teleoperation
In plain wordsControlling a robot or machine from a distance, with a person steering it in real time using a joystick, a matching 'puppet' arm, a VR headset or a screen.
Control of a robot or machine by a person who is not at its location, sending commands over a link and receiving sensor feedback — usually video, sometimes force or touch. Interfaces range from joysticks and screens to leader–follower setups, in which the operator moves a kinematically matched leader arm and the remote follower copies it, and virtual-reality headsets with hand tracking. Bilateral teleoperation returns contact forces to the operator through haptics; delays on long or wireless links can destabilize such loops. Traditional uses include handling hazardous materials, bomb disposal, deep-sea and space work, remote surgery and drone piloting. Two newer uses matter for AI. Teleoperation is the main source of demonstration data for imitation learningimitation learning, n.: Teaching an AI by showing it examples of an expert doing a task, so it learns to copy the behavior instead of discovering it through trial and error. in 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., made cheap by low-cost rigs such as ALOHA; and it backs up autonomy, as when remote operators assist stuck robotaxisrobotaxi, n.: A taxi with no human driver: you summon it with a phone app, and a self-driving car picks you up and drives you to your destination. or when makers of home robots have staff complete tasks their software cannot. Whether a robot demonstration was teleoperated is therefore an important disclosure.
Half of the training data came from teleoperation with a leader–follower arm pair.
Origin
From Greek tele-, 'far'. Raymond Goertz built mechanical and then electrically driven master–slave manipulators at Argonne National Laboratory from the late 1940s to handle radioactive material; Marvin Minsky's 1980 essay 'Telepresence' named the goal of feeling present at the remote site.
Usage note
Teleoperated robots are not autonomous, and promotional videos sometimes blur the two. For automated vehicles, 'remote assistance' (advising the vehicle) is distinguished from 'remote driving' (controlling it directly).
Related
- imitation learningimitation learning, n.: Teaching an AI by showing it examples of an expert doing a task, so it learns to copy the behavior instead of discovering it through trial and error.
- 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.
- action chunkingaction chunking, n.: Having a robot's AI plan a short burst of upcoming movements, say the next second, all at once instead of one tiny motion at a time, which makes motion smoother and mistakes rarer.
- human-in-the-loophuman-in-the-loop, adj.: Describes AI systems in which a person checks, corrects or approves the machine's work at key points, rather than letting it act entirely on its own.
- robotaxirobotaxi, n.: A taxi with no human driver: you summon it with a phone app, and a self-driving car picks you up and drives you to your destination.
- humanoid robothumanoid robot, n.: A robot built roughly in human shape, with a head, torso, two arms and usually two legs, so that it can work in spaces and with tools designed for people.
- human–robot interactionhuman–robot interaction, n.: The study of how people and robots communicate, cooperate and share spaces, and of how to design robots that people find safe, understandable, trustworthy and pleasant to live or work with.
Sources
- Sheridan, T. B. (1992). Telerobotics, Automation, and Human Supervisory Control. MIT Press.
- Minsky, M. (1980). Telepresence. Omni, June 1980.
Mentioned in
dronedrone, n.: An aircraft that carries no one aboard to fly it: a person steers it from the ground, or its own software does. Small camera-carrying quadcopters are the most familiar kind., humanoid robothumanoid robot, n.: A robot built roughly in human shape, with a head, torso, two arms and usually two legs, so that it can work in spaces and with tools designed for people., collaborative robotcollaborative robot, n.: A robot designed to work safely right next to people without a safety cage, for example by moving gently and stopping at once if it bumps into someone., imitation learningimitation learning, n.: Teaching an AI by showing it examples of an expert doing a task, so it learns to copy the behavior instead of discovering it through trial and error., 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., robot foundation modelrobot foundation model, n.: One large AI model trained on huge amounts of robot and internet data so that it can control many robots on many tasks, and be adapted quickly to new ones., 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., robotaxirobotaxi, n.: A taxi with no human driver: you summon it with a phone app, and a self-driving car picks you up and drives you to your destination., action chunkingaction chunking, n.: Having a robot's AI plan a short burst of upcoming movements, say the next second, all at once instead of one tiny motion at a time, which makes motion smoother and mistakes rarer., DAggerDAgger, n.: A way of teaching a robot by imitation in which an expert keeps labeling what it should have done in the situations it actually gets into, so it learns to recover from its own mistakes., dexterous manipulationdexterous manipulation, n.: Skilled handling of objects with robot fingers, such as spinning a pen, turning a key or rotating a cube in one hand: the fine finger work people do without thinking., human–robot interactionhuman–robot interaction, n.: The study of how people and robots communicate, cooperate and share spaces, and of how to design robots that people find safe, understandable, trustworthy and pleasant to live or work with., π0π0, prop. n.: A general-purpose AI model for controlling robots, released in 2024 by the start-up Physical Intelligence, that sees through cameras, follows typed or spoken instructions and moves robot arms deftly enough to fold laundry.