Designing for Error Recovery in Human-Robot Interaction
For human-robot interaction researchers, this paper highlights the need for error recovery but offers only conceptual discussion without empirical results.
This position paper argues that current AI systems focus on one-shot decisions, while real-world interaction requires error recovery. It discusses challenges and simple designs for error recovery in robotic nuclear gloveboxes.
This position paper looks briefly at the way we attempt to program robotic AI systems. Many AI systems are based on the idea of trying to improve the performance of one individual system to beyond so-called human baselines. However, these systems often look at one shot and one-way decisions, whereas the real world is more continuous and interactive. Humans, however, are often able to recover from and learn from errors - enabling a much higher rate of success. We look at the challenges of building a system that can detect/recover from its own errors, using the example of robotic nuclear gloveboxes as a use case to help illustrate examples. We then go on to talk about simple starting designs.