Matching (statistics)

Related papers: 20

About

Matching, in the context of statistics and robotics/AI, refers to the computational process of finding correspondences or alignments between two or more sets of data — such as sensor readings, images, point clouds, or feature descriptors. In robotics, matching is fundamental to tasks like simultaneous localization and mapping (SLAM), where laser range scans or visual features from successive observations must be aligned to build consistent environment maps. Techniques like Iterative Closest Point (ICP) align 3D point clouds for surface reconstruction and robot navigation, while template matching and feature-based methods enable object recognition and 6D pose estimation from camera imagery. Matching also underlies visual odometry, loop closure detection, and grasp synthesis, where candidate configurations are compared against known models or prior data. The importance of matching lies in its role as a bridge between raw sensory input and meaningful spatial or semantic understanding — without reliable correspondence estimation, robots cannot accurately localize themselves, recognize objects, or interact safely with their environment. Advances in deep learning have significantly improved matching robustness under challenging conditions like varying lighting, weather, and viewpoint changes.

Top Cited Papers

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Q. Al-Dujaili, Ye Duan, Omran Al-Shamma, José Santamaría, Mohammed A. Fadhel, Muthana Al‐Amidie, Laith Farhan

Citations: 7484 • 2021

Computer and Robot Vision

Robert M. Haralock, Linda G. Shapiro

Citations: 3952 • 1991

A survey of robot learning from demonstration

Brenna Argall, Sonia Chernova, Manuela Veloso, Brett Browning

Citations: 3252 • 2008

Target-driven visual navigation in indoor scenes using deep reinforcement learning

Yuke Zhu, Roozbeh Mottaghi, Eric Kolve, Joseph J. Lim, Abhinav Gupta, Li Fei-Fei, Ali Farhadi

Citations: 1507 • 2017

Globally Consistent Range Scan Alignment for Environment Mapping

Feng Lu, Evangelos Milios

Citations: 1272 • 1997

StereoScan: Dense 3d reconstruction in real-time

Andreas Geiger, Julius Ziegler, Christoph Stiller

Citations: 1102 • 2011

A flexible and scalable SLAM system with full 3D motion estimation

Stefan Kohlbrecher, Oskar von Stryk, Johannes Meyer, Uwe Klingauf

Citations: 1083 • 2011

SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights

Michael Milford, Gordon Wyeth

Citations: 970 • 2012

Visual simultaneous localization and mapping: a survey

Jorge Fuentes-Pacheco, J. Ruiz-Ascencio, Juan Manuel Rendón-Mancha

Citations: 886 • 2012

Data-Driven Grasp Synthesis—A Survey

Citations: 848 • 2014

The Representation, Recognition, and Locating of 3-D Objects

Olivier Faugeras, Martial Hebert

Citations: 796 • 1986

Matching robot appearance and behavior to tasks to improve human-robot cooperation

Jennifer L. Goetz, Sara Kiesler, Aaron Powers

Citations: 775 • 2004

Socially aware motion planning with deep reinforcement learning

Yu Fan Chen, Michael Everett, Miao Liu, Jonathan P. How

Citations: 715 • 2017

Interactive Robots as Social Partners and Peer Tutors for Children: A Field Trial

Takayuki Kanda, Takayuki Hirano, Daniel Eaton, Hiroshi Ishiguro

Citations: 705 • 2004

A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping

Sebastian Thrun, Wolfram Burgard, D. Fox

Citations: 691 • 2002

Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans

Feng Lu, Evangelos Milios

Citations: 672 • 1997

Mobile robot positioning: Sensors and techniques

J. Borenstein, H. R. Everett, Liang Feng, D.K. Wehe

Citations: 599 • 1997

Navigating Mobile Robots: Systems and Techniques

J. Borenstein, H. R. Everett, Liqiang Feng

Citations: 595 • 1996

DeepIM: Deep Iterative Matching for 6D Pose Estimation

Yi Li, Gu Wang, Xiangyang Ji, Xiang Yu, Dieter Fox

Citations: 581 • 2018

An efficient fastslam algorithm for generating maps of large-scale cyclic environments from raw laser range measurements

Dirk Hähnel, Wolfram Burgard, D. Fox, Sebastian Thrun

Citations: 574 • 2004