# Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator

arXiv: https://arxiv.org/abs/2509.03859 · HTML: https://mlsanity.com/paper/2509.03859/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2025.

## Built on by (most cited first, 3 of 3)

- [Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds](https://mlsanity.com/paper/2603.18532/) (2026)
- [Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers](https://mlsanity.com/paper/2604.12509/) (2026)
- [Learning Dynamic Pick-and-Place for a Legged Manipulator](https://mlsanity.com/paper/2605.15713/) (2026)

## Abstract (arXiv)

Quadruped-based mobile manipulation presents significant challenges in robotics due to the diversity of required skills, the extended task horizon, and partial observability. After presenting a multi-stage pick-and-place task as a succinct yet sufficiently rich setup that captures key desiderata for quadruped-based mobile manipulation, we propose an approach that can train a visuo-motor policy entirely in simulation, and achieve nearly 80% success in the real world. The policy efficiently performs search, approach, grasp, transport, and drop into actions, with emerged behaviors such as re-grasping and task chaining. We conduct an extensive set of real-world experiments with ablation studies highlighting key techniques for efficient training and effective sim-to-real transfer. Additional experiments demonstrate deployment across a variety of indoor and outdoor environments. Demo videos and additional resources are available on the project page: https://horizonrobotics.github.io/gail/SLIM.