Programming by Demonstration with User-Specified Perceptual Landmarks
This work addresses the need for more adaptable perception in robotics for end-users, though it appears incremental as it builds on existing programming by demonstration frameworks.
The paper tackles the problem of generalizing robot manipulation tasks to new scenes in programming by demonstration by introducing a flexible perception system that allows users to specify perceptual landmarks, and it experimentally evaluates the method in various settings and demonstrates its feasibility through user evaluations.
Programming by demonstration (PbD) is an effective technique for developing complex robot manipulation tasks, such as opening bottles or using human tools. In order for such tasks to generalize to new scenes, the robot needs to be able to perceive objects, object parts, or other task-relevant parts of the scene. Previous work has relied on rigid, task-specific perception systems for this purpose. This paper presents a flexible and open-ended perception system that lets users specify perceptual "landmarks" during the demonstration, by capturing parts of the point cloud from the demonstration scene. We present a method for localizing landmarks in new scenes and experimentally evaluate this method in a variety of settings. Then, we provide examples where user-specified landmarks are used together with PbD on a PR2 robot to perform several complex manipulation tasks. Finally, we present findings from a user evaluation of our landmark specification interface demonstrating its feasibility as an end-user tool.