Legible Robot Motion Planning
In order to distinguish essays and pre-prints from academic theses, we have a separate category. These are often much longer text based documents than a paper.
The goal of this thesis is to enable robots to produce motion that is suitable for human-robot collaboration and co-existence. Most motion in robotics is purely functional: industrial robots move to package parts, vacuuming robots move to suck dust, and personal robots move to clean up a dirty table. This type of motion is ideal when the robot is performing a task in isolation. Collaboration, however, does not happen in isolation. In collaboration, the robot’s motion has an observer, watching and interpreting the motion. In this work, we move beyond functional motion, and introduce the notion of an observer into motion planning, so that robots can generate motion that is mindful of how it will be interpreted by a human collaborator. We formalize predictability and legibility as properties of motion that naturally arise from the inferences that the observer makes, drawing on action interpretation theory in psychology. Predictable motion stems from a goal-to-action inference and matches the observer’s expectation, given the robot’s goal. Legible motion stems from an action-to-goal inference: the robot is clearly conveying its goal with its ongoing motion. We propose models for these inferences based on the principle of rational action, Bayesian inference, and the principle of maximum entropy. We then use a combination of constrained trajectory optimization and machine learning techniques to enable robots to plan motion that is predictable or legible. Finally, we verify that the generated motions are more predictable and legible, and evaluate the impact of such motion on a physical human-robot collaboration task. Our results suggest that predictability and legibility do not only increase task performance, but also make the collaboration process more fluent, increasing subjective metrics such as trust or comfort. We also show generalizations of the legibility formalism to deception, gestures, and assistive teleoperation.