Instructing Robots by Sketching: Learning from Demonstration via Probabilistic Diagrammatic Teaching
This addresses the challenge of making robot programming more accessible by reducing the need for physical handling or specialized hardware, though it is an incremental improvement over existing LfD methods.
The paper tackles the problem of enabling robots to learn new skills from user demonstrations by introducing Diagrammatic Teaching, which allows users to sketch trajectories on 2D images instead of using kinesthetic teaching or teleoperation, and it presents the RPTL framework that synthesizes these sketches into 3D motion models, validated in simulation and on real robots.
Learning for Demonstration (LfD) enables robots to acquire new skills by imitating expert demonstrations, allowing users to communicate their instructions in an intuitive manner. Recent progress in LfD often relies on kinesthetic teaching or teleoperation as the medium for users to specify the demonstrations. Kinesthetic teaching requires physical handling of the robot, while teleoperation demands proficiency with additional hardware. This paper introduces an alternative paradigm for LfD called Diagrammatic Teaching. Diagrammatic Teaching aims to teach robots novel skills by prompting the user to sketch out demonstration trajectories on 2D images of the scene, these are then synthesised as a generative model of motion trajectories in 3D task space. Additionally, we present the Ray-tracing Probabilistic Trajectory Learning (RPTL) framework for Diagrammatic Teaching. RPTL extracts time-varying probability densities from the 2D sketches, applies ray-tracing to find corresponding regions in 3D Cartesian space, and fits a probabilistic model of motion trajectories to these regions. New motion trajectories, which mimic those sketched by the user, can then be generated from the probabilistic model. We empirically validate our framework both in simulation and on real robots, which include a fixed-base manipulator and a quadruped-mounted manipulator.