Human–robot interaction

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Human–robot interaction is the study of interactions between humans and robots. It is often referred as HRI by researchers. Human–robot interaction is a multidisciplinary field with contributions from human–computer interaction, artificial intelligence, robotics, natural language understanding, design, and social sciences.


Human–robot interaction has been a topic of both science fiction and academic speculation even before any robots existed. Because HRI depends on a knowledge of (sometimes natural) human communication, many aspects of HRI are continuations of human communications topics that are much older than robotics per se.

The origin of HRI as a discrete problem was stated by 20th-century author Isaac Asimov in 1941, in his novel I, Robot. He states the Three Laws of Robotics as,

These three laws of robotics determine the idea of safe interaction. The closer the human and the robot get and the more intricate the relationship becomes, the more the risk of a human being injured rises. Nowadays in advanced societies, manufacturers employing robots solve this issue by not letting humans and robots share the workspace at any time. This is achieved by defining safe zones using lidar sensors or physical cages. Thus the presence of humans is completely forbidden in the robot workspace while it is working.

With the advances of artificial intelligence, the autonomous robots could eventually have more proactive behaviors, planning their motion in complex unknown environments. These new capabilities keep safety as the primary issue and efficiency as secondary. To allow this new generation of robot, research is being conducted on human detection, motion planning, scene reconstruction, intelligent behavior through task planning and compliant behavior using force control (impedance or admittance control schemes).

The goal of HRI research is to define models of humans' expectations regarding robot interaction to guide robot design and algorithmic development that would allow more natural and effective interaction between humans and robots. Research ranges from how humans work with remote, tele-operated unmanned vehicles to peer-to-peer collaboration with anthropomorphic robots.

Many in the field of HRI study how humans collaborate and interact and use those studies to motivate how robots should interact with humans.

The goal of friendly human–robot interactions[edit]

Kismet can produce a range of facial expressions.

Robots are artificial agents with capacities of perception and action in the physical world often referred by researchers as workspace. Their use has been generalized in factories but nowadays they tend to be found in the most technologically advanced societies in such critical domains as search and rescue, military battle, mine and bomb detection, scientific exploration, law enforcement, entertainment and hospital care.

These new domains of applications imply a closer interaction with the user. The concept of closeness is to be taken in its full meaning, robots and humans share the workspace but also share goals in terms of task achievement. This close interaction needs new theoretical models, on one hand for the robotics scientists who work to improve the robots utility and on the other hand to evaluate the risks and benefits of this new "friend" for our modern society.

With the advance in AI, the research is focusing on one part towards the safest physical interaction but also on a socially correct interaction, dependent on cultural criteria. The goal is to build an intuitive, and easy communication with the robot through speech, gestures, and facial expressions.

Dautenhahn refers to friendly Human–robot interaction as "Robotiquette" defining it as the "social rules for robot behaviour (a ‘robotiquette’) that is comfortable and acceptable to humans"[1] The robot has to adapt itself to our way of expressing desires and orders and not the contrary. But every day environments such as homes have much more complex social rules than those implied by factories or even military environments. Thus, the robot needs perceiving and understanding capacities to build dynamic models of its surroundings. It needs to categorize objects, recognize and locate humans and further their emotions. The need for dynamic capacities pushes forward every sub-field of robotics.

Furthermore, by understanding and perceiving social cues, robots can enable collaborative scenarios with humans. For example, with the rapid rise of personal fabrication machines such as desktop 3d printers, laser cutters, etc., entering our homes, scenarios may arise where robots can collaboratively share control, co-ordinate and achieve tasks together. Industrial robots have already been integrated into industrial assembly lines and are collaboratively working with humans. The social impact of such robots have been studied [2] and has indicated that workers still treat robots and social entities, rely on social cues to understand and work together.

On the other end of HRI research the cognitive modelling of the "relationship" between human and the robots benefits the psychologists and robotic researchers the user study are often of interests on both sides. This research endeavours part of human society. For effective human - humanoid robot interaction[3] numerous communication skills[4] and related features should be implemented in the design of such artificial agents/systems.

