Event
Review: Enabling robots to explain their own behavior and self-extend
1 reports · 1 sources
An arXiv cs.RO review surveys recent progress in self-aware, self-evolving robots, with the goal of enabling robots to explain to humans the reasons for their own actions, planning failures, or perceptual anomalies. The authors argue that deep learning alone cannot bridge this gap, because the reasons behind a black-box model's behavior are inaccessible, and an underlying architecture based on deeper reasoning is needed. The authors propose that when explanations arise from cognitive processes and are shared with and validated by humans, robots should be able to incorporate them into their knowledge base to improve subsequent behavior.
Report timeline
- Causal-based approaches to explain and learn from self-extension: A review
This review surveys recent advances in aware, self-evolving robots, with the goal of enabling robots to give humans explanations for the reasons behind their actions, plan failures, or perceptual anomalies. The authors note that deep learning alone cannot close this gap, because the reasons behind the behavior of black-box models are not accessible; an underlying architecture based on deeper reasoning is needed. When explanations arise from cognitive processes and are shared with and validated by humans, the robot should be able to incorporate them into its knowledge base to improve subsequent behavior.
arXiv cs.RO ·