analiza aiqbench
This research introduces Play2Perfect, an RL framework that leverages task-agnostic "play" pretraining to equip multi-fingered robots with reusable manipulation priors for precise assembly. By systematically analyzing factors like object diversity and goal precision, the method achieves significant sample efficiency and successful zero-shot sim-to-real transfer on complex tasks such as tight insertions and screwing. The work advances the field by demonstrating that foundational dexterity learned through play can effectively bridge the gap to high-precision industrial applications without relying on specialized hardware fixtures.
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
arXiv:2606.26428v3 Announce Type: replace Abstract: Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration with reinforcement learning (RL) intractable. Consequently, prior work has made progress by structuring the problem with specialized grippers, tool attachments, and environment fixtures. In this work, we argue that before a robot can perfect precise assembly, it must first learn to play. We further ask the question: what factors in the process of learning to play matter for precise assembly? We propose Play2Perfect, an RL framework for task-agnostic pretraining through play on diverse objects and goals, which is then perfected on precise assembly. The goal of play is to acquire reusable manipulation priors, such as grasping, in-hand reorientation and pose reaching. Finetuning then adapts this general prior to assembly, focusing exploration on the final contact-rich, high-precision interactions needed for success. We systematically study key design choices in play pretraining, including object diversity, training objective, trajectory diversity, and goal precision. We show that our prior is 33x more sample-efficient than RL training from scratch, even when provided with dense, multi-stage rewards. We demonstrate zero-shot sim-to-real transfer, achieving 60% success on tight insertions with only 0.5 mm contact clearance, and over 50% success on long-horizon multi-part assembly and screwing.
Title:Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
Abstract:Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach. These tasks are contact-rich, making data collection for imitation learning difficult, and sparse-reward, making direct exploration with reinforcement learning (RL) intractable. Consequently, prior work has made progress by structuring the problem with specialized grippers, tool attachments, and environment fixtures. In this work, we argue that before a robot can perfect precise assembly, it must first learn to play. We further ask the question: what factors in the process of learning to play matter for precise assembly? We propose Play2Perfect, an RL framework for task-agnostic pretraining through play on diverse objects and goals, which is then perfected on precise assembly. The goal of play is to acquire reusable manipulation priors, such as grasping, in-hand reorientation and pose reaching. Finetuning then adapts this general prior to assembly, focusing exploration on the final contact-rich, high-precision interactions needed for success. We systematically study key design choices in play pretraining, including object diversity, training objective, trajectory diversity, and goal precision. We show that our prior is 33x more sample-efficient than RL training from scratch, even when provided with dense, multi-stage rewards. We demonstrate zero-shot sim-to-real transfer, achieving 60% success on tight insertions with only 0.5 mm contact clearance, and over 50% success on long-horizon multi-part assembly and screwing.
25 pages, 19 figures, 4 tables. Project page: this https URL
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2606.26428 [cs.RO]
(or arXiv:2606.26428v3 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.26428 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 340 cuvinte
Subiecte conexe
Building a Foundation Stack for General-Purpose Robots
IEEE Spectrum · 13 iul. 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · 13 oct. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
World Models and Yann LeCun’s Bet Against Large Language Models
Quantum Zeitgeist · 17 iul. 2026