Trajectory optimization for motion planning requires good initial guesses to obtain good performance. In our proposed approach, we build a memory of motion based on a database of robot paths to provide good initial guesses. The memory of motion relies on function approximators and dimensionality reduction techniques to learn the mapping between the tasks and the robot paths. Three function approximators are compared: $k$-Nearest Neighbor, Gaussian Process Regression, and Bayesian Gaussian Mixture Regression. In addition, we show that the memory can be used as a metric to choose between several possible goals, and using an ensemble method to combine different function approximators results in a significantly improved warm-starting performance. We demonstrate the proposed approach with motion planning examples on the dual-arm robot PR2 and the humanoid robot Atlas.
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）
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）
Optimization-Based Trajectory Planning for Tractor-Trailer Vehicles on Curvy Roads: A Progressively Increasing Sampling Number Method
Department of Automation, Institute of Medical Robotics, Shanghai Jiao Tong University（自动化系、医疗机器人研究所、上海交通大学）；Key Laboratory of System Control and Information Processing, Ministry of Education of China（系统控制与信息处理重点实验室、中华人民共和国教育部）；Shanghai Engineering Research Center of Intelligent Control and Management, Shanghai（智能控制与管理上海工程研究中心）
Accelerating trajectory optimization with Sobolev-trained diffusion policies
Inria - Département d’Informatique de l’École normale supérieure, PSL Research University（法国国家科学研究中心-巴黎高等师范学院计算机系，PSL研究大学）；Courant Institute, New York University（纽约大学Courant研究所）
Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions
Institute of Engineering and Computational Mechanics, University of Stuttgart, 70569 Stuttgart, Germany（工程与计算力学研究所，斯图加特大学，德国斯图加特70569）；Mechanical Engineering, LUT University, 53850 Lappeenranta, Finland（机械工程，卢蒂大学，芬兰拉佩恩兰塔53850）
Accelerating Hybrid Model Predictive Control using Warm-Started Generalized Benders Decomposition
Independent Researcher（独立研究者）；Department of Mechanical Engineering, University of California, Los Angeles（加州大学洛杉矶分校机械工程系）；School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院机械工程学院）
PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
Purdue University（普渡大学）；Beijing University of Chemical Technology（北京化工大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Sungkyunkwan University（成均馆大学）；Indiana University Bloomington（印第安纳大学布卢明顿分校）
