A vision-language-action policy that jointly produces an end-effector trajectory and whole-body actions, then refines actions with a lightweight world model, improves mobile manipulation success.
International Conference on Learning Representations , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DreamTrajectory: Trajectory-Guided Action Generation with World Model Alignment for Mobile Manipulation
A vision-language-action policy that jointly produces an end-effector trajectory and whole-body actions, then refines actions with a lightweight world model, improves mobile manipulation success.