The authors built Revisable Temporal Planning, or RTP, on a task-adapted LingBot-VA world-action model.
Robots Can Revise Visual Plans Instead of Starting Over
A learned revision mechanism updates predicted visual futures after execution feedback and uses them to guide subsequent robot actions.
Top University
Pengyiang Liu · Junbo Niu · Wenhao Zheng · Xinchen Chen · Canyu Li · Zhongyue Shi · +2 more
Beihang University · Peking University
Research Digest··2 min read
Liu et al.
Why this paper
From Beihang University and Peking University
In one line
Revisable Temporal Planning revises a robot's visual plan after execution feedback by continuing from a saved intermediate generation state.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§