BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
Wanget al.BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Traversing risky terrains with sparse footholds poses a significant challenge for humanoid robots, requiring precise foot placements and stable locomotion. Existing learning-based approaches often struggle on such complex terrains due to sparse foothold rewards and inefficient learning processes. To address these challenges, we introduce BeamDojo, a reinforcement learning (RL) framework designed for enabling agile humanoid locomotion on sparse footholds. BeamDojo begins by introducing a sampling-based foothold reward tailored for polygonal feet, along with a double critic to balancing the learning process between dense locomotion rewards and sparse foothold rewards. To encourage sufficient trial-and-error exploration, BeamDojo incorporates a two-stage RL approach: the first stage relaxes the terrain dynamics by training the humanoid on flat terrain while providing it with task-terrain perceptive observations, and the second stage fine-tunes the policy on the actual task terrain. Moreover, we implement a onboard LiDAR-based elevation map to enable real-world deployment. Extensive simulation and real-world experiments demonstrate that BeamDojo achieves efficient learning in simulation and enables agile locomotion with precise foot placement on sparse footholds in the real world, maintaining a high success rate even under significant external disturbances.
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 12roles
background 1polarities
background 1representative citing papers
A proprioceptive humanoid policy trained with slope-adaptive ZMP regularization plus biomechanical reward gating traverses outdoor grass slopes to 32.1° without online exteroception.
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to new goal locations without per-task reward tuning.
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
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.
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
TA-WBC is a terrain-aware RL policy for legged loco-manipulation using exteroception, contact-plane sampling, and distillation to improve reachable space, tracking, and stability across terrains.
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
Integrating foot position maps into heightmaps and adding a locomotion-stability reward in an attention-based RL framework improves quadrupedal success rates on both trained and out-of-domain complex terrains.
UniCon standardizes states and control logic into modular execution graphs for efficient transfer of learning controllers across heterogeneous robots, with lower latency than ROS.
citing papers explorer
-
BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
-
Physics-Guided Biomechanical Gait Adaptation for Humanoid Locomotion on Extreme Sloped Terrains
A proprioceptive humanoid policy trained with slope-adaptive ZMP regularization plus biomechanical reward gating traverses outdoor grass slopes to 32.1° without online exteroception.
-
TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes
TaskNPoint lets humanoid robots learn dynamic skills such as tennis backhands from single short human video demonstrations plus under one hour of single-GPU simulation training, achieving zero-shot generalization to new goal locations without per-task reward tuning.
-
OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation
OmniContact introduces contact flow as a shared representation of body trajectories and contact signals to learn and chain loco-manipulation meta-skills, reporting 98.7% success on box carrying and 76.5% on push-stack tasks.
-
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.
-
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.
-
Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation
TA-WBC is a terrain-aware RL policy for legged loco-manipulation using exteroception, contact-plane sampling, and distillation to improve reachable space, tracking, and stability across terrains.
-
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
-
Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy
Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.
-
Learning Locomotion on Complex Terrain for Quadrupedal Robots with Foot Position Maps and Stability Rewards
Integrating foot position maps into heightmaps and adding a locomotion-stability reward in an attention-based RL framework improves quadrupedal success rates on both trained and out-of-domain complex terrains.
-
UniCon: A Unified System for Efficient Robot Learning Transfers
UniCon standardizes states and control logic into modular execution graphs for efficient transfer of learning controllers across heterogeneous robots, with lower latency than ROS.
- Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion