Warm-Starting Optimization-Based Motion Planning for Robotic Manipulators via Point Cloud-Conditioned Flow Matching
J. Mike Walker ’66 Department of Mechanical Engineering, Texas A&M University（J. Mike Walker ’66 机械工程系，德克萨斯A&M大学）；Zachry Department of Civil and Environmental Engineering, Texas A&M University（Zachry 市政与环境工程系，德克萨斯A&M大学）
Rapid robot motion generation is critical in Human-Robot Collaboration (HRC) systems, as robots need to respond to dynamic environments in real time by continuously observing their surroundings and replanning their motions to ensure both safe interactions and efficient task execution. Current sampling-based motion planners face challenges in scaling to high-dimensional configuration spaces and often require post-processing to interpolate and smooth the generated paths, resulting in time inefficiency in complex environments. Optimization-based planners, on the other hand, can incorporate multiple constraints and generate smooth trajectories directly, making them potentially more time-efficient. However, optimization-based planners are sensitive to initialization and may get stuck in local minima. In this work, we present a novel learning-based method that utilizes a Flow Matching model conditioned on a single-view point cloud to learn near-optimal solutions for optimization initialization. Our method does not require prior knowledge of the environment, such as obstacle locations and geometries, and can generate feasible trajectories directly from single-view depth camera input. Simulation studies on a UR5e robotic manipulator in cluttered workspaces demonstrate that the proposed generative initializer achieves a high success rate on its own, significantly improves the success rate of trajectory optimization compared with traditional and learning-based benchmark initializers, requires fewer optimization iterations, and exhibits strong generalization to unseen environments.
AERMANI-Diffusion: Regime-Conditioned Diffusion for Dynamics Learning in Aerial Manipulators
Robotics Research Center, International Institute of Information Technology Hyderabad（国际信息科技学院海得拉巴分校机器人研究中心）；Department of Computer Science, The University of Manchaster（曼彻斯特大学计算机科学系）
XFlowMP: Task-Conditioned Motion Fields for Generative Robot Planning with Schrodinger Bridges
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（莫扎德·本·扎耶德人工智能大学）；Automation & Control Institute (ACIN), TU Wien（自动化与控制研究所）；Austrian Institute of Technology (AIT) GmbH（奥地利技术研究所）
Warm-Starting Collision-Free Model Predictive Control With Object-Centric Diffusion
LAAS-CNRS, Université de Toulouse, CNRS（拉夫堡-安德鲁·马歇尔研究中心，图卢兹大学，法国国家科学研究中心）；Artificial and Natural Intelligence Toulouse Institute（图卢兹人工智能与自然智能研究所）；Continental（大陆集团）；Ecole Centrale de Lyon, LIRIS（里昂高等工程师学院，LIRIS研究所）；CIIRC, Czech Technical University in Prague（布拉格捷克技术大学智能信息研究中心）
Inverse Kinematics with Forward Dynamics Solvers for Sampled Motion Tracking
FZI Research Center for Information Technology（FZI信息技术研究中心）；IAR Institute for Anthropomatics and Robotics（IAR拟人系统与机器人研究所）；KIT Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
IIIT Hyderabad（国际信息技术研究所海得拉巴分校）；University of Tartu（塔尔图大学）
Joint space trajectory optimization under end-effector task constraints leads to a challenging non-convex problem. Thus, a real-time adaptation of prior computed trajectories to perturbation in task constraints often becomes intractable. Existing works use the so-called warm-starting of trajectory optimization to improve computational performance. We present a fundamentally different approach that relies on deriving analytical gradients of the optimal solution with respect to the task constraint parameters. This gradient map characterizes the direction in which the prior computed joint traject…
Whole-body Motion Control of an Omnidirectional Wheel-Legged Mobile Manipulator via Contact-Aware Dynamic Optimization
State Key Laboratory of Intelligent Manufacturing Equipment and Technology, School of Mechanical Science and Engineering, Huazhong University of Science and Technology（智能制造装备与技术国家重点实验室，机械科学与工程学院，华中科技大学）
AeroPlace-Flow: Language-Grounded Object Placement for Aerial Manipulators via Visual Foresight and Object Flow
Robotics Research Center, IIIT Hyderabad, India（印度IIIT海得拉巴机器人研究中心）；Department of Computer Science, University of Manchester, UK（英国曼彻斯特大学计算机科学系）；Newcastle University, UK（英国新castle大学）
D-SafeMPC: Diffusion-Driven Safe Model Predictive Control with Discrete-Time Control Barrier Functions
