Pith. sign in

REVIEW 12 cited by

BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.10363 v3 pith:2MCEBZXP submitted 2025-02-14 cs.RO cs.AIcs.LG

BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds

classification cs.RO cs.AIcs.LG
keywords sparsebeamdojolearninglocomotionfootholdshumanoidagilefoothold
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion

    cs.RO 2025-08 conditional novelty 7.0

    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.

  2. Physics-Guided Biomechanical Gait Adaptation for Humanoid Locomotion on Extreme Sloped Terrains

    cs.RO 2026-07 conditional novelty 6.0

    A proprioceptive humanoid policy trained with slope-adaptive ZMP regularization plus biomechanical reward gating traverses outdoor grass slopes to 32.1° without online exteroception.

  3. TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes

    cs.RO 2026-06 unverdicted novelty 6.0

    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 n...

  4. OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation

    cs.RO 2026-06 unverdicted novelty 6.0

    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.

  5. Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain

    cs.RO 2026-06 unverdicted novelty 6.0

    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.

  6. TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion

    cs.RO 2026-06 unverdicted novelty 6.0

    TAGA learns terrain-aware active gaze behaviors for humanoid robots via RL alone, enabling generalizable locomotion with 1.2m real-world gap traversal.

  7. Global-Local Attention Decomposition for Terrain Encoding in Humanoid Perceptive Locomotion

    cs.RO 2026-05 unverdicted novelty 5.0

    GLAD decomposes terrain encoding via coarse-to-fine attention on elevation maps to separate broad awareness from precise foothold selection in perceptive humanoid locomotion.

  8. Learning Terrain-Aware Whole-Body Control for Perceptive Legged Loco-Manipulation

    cs.RO 2026-05 unverdicted novelty 5.0

    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.

  9. MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots

    cs.RO 2026-05 unverdicted novelty 5.0

    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.

  10. Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy

    cs.RO 2026-05 unverdicted novelty 5.0

    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 ter...

  11. Learning Locomotion on Complex Terrain for Quadrupedal Robots with Foot Position Maps and Stability Rewards

    cs.RO 2026-04 unverdicted novelty 5.0

    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.

  12. UniCon: A Unified System for Efficient Robot Learning Transfers

    cs.RO 2026-01 unverdicted novelty 5.0

    UniCon standardizes states and control logic into modular execution graphs for efficient transfer of learning controllers across heterogeneous robots, with lower latency than ROS.