embodied AI
In plain wordsAI that has a body, usually a robot and sometimes a simulated character, and learns or acts by sensing and moving in a world rather than only processing text or images.
The study and engineering of agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. that perceive and act through a physical or simulated body situated in an environment, so that intelligence is shaped by, and evaluated through, sensorimotor interaction rather than by processing disembodied data. In current research the term covers robot learningrobot learning, n.: Teaching robots skills from data and experience, such as watching demonstrations, practicing by trial and error or training in simulation, instead of programming every movement by hand., learned navigation and manipulationmanipulation, n.: A robot's use of arms, hands or grippers to change the world around it: picking things up, moving, pushing, opening, assembling or using tools., instruction following in 3D simulators such as AI2-THOR and Habitat, embodied question answering and, since 2023, vision-language-action modelsvision-language-action model, n.: An AI model that looks through a robot's cameras, reads an instruction such as 'put the cup in the sink', and turns both straight into the robot's movements. that connect language-modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code. knowledge to motor control. A recurring claim of the field, inherited from embodied cognitionembodied cognition, n.: The idea that thinking is not something the brain does on its own: the body, its senses and movements, and its surroundings play a real part in how we think and understand., is that some capacities, such as common sense about objects, forces, causality and space, are learned most efficiently, or only, through interaction; whether models trained on text and video can acquire them without a body is an open question related to the symbol grounding problemsymbol grounding problem, n.: The puzzle of how words or symbols inside a machine can mean anything by themselves, rather than only pointing to more symbols — like a dictionary that defines every word using other words..
The lab's embodied AI work trains agents in simulated apartments before moving them onto real robots.
Origin
The thesis that intelligence needs a body was pressed in robotics by Rodney Brooks ('Elephants Don't Play Chess', 1990; 'Intelligence without Representation', 1991) and developed by Rolf Pfeifer and colleagues as embodied artificial intelligence in the 1990s and 2000s; the first use of the exact phrase is not established. The short form 'embodied AI' became common in the late 2010s for deep-learning agents trained in 3D simulators and the standard umbrella term for learned robotics in the 2020s.
Usage note
Overlaps heavily with physical AIphysical AI, n.: AI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them., which stresses industrial deployment, and with robot learningrobot learning, n.: Teaching robots skills from data and experience, such as watching demonstrations, practicing by trial and error or training in simulation, instead of programming every movement by hand., which stresses methods. 'Embodied agent' is also used, confusingly, for animated on-screen characters and avatars.
Related
- robot learningrobot learning, n.: Teaching robots skills from data and experience, such as watching demonstrations, practicing by trial and error or training in simulation, instead of programming every movement by hand.
- physical AIphysical AI, n.: AI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them.
- embodied cognitionembodied cognition, n.: The idea that thinking is not something the brain does on its own: the body, its senses and movements, and its surroundings play a real part in how we think and understand.
- vision-language-action modelvision-language-action model, n.: An AI model that looks through a robot's cameras, reads an instruction such as 'put the cup in the sink', and turns both straight into the robot's movements.
- world modelworld model, n.: An AI's internal simulation of how its world works, which lets it predict what will happen next — especially in response to its own actions — and so plan, imagine or practice without acting for real.
- symbol grounding problemsymbol grounding problem, n.: The puzzle of how words or symbols inside a machine can mean anything by themselves, rather than only pointing to more symbols — like a dictionary that defines every word using other words.
- Moravec's paradoxMoravec's paradox, n.: The observation that what is hard for people, like chess or algebra, is often easy for computers, while what toddlers do effortlessly, such as seeing, walking and picking things up, is very hard for machines.
- large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code.
Sources
- Brooks, R. A. (1991). Intelligence without representation. Artificial Intelligence 47, 139–159.
- Pfeifer, R. & Bongard, J. (2006). How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press.
Mentioned in
physical AIphysical AI, n.: AI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them., robotrobot, n.: A machine that senses its surroundings, decides what to do and physically acts, moving itself or handling objects, with some independence from a human operator. Factory arms, robot vacuums and self-driving cars are all robots., roboticsrobotics, n.: The science and engineering of building robots and making them work: designing their bodies, sensors and motors, and writing the software that lets them see, plan and move safely., embodied cognitionembodied cognition, n.: The idea that thinking is not something the brain does on its own: the body, its senses and movements, and its surroundings play a real part in how we think and understand., groundinggrounding, n.: Connecting an AI's words to something real — trusted documents, a live search, images or the physical world — so that its answers rest on evidence rather than only on what it absorbed in training., Moravec's paradoxMoravec's paradox, n.: The observation that what is hard for people, like chess or algebra, is often easy for computers, while what toddlers do effortlessly, such as seeing, walking and picking things up, is very hard for machines., perceptionperception, n.: How an AI system or robot turns raw sensor signals, such as camera pixels, microphone sound or laser scans, into an understanding of what is around it: objects, people, words and distances., robot learningrobot learning, n.: Teaching robots skills from data and experience, such as watching demonstrations, practicing by trial and error or training in simulation, instead of programming every movement by hand., Rodney BrooksRodney Brooks, prop. n.: An Australian-American roboticist who argued that intelligence grows out of acting in the world rather than abstract reasoning, and who co-founded the company behind the Roomba vacuum., symbol grounding problemsymbol grounding problem, n.: The puzzle of how words or symbols inside a machine can mean anything by themselves, rather than only pointing to more symbols — like a dictionary that defines every word using other words., Gemini RoboticsGemini Robotics, prop. n.: A family of AI models from Google DeepMind, built on its Gemini models, that let robots understand what they see and what people ask of them, and turn that understanding into physical actions., ICRAICRA, prop. n.: The largest yearly robotics conference, run by the engineering society IEEE, covering everything from robot arms and drones to self-driving cars., spatial intelligencespatial intelligence, n.: The ability to understand, imagine and act in three-dimensional space and the physical world — effortless for people, and treated by many AI researchers as the next big goal after language., subsumption architecturesubsumption architecture, n.: A way to build robot brains from stacked, reflex-like behaviors — a bottom layer that keeps clear of obstacles, others that roam or explore — where higher layers can take over from lower ones, with no central map or plan.