Surrogate Assisted Generation of Human-Robot Interaction Scenarios
This work addresses the computational cost of scenario generation for human-robot interaction evaluation, offering an incremental improvement for researchers and developers in robotics.
The paper tackled the problem of evaluating human-robot interaction systems by proposing surrogate models to predict human and robot behaviors, which efficiently generated diverse datasets of challenging scenarios in shared control teleoperation and shared workspace collaboration tasks, with failures shown to be reproducible in real-world interactions.
As human-robot interaction (HRI) systems advance, so does the difficulty of evaluating and understanding the strengths and limitations of these systems in different environments and with different users. To this end, previous methods have algorithmically generated diverse scenarios that reveal system failures in a shared control teleoperation task. However, these methods require directly evaluating generated scenarios by simulating robot policies and human actions. The computational cost of these evaluations limits their applicability in more complex domains. Thus, we propose augmenting scenario generation systems with surrogate models that predict both human and robot behaviors. In the shared control teleoperation domain and a more complex shared workspace collaboration task, we show that surrogate assisted scenario generation efficiently synthesizes diverse datasets of challenging scenarios. We demonstrate that these failures are reproducible in real-world interactions.