Versatile and Generalizable Manipulation via Goal-Conditioned Reinforcement Learning with Grounded Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Huiyi, Shahriar, Fahim, Azimi, Alireza, Vasan, Gautham, Mahmood, Rupam, Bellinger, Colin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911055756656640
author Wang, Huiyi
Shahriar, Fahim
Azimi, Alireza
Vasan, Gautham
Mahmood, Rupam
Bellinger, Colin
author_facet Wang, Huiyi
Shahriar, Fahim
Azimi, Alireza
Vasan, Gautham
Mahmood, Rupam
Bellinger, Colin
contents General-purpose robotic manipulation, including reach and grasp, is essential for deployment into households and workspaces involving diverse and evolving tasks. Recent advances propose using large pre-trained models, such as Large Language Models and object detectors, to boost robotic perception in reinforcement learning. These models, trained on large datasets via self-supervised learning, can process text prompts and identify diverse objects in scenes, an invaluable skill in RL where learning object interaction is resource-intensive. This study demonstrates how to integrate such models into Goal-Conditioned Reinforcement Learning to enable general and versatile robotic reach and grasp capabilities. We use a pre-trained object detection model to enable the agent to identify the object from a text prompt and generate a mask for goal conditioning. Mask-based goal conditioning provides object-agnostic cues, improving feature sharing and generalization. The effectiveness of the proposed framework is demonstrated in a simulated reach-and-grasp task, where the mask-based goal conditioning consistently maintains a $\sim$90\% success rate in grasping both in and out-of-distribution objects, while also ensuring faster convergence to higher returns.
format Preprint
id arxiv_https___arxiv_org_abs_2507_10814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Versatile and Generalizable Manipulation via Goal-Conditioned Reinforcement Learning with Grounded Object Detection
Wang, Huiyi
Shahriar, Fahim
Azimi, Alireza
Vasan, Gautham
Mahmood, Rupam
Bellinger, Colin
Robotics
General-purpose robotic manipulation, including reach and grasp, is essential for deployment into households and workspaces involving diverse and evolving tasks. Recent advances propose using large pre-trained models, such as Large Language Models and object detectors, to boost robotic perception in reinforcement learning. These models, trained on large datasets via self-supervised learning, can process text prompts and identify diverse objects in scenes, an invaluable skill in RL where learning object interaction is resource-intensive. This study demonstrates how to integrate such models into Goal-Conditioned Reinforcement Learning to enable general and versatile robotic reach and grasp capabilities. We use a pre-trained object detection model to enable the agent to identify the object from a text prompt and generate a mask for goal conditioning. Mask-based goal conditioning provides object-agnostic cues, improving feature sharing and generalization. The effectiveness of the proposed framework is demonstrated in a simulated reach-and-grasp task, where the mask-based goal conditioning consistently maintains a $\sim$90\% success rate in grasping both in and out-of-distribution objects, while also ensuring faster convergence to higher returns.
title Versatile and Generalizable Manipulation via Goal-Conditioned Reinforcement Learning with Grounded Object Detection
topic Robotics
url https://arxiv.org/abs/2507.10814