Event
Proposing an explainability framework for assistive robot navigation
1 reports · 1 sources
Researchers including Courtney proposed the Context-Aware Navigation Explanation framework, which uses large language models combined with perceptual context and planned trajectories to generate natural-language explanations for obstacle avoidance and navigation by assistive robots (guide robots for the blind), and conducted real-world deployment and evaluation in indoor navigation scenarios on the Unitree Go2 platform. The evaluation examined the effects of different explanation context configurations on user trust and explanation satisfaction. Results showed that explanation satisfaction was strongly positively correlated with user trust; the configuration combining obstacle information with future trajectories was considered by the researchers to produce the most effective explanations.
Report timeline
- An Explainability Framework for LLM-Based Assistive Robot Obstacle Avoidance Navigation
The study proposes the Context-Aware Navigation Explanation framework, which uses a large language model combined with perceptual context and planned trajectories to generate natural-language explanations for assistive robot obstacle avoidance and navigation. The system is deployed on a Unitree Go2 platform in indoor navigation scenarios to evaluate how different explanation context configurations affect user trust and explanation satisfaction. Results show a strong positive correlation between explanation satisfaction and trust, and that the configuration combining obstacle information with future trajectory produced the best explanations.
arXiv cs.RO ·