- Atlas
- Engineering
- Human Robot Interaction
Human Robot Interaction
Human–robot interaction (HRI) is the study and design of how people and robots work, talk, and live together.
10 frameworks, from 1945 to today · Robotics · Engineering
- Teleoperation 1945-Present
- Safety by Separation 1961-Present
- Humanlikeness and the Uncanny Valley 1970-Present
- Supervisory Control 1970-Present
- Social robot 1995-Present
- Cobot 1996-Present
- Field and Long-Term Deployment Studies 2005-Present
- Trust and Transparency 2005-Present
- Learning-Based Personalization 2010-Present
- Language-Mediated Interaction 2015-Present
Overview
Human–robot interaction (HRI) is the study and design of how people and robots work, talk, and live together1. It sits at the meeting point of robotics, psychology, design, and computer science, and it asks questions that pure engineering does not: not only whether a robot can perform a task, but whether a person can understand it, trust it, stay safe near it, and want it around1. The field's history is a slow widening of that question—from keeping people out of the robot's way, to putting the robot in the person's world, to building machines that read and respond to human behavior.
Teleoperators and the First Human in the Loop
The earliest human–robot relationships were remote ones. In the 1940s, working on radioactive materials at what became Argonne National Laboratory, Raymond Goertz developed mechanical master–slave manipulators: an operator moved a handle, and a linked arm across a protective wall copied the motion23. These teleoperators kept a human in control while removing the human from danger. The pattern—human commands, machine executes, feedback returns—defined the first decades of interaction.
Teleoperation matured with the space and deep-sea programs. The 1960s and 1970s brought powered, servo-controlled manipulators and, later, force reflection, so the operator could feel what the remote arm touched. The central design problem was transparency: making the remote machine feel like an extension of the operator's own hand. This work established a durable idea—that the interface between person and machine is itself an engineering object, as important as the robot.
Safety by Separation
As industrial robots spread through factories from the 1960s onward, the dominant interaction model was avoidance. A robot arm swinging a heavy payload is dangerous, so the standard answer was to fence it off. Workcells were enclosed, interlocked, and governed by safety standards that treated the human as a hazard to be excluded during operation. This was effective and is still the backbone of industrial safety, but it made "interaction" mostly a matter of keeping the two parties apart. The unresolved problem—how to let people and robots share space without a fence—would drive the field for decades.
Supervisory Control
Full teleoperation ties up a person continuously; full autonomy was not achievable. In the 1970s Thomas Sheridan and William Ferrell at MIT proposed supervisory control, a middle ground in which the human sets goals and monitors, while the machine executes lower-level actions and the operator intervenes when needed. Their framework named the key variables—how often the human must intervene, how much feedback to give, how to allocate authority between person and machine—that HRI still reasons about. It reframed the human not as a joystick operator but as a supervisor, and it made the division of labor between people and machines a research question in its own right.
Cobots and Shared Workspace
The fence came down in the 1990s. In 1996 J. Edward Colgate and Michael Peshkin at Northwestern introduced the "cobot," a robot designed to work alongside a person, and the idea of collaborative robotics took hold: machines built to share space safely rather than be walled off4. The enabling insight was that safety could be designed into the robot itself—through limited force, rounded forms, torque sensing, and speed-and-separation monitoring—rather than enforced only by barriers. Standards for collaborative operation followed in the 2000s and 2010s5. The cobot reframed the human as a coworker, and it opened manufacturing tasks where full automation was impractical but full manual labor was costly.
The Social Turn
Through the 1990s and 2000s, a second current pushed HRI beyond the factory. Researchers began building robots meant to interact with people socially—as guides, companions, teachers, and therapeutic aids. Cynthia Breazeal's Kismet, built at MIT in the late 1990s, used expressive eyes, eyebrows, and vocal affect to engage people and to study how humans read emotion in a machine. The field's methods borrowed from psychology and human–computer interaction: controlled studies of how people respond to a robot's gaze, gesture, voice, and apparent personality. The question shifted from "can it be safe near me?" to "can it be legible, likeable, and socially appropriate?"
Humanlikeness and the Uncanny
A recurring strand asked how human a robot should look. The "uncanny valley," proposed by Masahiro Mori in 1970, held that near-human appearance can provoke discomfort before true humanlikeness is reached. Androids—robots built to resemble people closely—became both a design ambition and a test case. Work by Hiroshi Ishiguro and others produced highly humanlike and remotely operated androids and used them to probe how appearance, motion, and voice affect a person's sense of presence and acceptance. The findings were rarely clean: humanlikeness could aid engagement in some settings and raise expectations or unease in others. The lesson that took hold was that appearance must be matched to function—a machine should signal what it can actually do.
Out of the Lab
As robots moved into homes, hospitals, schools, and streets, researchers confronted a gap between short laboratory studies and long real-world use. Field and long-term deployment studies followed robots through weeks and months of daily life, tracking how people's attitudes changed, how robots broke down, and how use drifted from the designers' intentions. These studies exposed problems invisible in a single session: novelty wearing off, maintenance burden, mismatched expectations, and the difficulty of designing for people who were not researchers. They pushed HRI toward longitudinal methods and toward treating deployment as a source of knowledge rather than a final demonstration.
