Sketch-to-Skill：利用人类绘制的轨迹草图引导机器人学习
Sketch-to-Skill: Bootstrapping Robot Learning with Human Drawn Trajectory Sketches
AI总结：
提出 Sketch-to-Skill 框架，将人类二维草图转为三维轨迹以自动生成演示，并结合行为克隆与引导式强化学习，显著降低机器人操作学习门槛。
摘要：
训练机器人操作策略传统上需要大量演示和/或环境交互轨迹。尽管近期的模仿学习（IL）和强化学习（RL）方法已减少所需演示数量，但它们仍依赖专家知识来收集高质量数据，从而限制了可扩展性和可及性。我们提出 Sketch-to-Skill，这是一种利用人类绘制的二维草图轨迹来引导并指导机器人操作强化学习的新颖框架。我们的方法超越了以往主要聚焦于模仿学习或策略条件化、且局限于特定训练任务的基于草图的方法。Sketch-to-Skill 采用一个 Sketch-to-3D Trajectory Generator（草图到三维轨迹生成器），将二维草图转换为三维轨迹，随后这些轨迹被用于自主收集初始演示。我们以两种方式利用这些由草图生成的演示：通过行为克隆预训练一个初始策略，以及通过带引导探索的强化学习来改进该策略。实验结果表明，仅依据草图输入，Sketch-to-Skill 达到了利用遥操作演示数据的基线模型约96%的性能，同时比纯强化学习策略的性能高出约170%。这使机器人操作学习更易获得，并有可能拓展其在多个领域中的应用。
英文摘要：
Training robotic manipulation policies traditionally requires numerous demonstrations and/or environmental rollouts. While recent Imitation Learning (IL) and Reinforcement Learning (RL) methods have reduced the number of required demonstrations, they still rely on expert knowledge to collect high-quality data, limiting scalability and accessibility. We propose Sketch-to-Skill, a novel framework that leverages human-drawn 2D sketch trajectories to bootstrap and guide RL for robotic manipulation. Our approach extends beyond previous sketch-based methods, which were primarily focused on imitation learning or policy conditioning, limited to specific trained tasks. Sketch-to-Skill employs a Sketch-to-3D Trajectory Generator that translates 2D sketches into 3D trajectories, which are then used to autonomously collect initial demonstrations. We utilize these sketch-generated demonstrations in two ways: to pre-train an initial policy through behavior cloning and to refine this policy through RL with guided exploration. Experimental results demonstrate that Sketch-to-Skill achieves ~96% of the performance of the baseline model that leverages teleoperated demonstration data, while exceeding the performance of a pure reinforcement learning policy by ~170%, only from sketch inputs. This makes robotic manipulation learning more accessible and potentially broadens its applications across various domains.
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。
