Representation (politics)
Related papers: 20
About
Representation in robotics and AI refers to the internal structures and formats used to encode knowledge about the world, enabling intelligent systems to reason, plan, and act. These structures can take many forms — probabilistic graphical models that capture uncertainty, spatial maps encoding environment geometry, point clouds or voxel grids describing 3D scenes, or learned motor primitives encoding movement dynamics. In robotics, representations are fundamental to tasks such as localization and mapping (SLAM), object recognition and pose estimation, motion planning, and sensor fusion, where a robot must maintain an accurate, actionable model of itself and its surroundings. The choice of representation profoundly shapes what a system can perceive, learn, and do: compact or distributed representations enable efficient computation, while richer semantic representations support more flexible reasoning. As systems grow more complex — navigating dynamic environments, manipulating objects, or learning from demonstration — the quality and expressiveness of underlying representations increasingly determines whether a robot can generalize reliably beyond its training conditions.
Top Researchers
Top Cited Papers
Probabilistic graphical models : principles and techniques
Daniel L. Koller, Nir Friedman
Citations: 6456 • 2009
Intelligence without representation
Rodney A. Brooks
Citations: 4701 • 1991
VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
Yin Zhou, Oncel Tuzel
Citations: 4542 • 2018
Simultaneous localization and mapping: part I
Hugh Durrant‐Whyte, T. Bailey
Citations: 4107 • 2006
VoxNet: A 3D Convolutional Neural Network for real-time object recognition
Daniel Maturana, Sebastian Scherer
Citations: 3579 • 2015
A tutorial on visual servo control
Seth Hutchinson, Gregory D. Hager, Peter Corke
Citations: 3499 • 1996
OctoMap: an efficient probabilistic 3D mapping framework based on octrees
Armin Hornung, Kai M. Wurm, Maren Bennewitz, Cyrill Stachniss, Wolfram Burgard
Citations: 2827 • 2013
Adaptive representation of dynamics during learning of a motor task
Reza Shadmehr, FA Mussa-Ivaldi
Citations: 2666 • 1994
PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
Xiang Yu, Tanner Schmidt, Venkatraman Narayanan, Dieter Fox
Citations: 2088 • 2018
Biped walking pattern generation by using preview control of zero-moment point
Shuuji Kajita, Fumio Kanehiro, Kenji Kaneko, Kiyoshi Fujiwara, Kensuke Harada, Kazuhito Yokoi, Hirohisa Hirukawa
Citations: 2083 • 2004
Monte Carlo localization for mobile robots
Frank Dellaert, D. Fox, Wolfram Burgard, Sebastian Thrun
Citations: 1613 • 2003
On the Representation and Estimation of Spatial Uncertainty
Randall C. Smith, Peter Cheeseman
Citations: 1562 • 1986
Sonar-based real-world mapping and navigation
Alberto Elfes
Citations: 1395 • 1987
Globally Consistent Range Scan Alignment for Environment Mapping
Feng Lu, Evangelos Milios
Citations: 1272 • 1997
Estimating Uncertain Spatial Relationships in Robotics
Randall K. Smith, Matthew W. Self, Peter Cheeseman
Citations: 1269 • 1990
The neural and behavioural organization of goal-directed movements
Marc Jeannerod
Citations: 1175 • 1988
Modeling and control of formations of nonholonomic mobile robots
Jaydev P. Desai, J.P. Ostrowski, Vijay Kumar
Citations: 1155 • 2001
A survey of vision-based methods for action representation, segmentation and recognition
Daniel Weinland, Rémi Ronfard, Edmond Boyer
Citations: 1008 • 2010
Robot Motion Planning: A Distributed Representation Approach
Jérôme Barraquand, Jean‐Claude Latombe
Citations: 988 • 1991
Sensor Fusion in Certainty Grids for Mobile Robots
Hans Moravec
Citations: 968 • 1989