Trust and Transparency
If people are to rely on robots, they must calibrate their trust—neither over-relying on a fallible machine nor abandoning a capable one. From the 2000s, HRI researchers modeled trust and reliance, borrowing from automation research and human factors. A central finding was that trust should match the robot's actual reliability, and that transparency—showing what the robot is doing and why—helps people calibrate. Studies of robot behavior, explanations, and failure handling showed that how a machine communicates its limits shapes whether people use it well. This work gave the field a vocabulary for the human side of autonomy: reliance, complacency, and the design of interfaces that keep expectations honest.
Learning to Adapt
Machine learning let robots personalize. Instead of fixed behavior, systems could adapt to a particular user's preferences, pace, or style over time—adjusting a assistive arm's assistance, a tutor's difficulty, or a companion's responses. Learning-based personalization raised new interaction questions: how much adaptation is welcome, how to keep the user in control of it, and how to learn from sparse, noisy human feedback. The robot became something that changes because of the relationship, not just something that performs a task.
Conversation and Language
The most recent turn is linguistic. Early social robots used scripted speech and simple commands. As speech recognition and large language models improved through the 2010s and 2020s, robots could hold open-ended conversation, interpret natural-language instructions, and explain themselves in words. LLM-mediated interaction made language a general interface to robot behavior, but it also imported the weaknesses of language models—unreliability, opacity, and the risk of confident error—into physical systems. The open problem is grounding: connecting what a robot says to what it can safely and actually do.
Where the Field Stands
Today HRI draws on all these strands at once. Collaborative robots share factory floors under safety standards; social robots work in classrooms and care settings; teleoperation remains essential for surgery, space, and hazardous work; and language models are being wired into robot control. The field's methods run from controlled laboratory experiments to months-long field deployments, and its central questions remain open: how to build trust that is calibrated rather than blind, how to make increasingly capable and conversational machines legible and safe, and how to design interactions that hold up when the novelty fades and real people, with all their variety, are the ones in the room.
References
- Human–robot interaction, Wikipedia
- Raymond Goertz, Wikipedia
- Remote manipulator (History), Wikipedia
- Cobot (History), Wikipedia
- ISO 10218, Wikipedia
The frameworks of Human Robot Interaction
Each framework is a way of working the field has used: when it held, and the question it answers.
- 1945-Present
- 1961-Present
- 1970-Present
- 1970-Present
Supervisory Control
How should authority be divided between person and machine?
- 1996-Present
- 2005-Present
Field and Long-Term Deployment Studies
How do robots fare in real, long-term use?
- 2005-Present
- 2010-Present
Learning-Based Personalization
How can a robot adapt to an individual user?
- 2015-Present
Language-Mediated Interaction
How can language serve as a general robot interface?
How the ideas connect
Each arrow runs from an earlier idea to the later one it shaped. The list below says what passed between them.
Supervisory Control grew out of Teleoperation
Sheridan and Ferrell's supervisory control grew directly out of teleoperation research at MIT, addressing the problem that continuous manual control tied up the operator. They reframed the human as a supervisor who sets goals and intervenes, rather than a joystick operator.
Carried by Thomas Sheridan; William Ferrell.
Cobot reacted against Safety by Separation
The cobot was defined against safety-by-separation: Colgate and Peshkin designed robots to share space safely rather than be fenced off. The enabling insight was to build safety into the robot itself through limited force and sensing.
Carried by J. Edward Colgate; Michael Peshkin.
Social robot influenced by Humanlikeness and the Uncanny Valley
Mori's uncanny valley shaped the design of early social robots such as Kismet, which used stylized, non-humanlike features to engage people without falling into the valley. Breazeal's work explicitly reasoned about appearance and expressiveness in light of Mori's hypothesis.
Carried by Masahiro Mori; Cynthia Breazeal.
Trust and Transparency influenced by Supervisory Control
Trust research in HRI borrowed supervisory control's framing of authority allocation and human intervention, recasting it as the problem of calibrating reliance on an autonomous machine. The variables Sheridan named—feedback, intervention frequency, authority—became the basis for modeling trust.
Carried by Thomas Sheridan.
Field and Long-Term Deployment Studies grew out of Social robot
Field and long-term deployment studies grew out of the social robot program as researchers moved those robots from lab demonstrations into homes, schools, and hospitals. The longitudinal methods were developed to track how social engagement held up outside controlled studies.
Learning-Based Personalization grew out of Social robot
Learning-based personalization grew out of social robotics' goal of adapting a robot's behavior to an individual user over time, such as a tutor adjusting difficulty or a companion tailoring responses. Machine learning supplied the mechanism for the adaptation that social HRI had sought.
