State space

Related papers: 20

About

State space is a mathematical framework that represents all possible configurations or conditions a system can occupy at any given moment. In robotics and AI, it is typically defined as a multidimensional vector capturing every variable needed to fully describe a robot or system — such as joint positions, velocities, sensor readings, or probability distributions over uncertain quantities. Algorithms for motion planning, control, localization, and learning all operate by reasoning about trajectories, transitions, or policies within this space. Planning methods like RRT and DDP search for feasible or optimal paths through state space, while control approaches such as sliding-mode and feedback controllers drive a robot toward desired states. Probabilistic techniques like particle filters and POMDPs extend the concept to belief space, where uncertainty about the true state is explicitly modeled. State space representation matters because it provides a unified, rigorous language for formulating and solving diverse robotics problems — from trajectory optimization and simultaneous localization and mapping to reinforcement learning — making complex system behavior analyzable, predictable, and ultimately controllable.

Top Cited Papers

A survey of robot learning from demonstration

Brenna Argall, Sonia Chernova, Manuela Veloso, Brett Browning

Citations: 3252 • 2008

Randomized Kinodynamic Planning

Steven M. LaValle, James Kuffner

Citations: 3241 • 2001

Tracking control of non-linear systems using sliding surfaces, with application to robot manipulators†

J.-J.E. Slotine, Shankar Sastry

Citations: 1788 • 1983

A Tutorial on Particle Filtering and Smoothing: Fifteen years later

Randal Douc, Adam M. Johansen

Citations: 1407 • 2008

Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks

Kevin J. Murphy, Stuart Russell

Citations: 1185 • 2001

Trajectory generation and control for precise aggressive maneuvers with quadrotors

Daniel Mellinger, Nathan Michael, Vijay Kumar

Citations: 866 • 2012

Model checking for programming languages using VeriSoft

Patrice Godefroid

Citations: 828 • 1997

Randomized Kinodynamic Motion Planning with Moving Obstacles

David Hsu, R. Kindel, Jean‐Claude Latombe, Stephen M. Rock

Citations: 768 • 2002

Resampling Methods for Particle Filtering: Classification, implementation, and strategies

Tiancheng Li, Miodrag Bolić, Petar M. Djurić

Citations: 595 • 2015

Universal plans for reactive robots in unpredictable environments

Marcel Schoppers

Citations: 479 • 1987

Control-limited differential dynamic programming

Yuval Tassa, Nicolas Mansard, Emo Todorov

Citations: 441 • 2014

Fast iterative alignment of pose graphs with poor initial estimates

Eli Olson, John J. Leonard, Seth Teller

Citations: 427 • 2006

Feedback control of a nonholonomic wheeled cart in Cartesian space

Claude Samson, Karim Ait-Abderrahim

Citations: 422 • 2002

Kinodynamic RRT*: Asymptotically optimal motion planning for robots with linear dynamics

Dustin J. Webb, Jur van den Berg

Citations: 412 • 2013

Smooth and time-optimal trajectory planning for industrial manipulators along specified paths

Daniela Constantinescu, Elizabeth A. Croft

Citations: 383 • 2000

Differentially constrained mobile robot motion planning in state lattices

Mihail Pivtoraiko, Ross A. Knepper, Alonzo Kelly

Citations: 380 • 2009

Abstraction and Control for Groups of Robots

Călin Belta, V. Kumar

Citations: 338 • 2004

Integrated task and motion planning in belief space

Leslie Pack Kaelbling, Tomás Lozano‐Pérez

Citations: 332 • 2013

Control of Mechanical Systems With Rolling Constraints

Nilanjan Sarkar, Xiaoping Yun, Vijay Kumar

Citations: 332 • 1994

Modeling and control of constrained dynamic systems with application to biped locomotion in the frontal plane

H. Hemami, Bostwick F. Wyman

Citations: 327 • 1979