robotics
Two Robot Dogs Shared the Errand
A validated schedule let one assistive robot guide a user while another fetched an object, cutting mean completion time by 41.3 percent in matched successes.
Summary
A validated schedule let one assistive robot guide a user while another fetched an object, cutting mean completion time by 41.3 percent in matched successes.
GuideFetch normalizes targets and skills, validates an LLM-produced four-action schedule against robot capabilities, then tracks robot and object state during sequential or parallel execution. Across 360 controlled runs, online plans matched their scripted counterparts; among 56 cases completed under both schedules, parallel execution reduced mean makespan by 41.3 percent. The result belongs to simulated task combinations, not unsupervised public deployment.
Why it matters
A validated schedule let one assistive robot guide a user while another fetched an object, cutting mean completion time by 41.3 percent in matched successes.
Limits and context
- The result belongs to simulated task combinations, not unsupervised public deployment.
Key claims
A validated schedule let one assistive robot guide a user while another fetched an object, cutting mean completion time by 41.3 percent in matched successes.
Qualification: The result belongs to simulated task combinations, not unsupervised public deployment.
Evidence: source-2026-08-20-003
Sources
- arXiv preprint 2608.18292arXiv · primary research
Corrections
No corrections have been recorded for this story.