运动能自然地解决先前未明确示教的多解任务。我们在任务空间和关节空间场景下，使用7自由度机械臂进行了广泛测试，证明该方法能基于人类操作员示教的复杂运动模式学习和生成运动技能。此外，我们评估了多种避障策略，并在多模态模式下生成了轨迹。