ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.
Libero: Benchmarking knowledge transfer for lifelong robot learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2023 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Any-point Trajectory Modeling for Policy Learning
ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.