General HRI research[edit]

HRI research spans a wide range of field, some general to the nature of HRI.

Methods for perceiving humans[edit]

Most methods intend to build a 3D model through vision of the environment. The proprioception sensors permit the robot to have information over its own state. This information is relative to a reference.

Methods for perceiving humans in the environment are based on sensor information. Research on sensing components and software led by Microsoft provide useful results for extracting the human kinematics (see Kinect). An example of older technique is to use colour information for example the fact that for light skinned people the hands are lighter than the clothes worn. In any case a human modelled a priori can then be fitted to the sensor data. The robot builds or has (depending on the level of autonomy the robot has) a 3D mapping of its surroundings to which is assigned the humans locations.

A speech recognition system is used to interpret human desires or commands. By combining the information inferred by proprioception, sensor and speech the human position and state (standing, seated).

Methods for motion planning[edit]

Motion planning in dynamic environment is a challenge that is for the moment only achieved for 3 to 10 degrees of freedom robots. Humanoid robots or even 2 armed robots that can have up to 40 degrees of freedom are unsuited for dynamic environments with today's technology. However lower-dimensional robots can use potential field method to compute trajectories avoiding collisions with human.

Cognitive models and theory of mind[edit]

Humans exhibit negative social and emotional responses as well as decreased trust toward some robots that closely, but imperfectly, resemble humans; this phenomenon has been termed the "Uncanny Valley."[5] However recent research in telepresence robots has established that mimicking human body postures and expressive gestures has made the robots likeable and engaging in a remote setting.[6] Further, when tested with an android or humanoid telepresence robot the presence of a human operator felt strongly than in just normal video communication through monitor.[7]

A lot of data has been gathered with regards to user studies. For example, when users encounter proactive behaviour on the part of the robot and the robot does not respect a safety distance, penetrating the user space, he or she might express fear. This is dependent on one person to another. Only intensive experiment can permit a more precise model. It has been shown that when a robot has no particular use, negative feelings are often expressed. The robot is perceived as useless and its presence becomes annoying. In another experiment, it has occurred that people tend to attribute to the robot personality characteristics that were not implemented.

Research demonstrates that during initial interactions, people are more uncertain, anticipate less social presence, and have less liking when thinking about interacting with robots. This finding has been called the human-to-human interaction script (,[8][9]).

Methods for human-robot co-ordination[edit]

A large body of work in the field of human-robot interaction has looked at how humans and robots may better collaborate. Primary social cue for humans to collaborate is the shared perception of an activity, to this end researchers have investigated anticipatory robot control by monitoring the behaviors of human partners using eye tracking, make inferences about human task intent, and plan robots own actions accordingly.[10] The studies revealed that the anticipatory control helped users perform tasks on average 2.5 seconds faster and 3.4 seconds faster when compared to reactive control (where users first performs and action and then robot plans its action)

A common approach to program social cues into robots is to first study human-human behaviors and then transfer the learning. For example, co-ordination mechanisms in human-robot collaboration [11] are based on the seminal work in neuroscience[12] which looked at how to enable joint action in human-human configuration by studying perception and action in social context rather than in isolation. These studies have revealed that maintaining a shared representation of the task is crucial for accomplishing tasks in groups. For example, the authors have examined the task of driving together by separating responsibilities of acceleration and braking i.e, one person is responsible for accelerating and the other for braking, the study revealed that pairs reached the same level of performance as individuals only when they received feedback about the timing of each other’s actions. Similarly, researchers have studied the aspect of human-human handovers with household scenarios like passing dining plates in order to enable an adaptive control of the same in human-robot handovers.[13] Most recently, researchers have studied a system that automatically distributes assembly tasks among co-located workers to improve co-ordination.[14]

Application-oriented HRI research[edit]

In addition to general HRI research, researchers are currently exploring application areas for human-robot interaction systems. Application-oriented research is used to help bring current robotics technologies to bear against problems that exist in today's society. While human-robot interaction is still a rather young area of interest, there is active development and research in many areas.

