Collaborative Loco-Manipulation for Pick-and-Place Tasks with Dynamic Reward Curriculum
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916952260214784 |
|---|---|
| author | An, Tianxu De Vincenti, Flavio Ma, Yuntao Hutter, Marco Coros, Stelian |
| author_facet | An, Tianxu De Vincenti, Flavio Ma, Yuntao Hutter, Marco Coros, Stelian |
| contents | We present a hierarchical RL pipeline for training one-armed legged robots to perform pick-and-place (P&P) tasks end-to-end -- from approaching the payload to releasing it at a target area -- in both single-robot and cooperative dual-robot settings. We introduce a novel dynamic reward curriculum that enables a single policy to efficiently learn long-horizon P&P operations by progressively guiding the agents through payload-centered sub-objectives. Compared to state-of-the-art approaches for long-horizon RL tasks, our method improves training efficiency by 55% and reduces execution time by 18.6% in simulation experiments. In the dual-robot case, we show that our policy enables each robot to attend to different components of its observation space at distinct task stages, promoting effective coordination via autonomous attention shifts. We validate our method through real-world experiments using ANYmal D platforms in both single- and dual-robot scenarios. To our knowledge, this is the first RL pipeline that tackles the full scope of collaborative P&P with two legged manipulators. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13239 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Collaborative Loco-Manipulation for Pick-and-Place Tasks with Dynamic Reward Curriculum An, Tianxu De Vincenti, Flavio Ma, Yuntao Hutter, Marco Coros, Stelian Robotics We present a hierarchical RL pipeline for training one-armed legged robots to perform pick-and-place (P&P) tasks end-to-end -- from approaching the payload to releasing it at a target area -- in both single-robot and cooperative dual-robot settings. We introduce a novel dynamic reward curriculum that enables a single policy to efficiently learn long-horizon P&P operations by progressively guiding the agents through payload-centered sub-objectives. Compared to state-of-the-art approaches for long-horizon RL tasks, our method improves training efficiency by 55% and reduces execution time by 18.6% in simulation experiments. In the dual-robot case, we show that our policy enables each robot to attend to different components of its observation space at distinct task stages, promoting effective coordination via autonomous attention shifts. We validate our method through real-world experiments using ANYmal D platforms in both single- and dual-robot scenarios. To our knowledge, this is the first RL pipeline that tackles the full scope of collaborative P&P with two legged manipulators. |
| title | Collaborative Loco-Manipulation for Pick-and-Place Tasks with Dynamic Reward Curriculum |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.13239 |