Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids

Traversing sparse 3D structures requires humanoid robots to perceive thin, overhanging geometry while executing agile, accurate whole-body motions. We study this problem through monkey-bar traversal, where the robot must jump to the structure, traverse it through sparse bar interactions, and land safely. For this task, we present a learning-based perceptive control system that operates directly on observations from a head-mounted solid-state lidar. To extract task-relevant geometry from the sparse returns, the policy consumes the raw lidar scan through an attention-based encoder with recurrent memory. This policy is obtained by a phase-scheduled teacher–student pipeline that combines privileged experts for jumping up, brachiating, and jumping down. For transfer to hardware, we model lidar noise, battery-voltage sag, and actuator thermal limits, and equip the humanoid with passive hook end-effectors for robust bar interaction. On hardware, the resulting policy completes the full jump-up→brachiation→jump-down sequence in 14 of 15 trials across three bar configurations and reaches brachiation speeds up to 0.5 m/s. Beyond brachiation, the same perception backbone supports a separately trained policy that ducks beneath thin overhead obstacles with 2 cm cross-sections.

Monkey-bar traversal

Ducking under thin obstacles

BibTeX

@misc{ongan2026learningagileperceptivetraversal,
      title={Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids},
      author={Efe Ongan and Chong Zhang and Boyang Sun and Andrei Cramariuc and Cesar Cadena and Marco Hutter},
      year={2026},
      eprint={2608.29769},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2608.29769},
}