Active Embodiment Identification with Reinforcement Learning for Legged Robots
Department of Computer Science, Technical University of Darmstadt（德累斯顿技术大学计算机科学系）；Robotics Institute Germany (RIG)（德国机器人研究所（RIG）；德国人工智能研究中心（DFKI）；hessian.AI）；German Research Center for AI (DFKI)；hessian.AI
We present an active embodiment identification method for legged robots that jointly learns information-seeking behavior and explicit embodiment prediction. Using a history-augmented URMA architecture, the method infers joint-level and global embodiment parameters through interaction with the environment in simulation across different morphologies.
ShanghaiTech University（上海科技大学）；Digital Brain Lab（数字大脑实验室）；Shanghai Jiao Tong University（上海交通大学）；University College London（伦敦大学学院）
Robots are traditionally bounded by a fixed embodiment during their operational lifetime, which limits their ability to adapt to their surroundings. Co-optimizing control and morphology of a robot, however, is often inefficient due to the complex interplay between the controller and morphology. In this paper, we propose a learning-based control method that can inherently take morphology into consideration such that once the control policy is trained in the simulator, it can be easily deployed to robots with different embodiments in the real world. In particular, we present the Embodiment-aware…
To safely deploy legged robots in the real world it is necessary to provide them with the ability to reliably detect unexpected contacts and accurately estimate the corresponding contact force. In this paper, we propose a collision detection and identification pipeline for a quadrupedal manipulator. We first introduce an approach to estimate the collision time span based on band-pass filtering and show that this information is key for obtaining accurate collision force estimates. We then improve the accuracy of the identified force magnitude by compensating for model inaccuracies, unmodeled lo…
NaviTrace: Evaluating Embodied Navigation of Vision-Language Models
Robotic Systems Lab, ETH Zurich（苏黎世联邦理工学院机器人系统实验室）；Intuitive Robots Lab, KIT（卡尔斯鲁厄理工学院直观机器人实验室）；FZI Research Center for Information Technology（弗劳恩霍夫信息技术研究中心）
Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusion
Southern University of Science and Technology, China（南方科技大学）；University of Notre Dame, United States（Notre Dame 大学）；Zhejiang University-University of Illinois Urbana-Champaign Institute, China（浙江大学-伊利诺伊大学厄巴纳-香槟分校联合研究所）；LimX Dynamics, Shenzhen, China（LimX 动力学（深圳））
Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）；National University of Singapore（新加坡国立大学）；Carnegie Mellon University（卡内基梅隆大学）；Morehouse College（莫尔豪斯学院）；Pennsylvania State University（宾夕法尼亚州立大学）；Rancho Research Institute（兰乔研究所）；Royal Veterinary College（皇家兽医学院）；University of Oviedo（奥维耶多大学）
Serially connected robots are promising candidates for performing tasks in confined spaces such as search-and-rescue in large-scale disasters. Such robots are typically limbless, and we hypothesize that the addition of limbs could improve mobility. However, a challenge in designing and controlling such devices lies in the coordination of high-dimensional redundant modules in a way that improves mobility. Here we develop a general framework to control serially connected multi-legged robots. Specifically, we combine two approaches to build a general shape control scheme which can provide baselin…
Fast and Modular Whole-Body Lagrangian Dynamics of Legged Robots with Changing Morphology
Autonomous Space Robotics and Mechatronics Laboratory, Carleton University（自主空间机器人与机电实验室，卡尔顿大学）；Mechanical, Industrial, and Mechatronics Engineering Department, Toronto Metropolitan University（机械、工业与机电工程系，多伦多 Metropolitan 大学）
One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion
Department of Computer Science, Technical University of Darmstadt（德累斯顿技术大学计算机科学系）；Institute of Robotics and Machine Intelligence, Poznan University of Technology（波兹南技术大学机器人与机器智能研究所）；German Research Center for AI (DFKI), Research Department: Systems AI for Robot Learning（德国人工智能研究中心（DFKI）系统AI for机器人学习研究部）；IDEAS NCBR, Warsaw, Poland（华沙波兰IDEAS NCBR）；Centre for Cognitive Science（认知科学中心）
Spring-mass models are well established tools for the analysis and control of legged locomotion. Among the alternatives, spring-loaded inverted pendulum (SLIP) model has shown to be a very accurate descriptor of animal locomotion. Despite its wide use, the SLIP model includes non-integrable stance dynamics that prevent analytical solutions for its equations of motion. Fortunately, there are approximate analytical solutions for different SLIP variants. However, the practicality of such approximations are mostly tested on simulation studies with a few notable exceptions. This thesis extends upon…
