Many manipulation tasks require the robot to rearrange objects relative to one another. Such tasks can be described as a sequence of relative poses between parts of a set of rigid bodies. In this work, we propose MATCH POLICY, a simple but novel pipeline for solving high-precision pick and place tasks. Instead of predicting actions directly, our method registers the pick and place targets to the stored demonstrations. This transfers action inference into a point cloud registration task and enables us to realize nontrivial manipulation policies without any training. MATCH POLICY is designed to solve high-precision tasks with a key-frame setting. By leveraging the geometric interaction and the symmetries of the task, it achieves extremely high sample efficiency and generalizability to unseen configurations. We demonstrate its state-of-the-art performance across various tasks on RLBench benchmark compared with several strong baselines and test it on a real robot with six tasks.
KISS-Matcher: Fast and Robust Point Cloud Registration Revisited
Laboratory for Information & Decision Systems (LIDS), Massachusetts Institute of Technology(信息与决策系统实验室,麻省理工学院);The School of Electrical Engineering, KAIST(电气工程学院,韩国科学技术院);Dexory, UK(英国Dexory);Computer Science Engineering and Interdisciplinary Program of AI, Seoul National University(人工智能工程与跨学科项目,首尔国立大学)
GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Guangdong Provincial Key Laboratory of Construction Robotics and Intelligent Construction(广东省建造机器人与智能建筑重点实验室)
Overlap Bias Matching is Necessary for Point Cloud Registration
School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件学院);School of Computer and Information Technology, Beijing Jiaotong University(北京交通大学计算机与信息技术学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Robust Point Cloud Registration Framework Based on Deep Graph Matching(TPAMI Version)
Fudan University(复旦大学);Digital Medical Research Center(数字医学研究中心);School of Basic Medical Science(基础医学院);Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention(上海市医学影像计算与计算机辅助干预重点实验室)
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
National University of Defense Technology(国防科技大学);Defense Innovation Institute, Academy of Military Sciences(军事科学院国防科技创新研究院);Sun Yat-sen University(中山大学)
PARTE: Plane-Assisted Robust Transformation Estimation for Point Cloud Registration
Colorado School of Mines(科罗拉多矿业大学);University of Texas at Dallas(德克萨斯大学达拉斯分校);U.S. Army Combat Capabilities Development Command, Army Research Laboratory(美国陆军作战能力发展司令部陆军研究实验室)
ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
University of Trento(特伦托大学);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会);East China University of Science and Technology(华东理工大学);ETH Zurich(苏黎世联邦理工学院);Shanghai AI Laboratory(上海人工智能实验室)
Resolving the Ambiguity of Complete-to-Partial Point Cloud Registration for Image-Guided Liver Surgery with Patches-to-Partial Matching
Center for Imaging Science and Department of Biomedical Engineering, Rochester Institute of Technology(成像科学中心和生物医学工程系,罗切斯特理工学院);Department of Biomedical Engineering, Vanderbilt University(生物医学工程系,范德比尔特大学);School of Science and Engineering, University of Missouri – Kansas City(科学与工程学院,密苏里大学-堪萨斯城分校)
GlobalMatch: Registration of Forest Terrestrial Point Clouds by Global Matching of Relative Stem Positions
Tongji University(同济大学);Delft University of Technology(代尔夫特理工大学);Zhejiang A&F University(浙江农林大学);Big Data Development Administration of Yichun(宜春市大数据发展管理局)
Robust Point Cloud Registration Framework Based on Deep Graph Matching
Digital Medical Research Center(数字医学研究中心);School of Basic Medical Science(基础医学院);Fudan University(复旦大学);Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention(上海医学影像计算与计算机辅助介入重点实验室)
Global Point Cloud Registration Network for Large Transformations
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);University Institute for Computing Research, University of Alicante(阿利坎特大学大学计算研究所);School of Informatics, University of Edinburgh(爱丁堡大学信息学院)
Efficient divide-and-conquer registration of UAV and ground LiDAR point clouds through canopy shape context
School of Geospatial Engineering and Science, Sun Yat-Sen University(中山大学测绘科学与技术学院);Department of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University(香港理工大学土地测量及地理资讯学系);Changjiang River Scientific Research Institute (CRSRI)(长江水利委员会长江科学院);Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院数字地球重点实验室);Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)(南方海洋科学与工程广东省实验室(珠海))
HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration
Northwestern Polytechnical University(北华理工大学);Wuhan University(武汉大学);Chinese Academy of Sciences(中国科学院);Peking University(北京大学);Chang’an University(长安大学)
CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration
Technical University of Munich(慕尼黑工业大学);Wuhan University(武汉大学);Hubei Luojia Laboratory(湖北珞珈实验室);Nanyang Technological University(南洋理工大学);Beijing Urban Construction Exploration and Surveying Design Research Institute Co. Ltd.(北京城建勘测设计研究院有限责任公司);National University of Defense Technology(国防科技大学)
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
School of Information Science and Technology, University of Science and Technology of China(信息科学与技术学院,中国科学技术大学);Institute of Advanced Technology, University of Science and Technology of China(先进技术研究院,中国科学技术大学)