---
title: "ETH Zurich's Humanoid Robot Swings Across Monkey Bars in 14 of 15 Tries"
subtitle: "A humanoid robot jumps onto monkey bars, swings across at half a meter per second, and drops safely, guided by raw lidar and a reinforcement-learned policy."
url: "https://alphasignal.ai/news/eth-zurich-s-humanoid-robot-swings-across-monkey-bars-in-14-of-15-tries"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-08-30T12:56:43.000Z"
updated: "2026-09-06T00:03:14.918Z"
type: "Paper"
topics:
  - "Robotics"
  - "Post Training"
subtopics:
  - "Vla Models"
  - "Rl"
  - "Distillation"
upvotes: 262
source_url: "https://arxiv.org/abs/2608.29769"
comments: 0
truncated: true
---

# ETH Zurich's Humanoid Robot Swings Across Monkey Bars in 14 of 15 Tries

> A humanoid robot jumps onto monkey bars, swings across at half a meter per second, and drops safely, guided by raw lidar and a reinforcement-learned policy.

Getting a humanoid robot to walk over rough ground is one thing. Leaping onto monkey bars, swinging hand over hand, and dismounting cleanly is an entirely different class of problem. A new paper from ETH Zurich tackles exactly that, with the resulting policy completing the full sequence in [14 of 15 hardware trials](https://arxiv.org/abs/2608.29769).

The work, titled [Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids](https://arxiv.org/html/2608.29769), uses monkey-bar brachiation as a stress test for three problems that usually get studied in isolation: perceiving thin geometry with lidar, discovering precise contact sequences through exploration, and executing whole-body motion within the torque and thermal limits of real hardware.

## Why monkey bars are a nasty benchmark

Most perceptive locomotion research assumes the robot stands on something. Ground can be represented as an elevation map, a 2.5D grid where every cell has a height. Monkey bars break that assumption. The support structure is overhead, sparse, and made of thin cylinders that solid-state lidar barely registers. Adjacent work like APEX (high-platform climbing) and perceptive humanoid parkour has pushed on parts of this problem, but none combined a mid-air jump, a swinging traverse, and a controlled landing in a single policy.

![Humanoid robot traversing three different monkey bar configurations](https://arxiv.org/html/2608.29769v1/media/three_diffrent_ladders.png) 

## Raw lidar straight into the policy

The robot carries a head-mounted solid-state lidar. Because the bars are thin, each scan produces only a handful of relevant returns, and those returns jitter frame to frame. Rather than pre-processing into a voxel grid or fitting geometry, the policy consumes raw lidar through an attention-based encoder with recurrent memory. The attention layer picks out sparse task-relevant points from thousands of returns, while the recurrent layer integrates them over time so the robot accumulates a stable estimate of each bar's position even when individual scans are noisy. The encoder design draws from prior attention-based work on elevation-map encoding for legged locomotion, adapted here to operate on raw point returns instead of a pre-built map.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Learning Agile Perceptive Traversal of Sparse 3D Structures for Humanoids](https://arxiv.org/abs/2608.29769)
- [Full paper HTML](https://arxiv.org/html/2608.29769)
- [APEX: Learning Adaptive High-Platform Traversal for Humanoid Robots](https://arxiv.org/html/2602.11143)
- [Author announcement on X](https://twitter.com/ChongZzZhang/status/2094695161796104236)