Model-based control usually relies on an accurate model, which is often obtained from CAD and actuator models. The more accurate the model the better the control performance. However, in bipedal robots that demonstrate high agility actions, such as running and hopping, the robot hardware will suffer from impacts with the environment and deform in vulnerable parts, which invalidates the predefined model. Thus, it is desired to have an adaptable kinematic structure that takes deformation into consideration. To account for this we propose an approach that models all of the robotic joints as 6-DOF…
Middle East Technical University（中东技术大学）；Robotics and Artificial Intelligence Technologies Application and Research Center（机器人与人工智能技术应用研究中心）
Underactuated legged robots depict highly nonlinear and complex dynamical behaviors that create significant challenges in accurately modeling system dynamics using both first principles and system identification approaches. Hence, it makes a more substantial challenge to design stabilizing controllers. If physical parameters on mathematical models have miscalibrations due to uncertainty in identifying and modeling processes, designed controllers could perform poorly or even result in unstable responses. Moreover, these parameters can certainly change-over-time due to operation and environmenta…
CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting
Peng Cheng Laboratory（鹏城实验室）；Southern University of Science and Technology（南方科技大学）；Innovation Investment Research Institute（创新投资研究院）；Soochow University（苏州大学）
Georgia Institute of Technology（佐治亚理工学院）；University of California, Los Angeles (UCLA)（加利福尼亚大学洛杉矶分校（UCLA））
The light and soft characteristics of Buoyancy Assisted Lightweight Legged Unit (BALLU) robots have a great potential to provide intrinsically safe interactions in environments involving humans, unlike many heavy and rigid robots. However, their unique and sensitive dynamics impose challenges to obtaining robust control policies in the real world. In this work, we demonstrate robust sim-to-real transfer of control policies on the BALLU robots via system identification and our novel residual physics learning method, Environment Mimic (EnvMimic). First, we model the nonlinear dynamics of the act…
AgniNav: Configuration-Driven Cross-Embodiment Local Planning for Robot Navigation
Eastern Institute of Technology, Ningbo, China（东方理工（宁波））；University of Nottingham, Nottingham, UK（诺丁汉大学）；University of Science and Technology of China, Hefei, China（中国科学技术大学）
AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking
Beihang University（北京航空航天大学）；City University of Macau（澳门城市大学）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；Minzu University of China（民族大学）；Center for Data Science in Clinical Medicine, Peking University Third Hospital（北京大学第三医院数据科学临床医学中心）；School of Computer Science, Peking University（北京大学计算机学院）
Adaptive Model-Base Control of Quadrupeds via Online System Identification using Kalman Filter
Robotics Innovation Center, German Research Center for Artificial Intelligence (DFKI GmbH)（机器人创新中心，德国人工智能研究中心（DFKI GmbH））；AG Robotik, University of Bremen（机器人技术研究所，不莱梅大学）；Dynamics Division, Department of Mechanics & Maritime Sciences, Chalmers University of Technology（动力学研究所，机械与海洋科学系，查尔姆斯理工大学）
Adaptive-MHE : A Sampling-Based Adaptive MPC for Legged Loco-Manipulation via Moving Horizon Estimation
University of Calgary（卡尔加里大学）；Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM)（慕尼黑工业大学机器人与机器智能研究所（MIRMI））
Rapid Embodiment Adaptation for Quadrupedal Locomotion
UC San Diego（加州大学圣迭戈分校）；Stanford University（斯坦福大学）；TU Darmstadt（达姆施塔特工业大学）；Sudo AI GmbH（Sudo AI 有限公司）；German Research Center for AI (DFKI)（德国人工智能研究中心）；Robotics Institute Germany（德国机器人研究所）
Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robots
Machine Intelligence and Robotics Lab, Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院智能机器人实验室）；Institute for Intelligent Systems, Esslingen University of Applied Sciences（埃森堡应用科学大学智能系统研究所）；Department of Computer Science, University of Freiburg（弗赖堡大学计算机科学系）
Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
Department of Computer Science, Technical University of Darmstadt（德累斯顿技术大学计算机科学系）；MAB Robtics；German Research Center for AI (DFKI), Research Department: Systems AI for Robot Learning（德国人工智能研究中心（DFKI）系统AI机器人学习研究部）；Robotics Institute Germany (RIG)（德国机器人研究所）
Massachusetts Institute of Technology（麻省理工学院）；NSF AI Institute for Artificial Intelligence and Fundamental Interactions（美国国家科学基金会人工智能与基础交互研究所）
Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances. Our controller is a neural network trained in simulation via reinforcement learning and transferred to the real world. The two key components are (i) an adaptive curriculum on velocity commands and (ii) an online system identification strategy f…