Language-Mediated Interaction grew out of Social robot
Language-mediated interaction grew out of social robots' use of scripted speech and simple commands, as improved speech recognition and language models allowed open-ended conversation. The social turn made language a central interface, which the later work generalized.
Trust and Transparency influenced by Social robot
Social robot research on legibility and appropriate behavior fed into trust and transparency work, which asked how a robot's communicated intent and limits shape whether people rely on it well. Studies of social cues and failure handling carried the concern with legibility into trust calibration.
Language-Mediated Interaction influenced by Trust and Transparency
Trust and transparency research on how robots communicate their limits and reasons fed into language-mediated interaction, where natural language became a means for a robot to explain itself. The concern with legibility and honest expectations carried into conversational interfaces.
Language-Mediated Interaction influenced by Learning-Based Personalization
Learning-based personalization's use of human feedback and adaptation informed language-mediated interaction, which likewise learns from and adapts to natural-language input. The shared reliance on learned models and sparse human signals connects the two.
Beyond the field
Where Human Robot Interaction's ideas came from in other fields, and what they led to there: the strongest 12 of 22 links.
Teleoperation grew out of Remote manipulator in Robotics
The remote manipulator was built to let an operator work at a distance through mechanical master-slave coupling; teleoperation as a field grew directly out of that arrangement and later added sensing and servos.
Carried by Raymond Goertz.
Teleoperation influenced Force control in Robot Manipulation
Teleoperation's force-reflection research supplied the sensing and control concepts that autonomous force control adapted for robots acting without an operator.
Teleoperation influenced by Human-Machine Systems Engineering in Human Factors
Human-machine systems engineering, developed in WWII fire-control and aircraft work, supplied teleoperation with the operator-vehicle display and control loop analysis that shaped early remote handling design.
Teleoperation influenced by Servomechanism and Feedback Control Theory in Mechatronics
Servomechanism and feedback control theory gave teleoperators their position-error feedback and force-reflection designs, as in Goertz's servo-controlled master-slave manipulators at Argonne.
Carried by Raymond Goertz.
Safety by Separation influenced by Hierarchy of hazard controls in Workplace Health And Safety
The hierarchy of hazard controls, with elimination and isolation ranked above guarding, supplied the rationale for physically separating operators from robots rather than relying on warnings or procedures.
Supervisory Control influenced Human–robot interaction in Robotics
Sheridan's supervisory control work on human operators of teleoperators and automated systems supplied the core models of human-robot authority sharing.
Carried by Thomas B. Sheridan.
Supervisory Control influenced by Human-Machine Systems Engineering in Human Factors
Human-machine systems engineering supplied supervisory control with its operator-task analysis and allocation-of-function concepts, which Sheridan and colleagues recast for computer-mediated control.
Carried by Thomas B. Sheridan.
Supervisory Control influenced by Control Theory in Electrical Engineering
Control theory provided the plant models, feedback loops and stability analysis that supervisory control used to formalize the human operator as a supervisor over automated subsystems.
Carried by Thomas B. Sheridan.
Social robot influenced by Behavior-based robotics in Robotics
Behavior-based robotics, especially Brooks's subsumption architecture, gave social robotics its layered reactive control style and its emphasis on embodied interaction rather than deliberative planning.
Carried by Rodney Brooks.
Trust and Transparency influenced by Probabilistic robotics in Robotics
Probabilistic robotics gave transparency and trust research the representations of uncertainty and confidence that robots could expose to users. Explanations of robot belief states and confidence estimates in trust studies were built on probabilistic robot methods.
Trust and Transparency influenced by Human Reliability Analysis in Reliability Engineering
Human reliability analysis provided HRI trust work with quantitative models of human trust, error and dependence on automated systems, notably through the automation-trust literature it fed. HRI researchers adapted these reliability and calibration frameworks to robot partners.
Language-Mediated Interaction influenced LLM-based multiagent systems in Multiagent Systems
Language-mediated interaction research in human-robot interaction, on using natural language to coordinate agents, directly preceded and shaped LLM multiagent systems. It established dialogue as a coordination medium that LLM agents then exploited at scale.

Human Robot Interaction is a planet in Nousfarer
Its city has a tower for each of these 10 frameworks. Land, walk in, and climb one concept at a time.
Land on Human Robot InteractionRelated fields
Fields its ideas are linked to
- Robotics 5 links
- Linguistic Anthropology 2 links
- Human Factors 2 links
- Robot Manipulation 2 links
- Guidance Navigation Control 1 link
- Ai Safety 1 link
- Multiagent Systems 1 link
- Process Control 1 link
- Interpersonal Communication 1 link
- Electrical Engineering 1 link
- Human Computer Interaction 1 link
- Workplace Health And Safety 1 link
More in Robotics
- Mobile Robotics
- Multi Robot Systems
- Robot Control
- Robot Kinematics Dynamics
- Robot Learning
- Robot Manipulation
- Robot Motion Planning
- Robot Perception And Slam
- Robotics
See where Human Robot Interaction sits on the Map of Human Knowledge