On the Utility of Model Learning in HRI
This work addresses the challenge of improving robot decision-making in HRI for autonomous driving, but it is incremental as it builds on existing debates without introducing a new paradigm.
The paper tackles the problem of whether robots should use model-based or model-free learning in human-robot interaction (HRI), specifically by comparing black-box and grey-box (theory of mind) approaches for modeling humans in an autonomous driving task, finding that performance varies under different scenarios of correct or incorrect assumptions.
Fundamental to robotics is the debate between model-based and model-free learning: should the robot build an explicit model of the world, or learn a policy directly? In the context of HRI, part of the world to be modeled is the human. One option is for the robot to treat the human as a black box and learn a policy for how they act directly. But it can also model the human as an agent, and rely on a "theory of mind" to guide or bias the learning (grey box). We contribute a characterization of the performance of these methods for an autonomous driving task under the optimistic case of having an ideal theory of mind, as well as under different scenarios in which the assumptions behind the robot's theory of mind for the human are wrong, as they inevitably will be in practice.