Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation
Beihang University(北京航空航天大学);Peking University(北京大学);The Chinese University of Hong Kong(香港中文大学);PKU-Psibot Lab(北大-智源机器人实验室);Zhongguancun Laboratory(中关村实验室);Hefei Comprehensive National Science Center(合肥综合性国家科学中心)
Jianing Guo, Fangzheng Chen, Zihao Mao, Wong Lik Hang Kenny, Zhenhong Wu, Yu Li, Yishuai Cai, Yuanpei Chen, Yikun Ban, Kai Chen, Qi Dou, Xianglong Liu, Huijie Z… 展开作者
Jianing Guo, Fangzheng Chen, Zihao Mao, Wong Lik Hang Kenny, Zhenhong Wu, Yu Li, Yishuai Cai, Yuanpei Chen, Yikun Ban, Kai Chen, Qi Dou, Xianglong Liu, Huijie Zhao, Simin Li, Yaodong Yang
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy. However, existing methods rely on discretized action chunks, making them brittle to demonstrations collected at heterogeneous control frequencies and prone to temporally inconsistent actions that degrade control stability. In this paper, we propose Frequency-Aware Flow Matching (FAFM), which outputs continuous, temporally consistent actions. To handle heterogeneous frequency input, we transform discrete action sequences into the frequency domain with the discrete cosine transform (DCT), perform flow matching over the resulting coefficients, and reconstruct continuous actions via cosine basis expansion. To generate temporally consistent actions, we regularize the first-order temporal derivative to promote smooth actions. This corresponds to a Sobolev-type constraint that suppresses high-frequency errors and discourages abrupt action changes. Our FAFM is simple, introduces no additional network parameters and applies to standalone flow-matching policies and vision-language action models. Across synthetic toy benchmark, obstacle avoidance, LapGym, and LIBERO, FAFM improves success rates, multimodal expressivity, motion smoothness, convergence speed, robustness to mechanical bias and mixed-frequency input. These gains are consistent when deployed on a real-world Franka robot. Code available at https://github.com/gakakulicc/FAFM.
Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation
Dept. Computing, Imperial College London(帝国理工学院伦敦分校计算机系);Dept. Computing, Manchester Metropolitan University(曼彻斯特 Metropolitan 大学计算机系);CVSSP, University of Surrey(萨里大学CVSSP研究中心);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Institute for Transport Studies, the University of Leeds(利兹大学交通研究所)
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China(清华大学交叉信息研究院);Department of Computer Science, Princeton University, New Jersey, US(普林斯顿大学计算机科学系);Galaxea Inc., Beijing, China(Galaxea公司)
Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences(中国科学院重庆绿色智能技术研究院);Chongqing School, University of Chinese Academy of Sciences(中国科学院大学重庆学院)
SurgLAT: Surgical Latent Attention Tracking for Depth-Aware Robotic Laparoscope Control
The Chinese University of Hong Kong(香港中文大学);Shenzhen Loop Area Institute(深圳河套学院);Shenzhen University(深圳大学);Southern University of Science and Technology(南方科技大学)
Safety Aware Task Planning via Large Language Models in Robotics
University of Minnesota – Twin Cities(明尼苏达大学双城分校);Institute for Robotics and Intelligent Machines (IRIM), Georgia Institute of Technology(佐治亚理工学院机器人与智能机器研究所);Pontificia Universidad Católica de Chile(智利天主教大学)
The Induced Matching Distance: A Novel Topological Metric with Applications in Robotics
Universidad de Sevilla(塞维利亚大学);Inserm(法国国家健康与医学研究院);INRAE(法国国家农业、食品与环境研究院);Université Paris Cité(巴黎西岱大学);Université Sorbonne Paris Nord(巴黎北索邦大学);SUPSI(瑞士应用科学大学);IDSIA
SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation
Shanghai Jiao Tong University(上海交通大学);The Hong Kong University of Science and Technology(香港科技大学);National University of Singapore(新加坡国立大学);Yuandao AI(元岛人工智能);Shanghai AI Lab(上海人工智能实验室)
Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(穆罕默德·本·扎耶德人工智能大学);University of Science and Technology of China (USTC)(中国科学技术大学);University of Freiburg(弗莱堡大学);Ludwig Maximilian University of Munich (LMU Munich)(慕尼黑大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心)
Robo2Process: Benchmarking and Learning Process-Aware Understanding in Vision-Language Robotic Manipulation
Shanghai AI Laboratory(上海人工智能实验室);Zhejiang University(浙江大学);Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学);China University of Mining Technology(中国矿业大学)
Disturbance-Aware Flight Control of Robotic Gliding Blimp via Moving Mass Actuation
Robotics and Control Laboratory, School of Advanced Manufacturing and Robotics, and the State Key Laboratory of Turbulence and Complex Systems, Peking University(机器人与控制实验室,先进制造与机器人学院,湍流与复杂系统国家重点实验室,北京大学)
Open-Source, Cost-Aware Kinematically Feasible Planning for Mobile and Surface Robotics
Open Navigation LLC;Carnegie Mellon University(卡内基梅隆大学);Locus Robotics;QUT Centre for Robotics and School of Electrical Engineering and Robotics(QUT机器人中心和电气工程与机器人学院)
Vision-Language Procedural Reasoning for Context-Aware Reward Modeling of Robotic Endovascular Guidewire Navigation
Department of Control Science and Engineering, College of Electronic and Information Engineering, and Shanghai Institute of Intelligent Science and Technology, Tongji University(同济大学电子与信息工程学院控制科学与工程系,以及上海智能科学与技术研究院);Department of Electronic Engineering, Faculty of Engineering, The Chinese University of Hong Kong(香港中文大学工程学院电子工程系);Shanghai Operation Robot Co., Ltd.(上海微创医疗机器人(集团)股份有限公司)
Skill-Aware Diffusion for Generalizable Robotic Manipulation
School of Control Science and Engineering, Shandong University(控制科学与工程学院,山东大学);Department of Computer Science, The University of Manchester(计算机科学系,曼彻斯特大学)
CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation
State Key Laboratory of Robotics and System, Harbin Institute of Technology(机器人系统国家重点实验室,哈尔滨工业大学);The University of Sydney(悉尼大学);Honor Device Co., Ltd.(荣耀设备有限公司)