HRI/OS research[edit]

The Human-Robot Interaction Operating System(HRI/OS), "provides a structured software framework for building human-robot teams, supports a variety of user interfaces, enables humans and robots to engage in task-oriented dialogue, and facilitates integration of robots through an extensible API".[15]

Search and rescue[edit]

First responders face great risks in search and rescue (SAR) settings, which typically involve environments that are unsafe for a human to travel[citation needed]. In addition, technology offers tools for observation that can greatly speed-up and improve the accuracy of human perception[citation needed]. Robots can be used to address these concerns[citation needed] . Research in this area includes efforts to address robot sensing, mobility, navigation, planning, integration, and tele-operated control[citation needed].

SAR robots have already been deployed to environments such as the Collapse of the World Trade Center.[16]

Other application areas include:

  • Entertainment
  • Education
  • Field robotics
  • Home and companion robotics
  • Hospitality
  • Rehabilitation and Elder Care
  • Robot Assisted Therapy (RAT)

See also[edit]





Bartneck and Okada[17] suggest that a robotic user interface can be described by the following four properties:

Tool – toy scale
  • Is the system designed to solve a problem effectively or is it just for entertainment?
Remote control – autonomous scale
  • Does the robot require remote control or is it capable of action without direct human influence?
Reactive – dialogue scale
  • Does the robot rely on a fixed interaction pattern or is it able to have dialogue — exchange of information — with a human?
Anthropomorphism scale
  • Does it have the shape or properties of a human?


International Conference on Social Robotics[edit]

The International Conference on Social Robotics is a conference for scientists, researchers, and practitioners to report and discuss the latest progress of their forefront research and findings in social robotics, as well as interactions with human beings and integration into our society.

  • ICSR2009, Incheon, Korea in collaboration with the FIRA RoboWorld Congress
  • ICSR2010, Singapore
  • ICSR2011, Amsterdam, Netherlands

International Conference on Human-Robot Personal Relationships[edit]

International Symposium on New Frontiers in Human-Robot Interaction[edit]

This symposium is organized in collaboration with the Annual Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour.

  • 2015, Canterbury, United Kingdom
  • 2014, London, United Kingdom
  • 2010, Leicester, United Kingdom
  • 2009, Edinburgh, United Kingdom

IEEE International Symposium in Robot and Human Interactive Communication[edit]

The IEEE International Symposium on Robot and Human Interactive Communication ( RO-MAN ) was founded in 1992 by Profs. Toshio Fukuda, Hisato Kobayashi, Hiroshi Harashima and Fumio Hara. Early workshop participants were mostly Japanese, and the first seven workshops were held in Japan. Since 1999, workshops have been held in Europe and the United States as well as Japan, and participation has been of international scope.

ACM/IEEE International Conference on Human-Robot Interaction[edit]

This conference is amongst the best conferences in the field of HRI and has a very selective reviewing process. The average acceptance rate is 26% and the average attendance is 187. Around 65% of the contributions to the conference come from the USA and the high level of quality of the submissions to the conference becomes visible by the average of 10 citations that the HRI papers attracted so far.[18]

  • HRI 2006 in Salt Lake City, Utah, USA, Acceptance Rate: 0.29
  • HRI 2007 in Washington DC, USA, Acceptance Rate: 0.23
  • HRI 2008 in Amsterdam, Netherlands, Acceptance Rate: 0.36 (0.18 for oral presentations)
  • HRI 2009 in San Diego, CA, USA, Acceptance Rate: 0.19
  • HRI 2010 in Osaka, Japan, Acceptance Rate: 0.21
  • HRI 2011 in Lausanne, Switzerland, Acceptance Rate: 0.22 for full papers
  • HRI 2012 in Boston, Massachusetts, USA, Acceptance Rate: 0.25 for full papers
  • HRI 2013 in Tokyo, Japan, Acceptance Rate: 0.24 for full papers
  • HRI 2014 in Bielefeld, Germany, Acceptance Rate: 0.24 for full papers

International Conference on Human-Agent Interaction[edit]

Related conferences[edit]

There are many conferences that are not exclusively HRI, but deal with broad aspects of HRI, and often have HRI papers presented.

