Sensor fusion
Related papers: 20
About
Sensor fusion is the process of combining data from multiple sensors to produce estimates that are more accurate, complete, and reliable than any single sensor could provide alone. In robotics and AI, it integrates inputs from diverse sources — such as cameras, LiDAR, IMUs, GPS, and sonar — to build coherent representations of a robot's environment and its own state. Common algorithmic approaches include Kalman filtering, Bayesian inference, and deep learning-based fusion, applied to tasks like simultaneous localization and mapping (SLAM), object tracking, and motion forecasting. Temporal and spatial calibration between sensors is critical to ensure data alignment before fusion occurs. Sensor fusion matters because individual sensors have inherent limitations: cameras lack depth perception, GPS fails indoors, and IMUs drift over time. By combining complementary modalities, robots gain robustness against sensor failures, improved perception in challenging conditions, and greater situational awareness. This makes sensor fusion foundational to autonomous vehicles, aerial drones, legged robots, agricultural systems, and search-and-rescue platforms — essentially any application demanding reliable real-world interaction.
Top Researchers
Top Institutes
Top Cited Papers
Argoverse: 3D Tracking and Forecasting With Rich Maps
Ming-Fang Chang, John Lambert, Patsorn Sangkloy, Jagjeet Singh, Sławomir Bąk, Andrew T. Hartnett, Wang De, Peter Carr, Simon Lucey, Deva Ramanan, James Hays
Citations: 1420 • 2019
Sensor Fusion in Certainty Grids for Mobile Robots
Hans Moravec
Citations: 968 • 1989
Unified temporal and spatial calibration for multi-sensor systems
Paul Furgale, Joern Rehder, Roland Siegwart
Citations: 784 • 2013
Multisensor integration and fusion in intelligent systems
R.C. Luo, Michael G. Kay
Citations: 747 • 1989
Agricultural robots for field operations: Concepts and components
Avital Bechar, Clément Vigneault
Citations: 712 • 2016
Bayesian approach to extended object and cluster tracking using random matrices
Wolfgang Koch
Citations: 666 • 2008
Multisensor fusion and integration: approaches, applications, and future research directions
R.C. Luo, Chih‐Chen Yih, Kuo Su
Citations: 613 • 2002
A robust and modular multi-sensor fusion approach applied to MAV navigation
Simon Lynen, Markus Achtelik, Stephan Weiß, Margarita Chli, Roland Siegwart
Citations: 571 • 2013
A Review on Challenges of Autonomous Mobile Robot and Sensor Fusion Methods
Mary B. Alatise, Gerhard P. Hancke
Citations: 570 • 2020
Gesture recognition using a bioinspired learning architecture that integrates visual data with somatosensory data from stretchable sensors
Ming Wang, Zheng Yan, Ting Wang, Pingqiang Cai, Siyu Gao, Yi Zeng, Changjin Wan, Hong Wang, Liang Pan, Jiancan Yu, Shaowu Pan, Ke He, Jie Lü, Xiaodong Chen
Citations: 535 • 2020
Visual-Inertial Sensor Fusion: Localization, Mapping and Sensor-to-Sensor Self-calibration
Jonathan Kelly, Gaurav S. Sukhatme
Citations: 530 • 2010
Decentralized Estimation and Control for Multisensor Systems
Arthur G.O. Mutambara
Citations: 454 • 2019
Data fusion in robotics and machine intelligence
Mongi A. Abidi, R. C. Gonzalez
Citations: 448 • 1992
A Generalized Extended Kalman Filter Implementation for the Robot Operating System
Tom Moore, Daniel W. Stouch
Citations: 406 • 2015
Approaches to Multisensor Data Fusion in Target Tracking: A Survey
David Smith, Soraisam Gobinkumar Singh
Citations: 375 • 2006
A Review of Visual-LiDAR Fusion based Simultaneous Localization and Mapping
César Debeunne, Damien Vivet
Citations: 372 • 2020
Multisensor data fusion
Pramod K. Varshney
Citations: 372 • 1997
Image Fusion Techniques: A Survey
Harpreet Kaur, Deepika Koundal, Virender Kadyan
Citations: 343 • 2021
Data Fusion and Sensor Management: A Decentralized Information-Theoretic Approach
James Manyika, Hugh Durrant‐Whyte
Citations: 335 • 1995
Estimating Three-Dimensional Orientation of Human Body Parts by Inertial/Magnetic Sensing
A.M. Sabatini
Citations: 332 • 2011