TL;DR
CANINE is an adaptive coaching system that trains visually impaired users for interactive navigation with robot guide dogs, significantly improving learning efficiency and navigation skills through personalized verbal feedback.
Contribution
It introduces a novel multi-level adaptive coaching framework using knowledge tracing and foundation models for personalized training of complex human-robot coordination skills.
Findings
CANINE significantly improves learning efficiency and navigation performance.
The system demonstrates lasting skill retention after two weeks.
Effective in training a visually impaired user, with insights for real-world deployment.
Abstract
Robot guide dogs offer navigation assistance that greatly expands the independent mobility of the visually impaired, but their effective use requires subtle human-robot coordination that is difficult for users to learn from generic verbal instructions. To tackle this challenge, we present CANINE, an automated coaching system that trains users for interactive navigation with a robot guide dog, through personalized, adaptive verbal feedback. CANINE decomposes a complex coordination task into sub-skills and operates at two levels. At the high level, it decides what to train by tracking the learner's proficiency across sub-skills using knowledge tracing and prioritizing training on the weakest areas. At the low level, CANINE decides how to train each sub-skill by observing each human practice episode, using foundation models to infer the underlying causes of errors, and generating targeted…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
