FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
Humanoid-gym: Reinforcement learning for humanoid robot with zero-shot sim2real transfer
9 Pith papers cite this work, alongside 6 external citations. Polarity classification is still indexing.
9
Pith papers citing it
6
external citations · external index
fields
cs.RO 9representative citing papers
Selective AMP in RL enables a single policy for five humanoid gaits with faster convergence and better performance on stability tasks without losing dynamic agility.
CMP projects actions onto a learned competence manifold using a frame-wise safety scheme and isomorphic latent space to achieve up to 10x better survival in out-of-distribution scenarios with under 10% tracking loss.
HUSKY combines humanoid-skateboard dynamics modeling with adversarial motion priors and physics-guided lean-to-steer strategies to achieve real-world stable skateboarding on a humanoid robot.
SPRINT generates sprint trajectories for humanoids via spectral priors from five human motion sequences, achieving 6 m/s peak velocity with zero-shot sim-to-real transfer on Unitree G1.
ParkourFormer achieves 93.85% average success on multi-terrain humanoid parkour by fusing Transformer sequence modeling with supervised future-state prediction.
A two-stage distillation plus reinforced fine-tuning approach produces a single humanoid locomotion controller that adapts across skills and irregular terrains.
Describes an integrated pipeline for curating motion data, adapting real-to-sim models, applying AMP-based RL, and deploying locomotion policies on Booster T1 and K1 humanoid robots.
SRL combines SLIP feedforward with RL feedback to produce stable bipedal and quadrupedal jumps with lower training cost than pure RL.
citing papers explorer
-
FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control
FADA is a three-stage Planner-IDM method that achieves few-shot domain adaptation for humanoid control by distilling an oracle policy then finetuning only the IDM on short target-domain rollouts via supervised learning.
-
Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior
Selective AMP in RL enables a single policy for five humanoid gaits with faster convergence and better performance on stability tasks without losing dynamic agility.
-
CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projection
CMP projects actions onto a learned competence manifold using a frame-wise safety scheme and isomorphic latent space to achieve up to 10x better survival in out-of-distribution scenarios with under 10% tracking loss.
-
HUSKY: Humanoid Skateboarding System via Physics-Aware Whole-Body Control
HUSKY combines humanoid-skateboard dynamics modeling with adversarial motion priors and physics-guided lean-to-steer strategies to achieve real-world stable skateboarding on a humanoid robot.
-
SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints
SPRINT generates sprint trajectories for humanoids via spectral priors from five human motion sequences, achieving 6 m/s peak velocity with zero-shot sim-to-real transfer on Unitree G1.
-
ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion
ParkourFormer achieves 93.85% average success on multi-terrain humanoid parkour by fusing Transformer sequence modeling with supervised future-state prediction.
-
Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-Tuning
A two-stage distillation plus reinforced fine-tuning approach produces a single humanoid locomotion controller that adapts across skills and irregular terrains.
-
Booster Lab: A Data-Centric Pipeline for Learning Deployable Humanoid Locomotion Policies
Describes an integrated pipeline for curating motion data, adapting real-to-sim models, applying AMP-based RL, and deploying locomotion policies on Booster T1 and K1 humanoid robots.
-
SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping
SRL combines SLIP feedforward with RL feedback to produce stable bipedal and quadrupedal jumps with lower training cost than pure RL.