Generating Legible Motion

Abstract

Abstract-Legible motion -motion that communicates its intent to a human observer -is crucial for enabling seamless human-robot collaboration. In this paper, we propose a functional gradient optimization technique for autonomously generating legible motion. Our algorithm optimizes a legibility metric inspired by the psychology of action interpretation in humans, resulting in motion trajectories that purposefully deviate from what an observer would expect in order to better convey intent. A trust region constraint on the optimization ensures that the motion does not become too surprising or unpredictable to the observer.Our studies with novice users that evaluate the resulting trajectories support the applicability of our method and of such a trust region. They show that within the region, legibility as measured in practice does significantly increase. Outside of it, however, the trajectory becomes confusing and the users' confidence in knowing the robot's intent significantly decreases.

Effects of Robot Motion on Human-Robot Collaboration

“…This section summarizes the three motion planning paradigms compared in the study: purely functional motion planning, which is typically achieved via sampling-based methods, and predictable and legible motion planning as defined in our prior work [4], achieved via trajectory optimization. Notation.…”

“…Given an ongoing trajectory ξ S→Q , the probability that the collaborator will assign to any goal G ∈ G can be modeled [4] as:…”

“…However, instead of optimizing C, it optimizes the probability that the collaborator will infer G R along the trajectory [4]:…”

“…The robot generated predictable and legible trajectories following [4], using functional gradient optimization, and initializing the optimizer with a straight line, constant velocity trajectory. As the next section will detail, one measure is how quickly participants infer the goal.…”

“…Our recent work introduced motion planners that autonomously generate motion with these properties, and tested their ability to produce more predictable or more legible motion via online video-based studies in a non-collaborative setting [4,6]. With this, we know the robot can produce more predictable or legible motion, but what we do not know is how this affects human-robot interaction.…”