Sketch-to-Skill: Bootstrapping Robot Learning with Human Drawn Trajectory Sketches
This makes robotic manipulation learning more accessible by reducing reliance on expert knowledge, though it is incremental as it builds on existing sketch-based and RL methods.
The paper tackles the problem of reducing the need for expert demonstrations in robotic manipulation by proposing Sketch-to-Skill, a framework that uses human-drawn 2D sketches to bootstrap reinforcement learning, achieving ~96% of the performance of a teleoperated baseline and ~170% improvement over pure reinforcement learning.
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.