Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
Residual Reinforce- ment Learning for Robot Control
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
TAM is a policy-agnostic torque adaptation module trained in randomized simulation that improves zero-shot real-robot performance on dynamic manipulation tasks compared to system identification and RMA baselines.
An LSTM state estimator paired with a residual RL policy enables robust robot teleoperation under stochastic delays by reconstructing continuous states and learning compensatory torques, outperforming baselines on Franka Panda robots.
Residual reinforcement learning automates map-based ECU calibration to closely match series production references with minimal human intervention.
citing papers explorer
-
Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
Perceptive BFM grounds human motion priors in robot terrain perception via terrain-conformal reference synthesis and teacher-student transfer from adapted to raw-reference tracking.
-
TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation
TAM is a policy-agnostic torque adaptation module trained in randomized simulation that improves zero-shot real-robot performance on dynamic manipulation tasks compared to system identification and RMA baselines.
-
Residual Reinforcement Learning for Robot Teleoperation under Stochastic Delays
An LSTM state estimator paired with a residual RL policy enables robust robot teleoperation under stochastic delays by reconstructing continuous states and learning compensatory torques, outperforming baselines on Franka Panda robots.
-
Production-Ready Automated ECU Calibration using Residual Reinforcement Learning
Residual reinforcement learning automates map-based ECU calibration to closely match series production references with minimal human intervention.