We introduce MuJoCo MPC (MJPC), an open-source, interactive application and software framework for real-time predictive control, based on MuJoCo physics. MJPC allows the user to easily author and solve complex robotics tasks, and currently supports three shooting-based planners: derivative-based iLQG and Gradient Descent, and a simple derivative-free method we call Predictive Sampling. Predictive Sampling was designed as an elementary baseline, mostly for its pedagogical value, but turned out to be surprisingly competitive with the more established algorithms. This work does not present algorithmic advances, and instead, prioritises performant algorithms, simple code, and accessibility of model-based methods via intuitive and interactive software. MJPC is available at: github.com/deepmind/mujoco_mpc, a video summary can be viewed at: dpmd.ai/mjpc.
Whole-Body Model-Predictive Control of Legged Robots with MuJoCo
Department Aeronautics and Astronautics, Massachusetts Institute of Technology（航空宇航与工程力学系，麻省理工学院）；Google DeepMind（谷歌DeepMind）；Department of Electrical and Computer Engineering, Carnegie Mellon University（电气与计算机工程系，卡内基梅隆大学）；Robotics Institute, Carnegie Mellon University（机器人研究所，卡内基梅隆大学）
Adaptive Legged Locomotion via Online Learning for Model Predictive Control
Department of Aerospace Engineering, University of Michigan（密歇根大学航空航天工程系）；Institute for Robotics and Intelligent Machines, Georgia Institute of Technology（佐治亚理工学院机器人与智能机器研究所）
Unified Multi-Rate Model Predictive Control for a Jet-Powered Humanoid Robot
Artificial and Mechanical Intelligence, Istituto Italiano di Tecnologia（人工智能与机械智能研究所）；School of Computer Science, University of Manchester（曼彻斯特大学计算机科学学院）
Hybrid Data-Driven Predictive Control for Robust and Reactive Exoskeleton Locomotion Synthesis
Department of Computation and Neural Systems, Caltech（计算与神经系统系，加州理工学院）；Department of Mechanical and Civil Engineering, Caltech（机械与土木工程系，加州理工学院）；Wandercraft；Department of Computing and Mathematical Sciences, Caltech（计算与数学科学系，加州理工学院）；Department of Control and Dynamical Systems, Caltech（控制与动态系统系，加州理工学院）
Beijing Research Institute of UBTECH Robotics（优必选机器人北京研究院）；Tsinghua University（清华大学）
The planning of whole-body motion and step time for bipedal locomotion is constructed as a model predictive control (MPC) problem, in which a sequence of optimization problems needs to be solved online. While directly solving these problems is extremely time-consuming, we propose a predictive gait synthesizer to offer immediate solutions. Based on the full-dimensional model, a library of gaits with different speeds and periods is first constructed offline. Then the proposed gait synthesizer generates real-time gaits at 1kHz by synthesizing the gait library based on the online prediction of cen…
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Department of Networked Intelligence, Peng Cheng Laboratory（鹏城实验室网络智能部）；School of Computer Science and Engineering, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）计算机科学与工程学院）
Indian Institute of Science Bangalore（印度科学理工学院）；Manipal Institute of Technology（马尼帕尔理工学院）；National Institute of Technology Karnataka, Surathkal（卡纳塔克邦国立技术学院苏拉特卡尔）
Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works, we propose a hierarchical framework that integrates online learning for the Mb-trajectory optimization with off-policy methods for the Mf-RL. In particular, two loops are proposed, where the Dynamic Mirror Descent based Model Predictive Control (DMD-MPC) is used as the inner loop Mb-RL to obtain an optimal sequence of actions. These actions are in turn used t…
BC-MPPI: A Probabilistic Constraint Layer for Safe Model-Predictive Path-Integral Control
Department of Computer Science, University College London, UK（伦敦大学学院计算机科学系，英国）；Istituto Italiano di Tecnologia (IIT), Genova, Italy（意大利热那亚Istituto Italiano di Tecnologia（IIT））；CNRS, Inria, IRISA, Campus de Beaulieu, Rennes Cedex, France（法国里昂CNRS、Inria、IRISA研究中心）
MR-MPCC: Model Predictive Contouring Control for Robotic Manipulator Tracking under Moving Reference Frames
University of Technology Sydney（悉尼科技大学）；Robotics Institute, University of Technology Sydney（悉尼科技大学机器人研究所）；University of Edinburgh（爱丁堡大学）；School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
A Systematic Review and Taxonomy of Reinforcement Learning-Model Predictive Control Integration for Linear Systems
Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano（电子信息生物工程系（DEIB），米兰理工大学）；Department of Applied Mathematics, Ferdowsi University of Mashhad（应用数学系，法尔德大学）；Department of Mechanical Engineering, Politecnico di Milano（机械工程系，米兰理工大学）；Department of Applied Mathematics, Faculty of Mathematical Sciences, University of Guilan（应用数学系，加林大学）；Department of Robotics and Control Engineering, Shahrood University of Technology（机器人与控制工程系，沙霍德技术大学）
Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works, we propose a hierarchical framework that integrates online learning for the Mb-trajectory optimization with off-policy methods for the Mf-RL. In particular, two loops are proposed, where the Dynamic Mirror Descent based Model Predictive Control (DMD-MPC) is used as the inner loop to obtain an optimal sequence of actions. These actions are in turn used to sign…
Do My Samples Help? Compute Budget Allocation for Real-World Sampling-Based MPC in Contact-Rich Manipulation
TU Darmstadt（达姆施塔特工业大学）；German Research Center for AI (DFKI)（德国人工智能研究中心）；Robotics Institute Germany (RIG)（德国机器人研究所）；School of Computing, DePaul University（德保罗大学计算学院）
Motion planning for autonomous vehicles requires spatio-temporal motion plans (i.e. state trajectories) to account for dynamic obstacles. This requires a trajectory tracking control process which faithfully tracks planned trajectories. In this paper, a control scheme is presented which first optimizes a planned trajectory and then tracks the optimized trajectory using a feedback-feedforward controller. The feedforward element is calculated in a model predictive manner with a cost function focusing on driving performance. Stability of the error dynamic is then guaranteed by the design of the fe…
University of Notre Dame（圣母大学）；Robotics at Google（谷歌机器人部门）
Specialized motions such as jumping are often achieved on quadruped robots by solving a trajectory optimization problem once and executing the trajectory using a tracking controller. This approach is in parallel with Model Predictive Control (MPC) strategies that commonly control regular gaits via online re-planning. In this work, we present a nonlinear MPC (NMPC) technique that unlocks on-the-fly re-planning of specialized motion skills and regular locomotion within a unified framework. The NMPC reasons about a hybrid kinodynamic model, and is solved using a variant of a constrained Different…
University of Washington（华盛顿大学）；Roboti LLC（Roboti有限责任公司）
We introduce Lyceum, a high-performance computational ecosystem for robot learning. Lyceum is built on top of the Julia programming language and the MuJoCo physics simulator, combining the ease-of-use of a high-level programming language with the performance of native C. In addition, Lyceum has a straightforward API to support parallel computation across multiple cores and machines. Overall, depending on the complexity of the environment, Lyceum is 5-30x faster compared to other popular abstractions like OpenAI's Gym and DeepMind's dm-control. This substantially reduces training time for vario…
Sampling-Based Model Predictive Control for Dexterous Manipulation on a Biomimetic Tendon-Driven Hand
Soft Robotics Lab, Department of Mechanical and Process Engineering, ETH Zurich（苏黎世联邦理工学院机械与过程工程系软机器人实验室）；School of Computer Science, University of Leeds（利兹大学计算机科学学院）
