Recent large language models (LLMs) have demonstrated promising capabilities in modeling real-world knowledge and enhancing knowledge-based generation tasks. In this paper, we further explore the potential of using LLMs to aid in the design of soft modular robots, taking into account both user instructions and physical laws, to reduce the reliance on extensive trial-and-error experiments typically needed to achieve robot designs that meet specific structural or task requirements. Specifically, we formulate the robot design process as a sequence generation task and find that LLMs are able to capture key requirements expressed in natural language and reflect them in the construction sequences of robots. To simplify, rather than conducting real-world experiments to assess design quality, we utilize a simulation tool to provide feedback to the generative model, allowing for iterative improvements without requiring extensive human annotations. Furthermore, we introduce five evaluation metrics to assess the quality of robot designs from multiple angles including task completion and adherence to instructions, supporting an automatic evaluation process. Our model performs well in evaluations for designing soft modular robots with uni- and bi-directional locomotion and stair-descending capabilities, highlighting the potential of using natural language and LLMs for robot design. However, we also observe certain limitations that suggest areas for further improvement.
Development of a Modular and Submersible Soft Robotic Arm and Corresponding Learned Kinematics Models
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Beckman Institute for Advanced Science and Technology(贝克曼高等科学技术研究所);University of Michigan(密歇根大学)
A Continual Learning Framework for Adaptive Control of Modular Soft Robots
The BioRobotics Institute, Scuola Superiore Sant’Anna(生物机器人研究所,圣安娜高等学校);Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna(机器人与人工智能卓越系,圣安娜高等学校);Department of Mechanical Engineering, National University of Singapore(新加坡国立大学机械工程系);ETIS Lab UMR8051 CY Cergy Paris University - ENSEA - CNRS(ETIS实验室UMR8051,CY赛尔吉 - 巴黎大学 - ENSEA - 法国国家科学研究中心)
Modularity for lunar exploration: European Moon Rover System Pre-Phase A Design and Field Test Campaign Results
GMV Aerospace and Defence SAU(GMV航空航天与防务SAU);GMV NSL Ltd(GMV NSL有限公司);AVS Added Value Solutions(AVV增值解决方案公司);OHB System AG(OHB系统股份公司);Hellenic Technology of Robotics(希腊机器人技术公司);German Aerospace Center (DLR)(德国航空航天中心);ESTEC, ESA(欧洲空间局欧洲空间研究和技术中心)
Learning Soft Robotic Dynamics with Active Exploration
Soft Robotics Lab, D-MAVT, ETH Zurich(软机器人实验室,ETH Zurich);Learning & Adaptive Systems Group, D-INFK, ETH Zurich(学习与自适应系统组,ETH Zurich);ETH AI Center, ETH Zurich(ETH人工智能中心,ETH Zurich)
A Modular Pneumatic Soft Gripper Design for Aerial Grasping and Landing
The Hong Kong Polytechnic University(香港理工大学);Hong Kong Center for Construction Robotics(香港建造机器人中心);Research Centre of Unmanned Autonomous Systems(无人自主系统研究中心);Department of Aeronautical and Aviation Engineering(航空及民航工程系);Department of Mechanical Engineering(机械工程系)
A Novel Modular Cable-Driven Soft Robotic Arm with Multi-Segment Reconfigurability
Department of Agricultural and Biological Engineering, Mississippi State University(农业与生物工程系,密苏里州立大学);Department of Electrical and Computer Engineering, Michigan State University(电气与计算机工程系,密苏里州立大学);Texas A&M AgriLife Research and Extension Center in Dallas, Texas A&M University(德克萨斯A&M大学达拉斯分校农业与生命科学研究中心)
The Soft Compiler: A Web-Based Tool for the Design of Modular Pneumatic Circuits for Soft Robots
University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Edinburgh(爱丁堡大学);Harvard University(哈佛大学);Worcester Polytechnic Institute(伍斯特理工学院);Eastern Virginia Medical School(东弗吉尼亚医学院)
Learning Object-conditioned Exploration using Distributed Soft Actor Critic
Robotics at Google(谷歌机器人部门)
对象导航被定义为在复杂的、未探索的环境中导航到给定标签的对象。在其一般形式中,这个问题给机器人技术带来了几个挑战:在搜索对象和低级控制时对未知环境进行语义探索。在这项工作中,我们研究了对象引导的探索和低级别的控制,并提出了一个端到端的训练导航策略,实现了0.68的成功率和0.58的SPL对看不见的,视觉上复杂的扫描真实的家园。我们提出了一种高度可扩展的非策略强化学习算法的实现,分布式Soft Actor Critic,它允许系统在8个GPU上在24小时内利用98M经验步骤。我们的系统学习控制差分驱动移动基地在模拟中,从机器人平台上常用的高维观测堆栈。学习的策略能够从现实环境中的纯经验中学习到对象引导的探索性行为和低级控制。
Whole-Body Proprioceptive Morphing: A Modular Soft Gripper for Robust Cross-Scale Grasping
Mechanical Engineering Department at the University of Michigan-Ann Arbor(密歇根大学安娜堡分校机械工程系);Robotics Department at the University of Michigan-Ann Arbor(密歇根大学安娜堡分校机器人学系)
Design and Control of Modular Soft-Rigid Hybrid Manipulators with Self-Contact
Computer Science and Artificial Intelligence Laboratory, MIT(麻省理工学院计算机科学与人工智能实验室);Delft University of Technology(代尔夫特理工大学);German Aerospace Center (DLR)(德国航空航天中心)
A Versatile Neural Network Configuration Space Planning and Control Strategy for Modular Soft Robot Arms
Biorobotics Institute and the Department of Excellence in Robotics and AI(生物机器人研究所和机器人与人工智能卓越部门);Scuola Superiore Sant’Anna(圣安娜高等学院);CREATE Lab(CREATE实验室);EPFL(瑞士联邦理工学院)
Object Classification Utilizing Neuromorphic Proprioceptive Signals in Active Exploration: Validated on a Soft Anthropomorphic Hand
Institute for Cognitive Systems, Technical University of Munich(认知系统研究所,慕尼黑技术大学);Department of Biomedical Engineering, Johns Hopkins University(生物医学工程系,约翰霍普金斯大学)
MOSAIC: Modular Scalable Autonomy for Intelligent Coordination of Heterogeneous Robotic Teams
FZI Forschungszentrum für Informatik, Karlsruhe, Germany(弗赖堡信息研究中心,卡尔斯鲁厄,德国);Robotic Systems Lab (RSL), ETH Zürich, Zürich, Switzerland(机器人系统实验室(RSL),苏黎世联邦理工学院,苏黎世,瑞士);Machine Intelligence and Robotics Lab (MaiRo), Karlsruhe Institute for Technology (KIT), Karlsruhe, Germany(机器智能与机器人实验室(MaiRo),卡尔斯鲁厄技术学院(KIT),卡尔斯鲁厄,德国);European Space Agency (ESA), Noordwijk, Netherlands(欧洲航天局(ESA),诺德威克,荷兰)