Trajectory consistency training, smoothness regularization, and higher-order integration for flow matching policies deliver 60-70% success on long-horizon real-robot tasks where baselines achieve 0%.
Alvinn: An autonomous land vehicle in a neural network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning
Trajectory consistency training, smoothness regularization, and higher-order integration for flow matching policies deliver 60-70% success on long-horizon real-robot tasks where baselines achieve 0%.