Paderborn University（帕德博恩大学）；Illinois Institute of Technology（伊利诺伊理工学院）；California Institute of Technology（加州理工学院）；Technical University of Munich（慕尼黑工业大学）
Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics
University of Applied Science and Arts of Southern Switzerland, Department of Innovative Technologies, IDSIA-SUPSI（瑞士南方应用科学与艺术大学创新技术系，IDSIA-SUPSI）；Università della Svizzera Italiana, Faculty of Informatics（瑞士意大利大学信息学院）；Politecnico di Milano, Mechanical Department（米兰理工学院机械系）
This paper presents a framework that allows online dynamic-stability-constrained optimal trajectory planning of a mobile manipulator robot working on rough terrain. First, the kinematics model of a mobile manipulator robot, and the Zero Moment Point (ZMP) stability measure are presented as theoretical background. Then, a sampling-based quasi-static planning algorithm modified for stability guarantee and traction optimization in continuous dynamic motion is presented along with a mathematical proof. The robot's quasi-static path is then used as an initial guess to warm-start a nonlinear optimal…
Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation
Technical University of Munich（慕尼黑技术大学）；Corporate Research, Robert Bosch GmbH（罗伯特·博世集团企业研究部）；University of California Berkeley（加州大学伯克利分校）；Microsoft（微软）；Google DeepMind（谷歌DeepMind）；Carnegie Mellon University（卡内基梅隆大学）；Imperial College London（伦敦帝国理工学院）；Princeton University（普林斯顿大学）；University of Southern California（南加州大学）；Sun Yat-sen University（中山大学）；University of Michigan（密歇根大学）；Institute for Artificial Intelligence, University of Stuttgart（斯图加特大学人工智能研究所）；The State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）
A Cross-Environment and Cross-Embodiment Path Planning Framework via a Conditional Diffusion Model
Computer Engineering Department, University of Victoria（维多利亚大学计算机工程系）；Mila-Quebec AI Institute（魁北克AI研究院）；Mechanical Engineering Department, University of Victoria（维多利亚大学机械工程系）
Idiap Research Institute（伊迪亚普研究所）；Dalle Molle Institute for Artificial Intelligence (IDSIA)（达尔·莫勒人工智能研究所（IDSIA））；USI-SUPSI（提契诺大学-瑞士南部应用科学与艺术大学）
This paper addresses the problem of efficiently achieving visual predictive control tasks. To this end, a memory of motion, containing a set of trajectories built off-line, is used for leveraging precomputation and dealing with difficult visual tasks. Standard regression techniques, such as k-nearest neighbors and Gaussian process regression, are used to query the memory and provide on-line a warm-start and a way point to the control optimization process. The proposed technique allows the control scheme to achieve high performance and, at the same time, keep the computational time limited. Sim…
Institute for Robotics & Intelligent Machines, Georgia Institute of Technology（佐治亚理工学院机器人与智能机器研究所）
We present a unified probabilistic framework for simultaneous trajectory estimation and planning (STEAP). Estimation and planning problems are usually considered separately, however, within our framework we show that solving them simultaneously can be more accurate and efficient. The key idea is to compute the full continuous-time trajectory from start to goal at each time-step. While the robot traverses the trajectory, the history portion of the trajectory signifies the solution to the estimation problem, and the future portion of the trajectory signifies a solution to the planning problem. B…
Learning to Move in Rhythm: Task-Conditioned Motion Policies with Orbital Stability Guarantees
CSAIL, Massachusetts Institute of Technology（CSAIL，麻省理工学院）；Cognitive Robotics, Delft University of Technology（认知机器人学，代尔夫特理工大学）；ELLIS Institute Tübingen（图宾根ELLIS研究所）；Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所）；Mechanical and Aerospace Engineering, Case Western Reserve University（机械与航空航天工程，凯斯西储大学）；Division of Robotics, Perception and Learning, KTH（机器人、感知与学习部门，皇家理工学院）；CREATE Lab, EPFL（CREATE实验室，瑞士联邦理工学院）；Embodied AI AG, Lausanne, Switzerland（具身人工智能有限公司，瑞士洛桑）
Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics
Zhejiang University（浙江大学）；Beijing Zhongguancun Academy（北京中关村学院）；University of Science and Technology of China（中国科学技术大学）；Eastern Institute of Technology（东方理工学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
IRIS: Learning-Driven Task-Specific Cinema Robot Arm for Visuomotor Motion Control
Aerospace Eng. Department New York University（航空航天工程系 新 York 大学）；MIE Department University of Toronto（机械工程系 蒂姆斯大学）；ECE Department University of Toronto（电子与计算机工程系 蒂姆斯大学）
