Enabling robots to learn novel tasks in a data-efficient manner is a long-standing challenge. Common strategies involve carefully leveraging prior experiences, especially transition data collected on related tasks. Although much progress has been made for general pick-and-place manipulation, far fewer studies have investigated contact-rich assembly tasks, where precise control is essential. We introduce SRSA (Skill Retrieval and Skill Adaptation), a novel framework designed to address this problem by utilizing a pre-existing skill library containing policies for diverse assembly tasks. The challenge lies in identifying which skill from the library is most relevant for fine-tuning on a new task. Our key hypothesis is that skills showing higher zero-shot success rates on a new task are better suited for rapid and effective fine-tuning on that task. To this end, we propose to predict the transfer success for all skills in the skill library on a novel task, and then use this prediction to guide the skill retrieval process. We establish a framework that jointly captures features of object geometry, physical dynamics, and expert actions to represent the tasks, allowing us to efficiently learn the transfer success predictor. Extensive experiments demonstrate that SRSA significantly outperforms the leading baseline. When retrieving and fine-tuning skills on unseen tasks, SRSA achieves a 19% relative improvement in success rate, exhibits 2.6x lower standard deviation across random seeds, and requires 2.4x fewer transition samples to reach a satisfactory success rate, compared to the baseline. Furthermore, policies trained with SRSA in simulation achieve a 90% mean success rate when deployed in the real world. Please visit our project webpage https://srsa2024.github.io/.
Autonomous Integration and Improvement of Robotic Assembly using Skill Graph Representations
Department of Electrical and Computer Engineering, Carnegie Mellon University(卡内基梅隆大学电气与计算机工程系);Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)
Learning-Based Strategy for Composite Robot Assembly Skill Adaptation
Chair of Machine Tools and Control System, RPTU University Kaiserslautern-Landau(机床与控制系统系,凯撒斯劳滕-兰道大学);Innovative Factory Systems, German Institute of Artificial Intelligence(创新工厂系统,德国人工智能研究中心)
Contact Skill Imitation Learning for Robot-Independent Assembly Programming
FZI Research Center for Information Technology(FZI信息科技研究中心);IAR Institute for Anthropomatics and Robotics, HIS Humanoids and Intelligence Systems Lab, KIT Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院(KIT)IAR人形机器人与机器人学研究所、HIS人形与智能系统实验室)
Cognitive Manipulation: Semi-supervised Visual Representation and Classroom-to-real Reinforcement Learning for Assembly in Semi-structured Environments
South China University of Technology(华南理工大学);Nanyang Technological University(南洋理工大学)
SharedAssembly: A Data Collection Approach via Shared Tele-Assembly
Technical University of Munich(慕尼黑工业大学);Munich Institute of Robotics and Machine Intelligence(慕尼黑机器人与机器智能研究所);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
TacDiffusion: Force-domain Diffusion Policy for Precise Tactile Manipulation
Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich(慕尼黑工业大学慕尼黑机器人与机器智能研究所(MIRMI));Centre for Tactile Internet with Human-in-the-Loop (CeTI)(以人为中心的触觉互联网中心(CeTI));Mohamed Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulation
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);School of Electrical and Electronic Engineering, Nanyang Technological University(南洋理工大学电气与电子工程学院)