Action (physics)

Related papers: 20

About

Action, in the context of robotics and AI, refers to any discrete or continuous behavior executed by an agent to interact with or change its environment. Rooted in physics and philosophy, the concept describes purposeful movement or intervention — from a robot joint's torque to a high-level task step like "pick up object." In robotics and AI, actions are the fundamental building blocks of behavior, connecting perception to physical or simulated outcomes. Systems ranging from reinforcement learning agents and motor schema architectures to large language model planners all define, sequence, and optimize actions to achieve goals. Actions can be represented as primitives (elemental motor commands), policies (mappings from states to behaviors), or structured plans, and can be learned through demonstration, trial-and-error, or observation. Understanding and engineering actions well is critical because effective action selection and execution determines whether a robot can navigate safely, collaborate with humans, adapt to unexpected events, and accomplish complex real-world tasks reliably and efficiently.

Top Cited Papers

Intelligence without representation

Rodney A. Brooks

Citations: 4701 • 1991

Learning and executing generalized robot plans

Richard Fikes, Peter E. Hart, Nils J. Nilsson

Citations: 1033 • 1972

A survey of vision-based methods for action representation, segmentation and recognition

Daniel Weinland, Rémi Ronfard, Edmond Boyer

Citations: 1008 • 2010

Motor Schema — Based Mobile Robot Navigation

Ronald C. Arkin

Citations: 1004 • 1989

Situated Cognition: On Human Knowledge and Computer Representations

William J. Clancey

Citations: 910 • 1997

Reinforcement learning for robots using neural networks

Long-Ji Lin

Citations: 887 • 1992

Reactive reasoning and planning

Michael Georgeff, Amy Lansky

Citations: 881 • 1987

An Interference Effect of Observed Biological Movement on Action

James M. Kilner, Yves Paulignan, Sarah‐Jayne Blakemore

Citations: 841 • 2003

Designing autonomous agents

Pattie Maes

Citations: 804 • 1990

New Approaches to Robotics

Rodney A. Brooks

Citations: 751 • 1991

The anthropomorphic brain: The mirror neuron system responds to human and robotic actions

Valeria Gazzola, Giacomo Rizzolatti, Bruno Wicker, Christian Keysers

Citations: 726 • 2007

Foundations for a New Science of Learning

Andrew N. Meltzoff, Patricia K. Kuhl, Javier R. Movellan, Terrence J. Sejnowski

Citations: 710 • 2009

A Survey on Policy Search for Robotics

Marc Peter Deisenroth

Citations: 684 • 2011

Learning by watching: extracting reusable task knowledge from visual observation of human performance

Yasuo Kuniyoshi, Masayuki Inaba, H. Inoue

Citations: 682 • 1994

Rulers of the world, unite! The challenges and opportunities of artificial intelligence

Andreas Kaplan, Michael Haenlein

Citations: 638 • 2019

Deep visual foresight for planning robot motion

Chelsea Finn, Sergey Levine

Citations: 627 • 2017

Knowledge in Action

Raymond Reiter

Citations: 569 • 2001

Movement Variability and the Use of Nonlinear Tools: Principles to Guide Physical Therapist Practice

Regina T. Harbourne, Nicholas Stergiou

Citations: 519 • 2009

First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations

Guillermo Garcia-Hernando, Shanxin Yuan, Seungryul Baek, Tae‐Kyun Kim

Citations: 511 • 2018

ProgPrompt: Generating Situated Robot Task Plans using Large Language Models

Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg

Citations: 508 • 2023