---
title: "Amazon's LadderMan Teaches Humanoid Robots to Climb at Near-Human Speed"
subtitle: "Amazon FAR's LadderMan teaches a humanoid robot to climb diverse real-world ladders and perform manipulation tasks using a single motion capture reference and zero-shot sim-to-real transfer."
url: "https://alphasignal.ai/news/amazon-s-ladderman-teaches-humanoid-robots-to-climb-at-near-human-speed"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-04T00:00:00.000Z"
updated: "2026-06-12T01:26:21.477Z"
type: "Paper"
topics:
  - "Robotics"
  - "Post Training"
subtopics:
  - "Vla Models"
  - "Distillation"
  - "Rl"
upvotes: 4500
source_url: "https://arxiv.org/abs/2606.05873"
comments: 0
truncated: true
---

# Amazon's LadderMan Teaches Humanoid Robots to Climb at Near-Human Speed

> Amazon FAR's LadderMan teaches a humanoid robot to climb diverse real-world ladders and perform manipulation tasks using a single motion capture reference and zero-shot sim-to-real transfer.

Getting a humanoid robot to walk on flat ground is hard enough. Getting it to climb a ladder, perceive the rungs in real time, and then adjust a wall painting while perched at the top? That is a different problem entirely. Researchers from Amazon FAR, UC Berkeley, Stanford, USC, and CMU have released [LadderMan](https://ladderman-robot.github.io/), a system that does exactly that on a Unitree G1 humanoid, with no hardware modifications and no fine-tuning on the target ladder.

## Why ladders are so brutally hard

Ladder climbing sits at the intersection of everything that makes humanoid control difficult. Unlike walking on flat ground or stairs, ladder climbing requires precise and sustained coordination between upper and lower body contacts under sparse, discontinuous, and narrow footholds and handholds. Miss a rung by a centimeter and the robot falls. The problem is compounded by the real world: ladders vary in inclination angle, rung spacing, rung width, and material. A policy trained on one ladder will almost certainly fail on another.

Prior work on ladder climbing largely relies on carefully engineered model-based control without incorporating perception into the control loop, and requires accurate environment modeling, task-specific tuning, and specialized hardware design. These approaches typically exhibit slow climbing speeds, limited robustness, and poor generalization beyond specific ladder configurations. Learning-based approaches existed for quadruped robots, but humanoids introduce a harder version of the problem: heterogeneous limbs, a much taller and less stable body, and the need to coordinate hands and feet simultaneously.

## A four-stage pipeline from one motion clip

LadderMan's core insight is to decompose the problem into stages rather than trying to learn everything end-to-end. The climbing policy is built on a scalable two-stage learning pipeline, where hybrid motion tracking is used to learn multiple climbing experts from a single reference motion, and these experts are distilled into a unified depth-based visuomotor climbing policy via hybrid imitation and reinforcement learning.

![LadderMan four-stage pipeline overview: expert policy learning, perceptive policy distillation, sim-to-real transfer, and on-ladder manipulation](https://arxiv.org/html/2606.05873v1/x2.png) 

Here is how the four stages work in practice:

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

## Sources

- [LadderMan: Learning Humanoid Perceptive Ladder Climbing (arXiv)](https://arxiv.org/html/2606.05873)
- [LadderMan Project Website](https://ladderman-robot.github.io/)
- [LadderMan GitHub Repository](https://github.com/amazon-far/LadderMan)