FusionForce predicts robot trajectories by learning terrain properties from camera and lidar, then simulating them through a differentiable rigid-body physics engine, cutting trajectory error versus LSTM baselines by about three times.
Learning visual locomotion with cross-modal supervision,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
FusionForce: End-to-end Differentiable Neural-Symbolic Layer for Trajectory Prediction
FusionForce predicts robot trajectories by learning terrain properties from camera and lidar, then simulating them through a differentiable rigid-body physics engine, cutting trajectory error versus LSTM baselines by about three times.