Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Rattachement africain : kr, ca, de. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using Supervised Fine-Tuning (SFT). However, SFT datasets are often heuristically constructed and not explicitly optimized for improving robot control. Furthermore, SFT often leads to issues such as catastrophic forgetting and reduced generalization performance. To address these limitations, we introduce Robot-R1, a novel framework that leverages reinforcement learning to enhance embodied reasoning specifically for robot control. Robot-R1 learns to predict the next keypoint state required for task completion, conditioned on the current scene image and environment metadata derived from expert demonstrations. Inspired by the DeepSeek-R1 learning approach, Robot-R1 samples reasoning-based responses and reinforces those that lead to more accurate predictions. To rigorously evaluate Robot-R1, we also introduce a new benchmark that demands the diverse embodied reasoning capabilities for the task. Our experiments show that models trained with Robot-R1 outperform SFT methods on embodied reasoning tasks. Despite having only 7B parameters, Robot-R1 even surpasses GPT-4o on reasoning tasks related to low-level action control, such as spatial and movement reasoning.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
- Date Crossref
- 01/01/2025
- Éditeur
- Neural Information Processing Systems Foundation, Inc. (NeurIPS)
- Type
- proceedings-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Korea Advanced Institute of Science and Technology pays non établi dans la noticeUniversité ou école supérieure
-
Kootenay Association for Science & Technology pays non établi dans la noticeOrganisation à but non lucratif
-
Yonsei University pays non établi dans la noticeUniversité ou école supérieure
-
Amazon (Germany) pays non établi dans la noticeEntreprise
-
KAIST pays non établi dans la noticeInstitution
-
Korea Advanced Institute of Science & pays non établi dans la noticeStructure de recherche
Korea Advanced Institute of Science and Technology, Kootenay Association for Science & Technology et Yonsei University, avec 3 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.