  • IEEE-RAS/RSJ International Conference on Humanoid Robots (Humanoids)
  • Ubiquitous Computing (UbiComp)
  • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • Intelligent User Interfaces (IUI)
  • Computer Human Interaction (CHI)
  • American Association for Artificial Intelligence (AAAI)

Related journals[edit]

There are currently two dedicated HRI Journals

  • International Journal of Social Robotics
  • The open access Journal of Human-Robot Interaction

and there are several more general journals in which one will find HRI articles.


  1. ^ Dautenhahn, Kerstin (29 April 2007). "Socially intelligent robots: dimensions of human–robot interaction" (pdf). Phil. Trans. R. Soc. b. 362 (1480): 679–704. doi:10.1098/rstb.2006.2004. 
  2. ^ Sauppe, Allison; Mutlu, Bilge (2015). "The Social Impact of a Robot Co-Worker in Industrial Settings" (pdf): 3613–3622. doi:10.1145/2702123.2702181. 
  3. ^
  4. ^ "Implications of interpersonal communication competence research on the design of artificial behavioral systems that interact with humans (PDF Download Available)". ResearchGate. Retrieved 2017-03-02. 
  5. ^ Mathur, Maya B.; Reichling, David B. (2016). "Navigating a social world with robot partners: a quantitative cartography of the Uncanny Valley" (PDF). Cognition. 146: 22–32. PMID 26402646. doi:10.1016/j.cognition.2015.09.008. 
  6. ^ Adalgeirsson, Sigurdur; Breazeal, Cynthia (2010). "MeBot: A Robotic Platform for Socially Embodied Presence" (pdf). 
  7. ^ "Android As a Telecommunication Medium with a Human-like Presence" (pdf). 2007. 
  8. ^ Spence, P.R.; Westerman, , David; Edwards, Chad; Edwards, Autumn (2014). "Welcoming our robot overlords: Initial expectations about interaction with a robot". Communication Research Reports. 31: 272–280. doi:10.1080/08824096.2014.924337. 
  9. ^ Edwards, Chad; Edwards, ,Autumn; Spence, P.R.; Westerman, David (2015). "Initial Interaction Expectations with Robots: Testing the Human-To-Human Interaction Script". Communication Studies. 67: 227–238. doi:10.1080/10510974.2015.1121899. 
  10. ^ "Anticipatory Robot Control for Efficient Human-Robot Collaboration" (pdf). 2016. 
  11. ^ "Coordination mechanisms in human-robot collaboration" (pdf). 2013. 
  12. ^ "Joint action: bodies and minds moving together" (pdf). 2006. 
  13. ^ "Adaptive Coordination Strategies for Human-Robot Handovers" (PDF). 2015. 
  14. ^ "WeBuild: Automatically Distributing Assembly Tasks Among Collocated Workers to Improve Coordination" (PDF). 2017. 
  15. ^ Fong, T.; Kunz, C.; Hiatt, L.; Bugjska, M. (2006). "The Human-Robot Interaction Operating System" (PDF). 
  16. ^ Casper, J.; Murphy, R. (June 2003). "Human-robot interactions during the robot-assisted urban search and rescue response at the World Trade Center" (PDF). IEEE Transactions on Systems, Man, and Cybernetics. 33 (3): 367–385. doi:10.1109/tsmcb.2003.811794. 
  17. ^ Bartneck, Christoph; Michio Okada (2001). "Robotic User Interfaces" (PDF). Proceedings of the Human and Computer Conference. pp. 130–140. 
  18. ^ Bartneck, Christoph (February 2011). "The end of the beginning: a reflection on the first five years of the HRI conference". Scientometrics. 86 (2): 487–504. doi:10.1007/s11192-010-0281-x. 

External links[edit]