RoCUS: Robot Controller Understanding via Sampling
This work provides a systematic analysis framework for engineers and end users to understand emergent robot behaviors, which is crucial for safe and trustworthy robot deployment.
This paper addresses the challenge of understanding robot controller behaviors beyond those directly optimized by the objective function. It proposes RoCUS, a framework that uses Bayesian posterior sampling to identify situations where a robot controller exhibits user-specified behaviors, such as jerky motions. RoCUS was applied to three controller classes across two domains, yielding insights for improving controller designs.
As robots are deployed in complex situations, engineers and end users must develop a holistic understanding of their behaviors, capabilities, and limitations. Some behaviors are directly optimized by the objective function. They often include success rate, completion time or energy consumption. Other behaviors -- e.g., collision avoidance, trajectory smoothness or motion legibility -- are typically emergent but equally important for safe and trustworthy deployment. Designing an objective which optimizes every aspect of robot behavior is hard. In this paper, we advocate for systematic analysis of a wide array of behaviors for holistic understanding of robot controllers and, to this end, propose a framework, RoCUS, which uses Bayesian posterior sampling to find situations where the robot controller exhibits user-specified behaviors, such as highly jerky motions. We use RoCUS to analyze three controller classes (deep learning models, rapidly exploring random trees and dynamical system formulations) on two domains (2D navigation and a 7 degree-of-freedom arm reaching), and uncover insights to further our understanding of these controllers and ultimately improve their designs.