What is Human-Robot Interaction?

The complex relationship between robots and humans

How to design the HRI in real projects?

The Human-Robot Interaction definitions

Goodrich & Schultz

2008, p. 1

Human–Robot Interaction (HRI) is a field of study dedicated to under- standing, designing, and evaluating robotic systems for use by or with humans. Interaction, by definition, requires communication between robots and humans. Communication between a human and a robot may take several forms, but these forms are largely influenced by whether the human and the robot are in close proximity to each other or not.

Feil-Seifer & Mataric

2009, pp. 1-2

Human-robot interaction (HRI) is the interdisciplinary study of interaction dynamics between humans and robots. Researchers and practitioners specializing in HRI come from a variety of fields, including engineering (electrical, mechanical, industrial, and design), computer science (human-computer interaction, artificial intelligence, robotics, natural language understanding, and computer vision), social sciences (psychology, cognitive science, communications, anthropology, and human factors), and humanities (ethics and philosophy).

The HRI taxonomies & challenges

Human supervisory

control of robots in performance of routine tasks. These include handling of parts on manufacturing assembly lines and accessing and delivery of packages, components, mail, and medicines in warehouses, offices, and hospitals. Such machines can be called telerobots, capable of carrying out a limited series of actions automatically, based on a computer program, and capable of sensing its environment and its own joint positions and communicating such information back to a human operator who updates its computer instructions as required.

Automated vehicles

in which a human is a passenger, including automated highway and rail vehicles and commercial aircraft.

Multi-Modal Perception

In the HRI field, perceiving, understanding and reacting in real time to complex human activities is an important challenge, both from the point of view of the sophistication of perceptual technology (sensors, machine vision, etc.) and of the processing capacity of the collected data (e.g. distinction of linguistic and visual data, expression detection, etc.). Interesting robotic examples in this sense are Kismet (Breazeal & Scassellati, 2000) , which can detect and imitate facial expressions or ASIMO (Sakagami et al., 2002) , the humanoid that has a sophisticated system of auditory and visual perception.

Social, Service and Assistive Robotics

Service or assistance robotics concerns the application of robotics in domains such as office, rehabilitation, health care (robots that act as wheelchairs, exoskeletons, arms for rehabilitation or patient handling, for walking accompaniment, etc.) or education while social robotics focuses on man-robot social interaction modes. The definition of assistive robotics (AR) has expanded considerably in recent years, especially with the shift from exclusively physical assistance to a new type of contactless social interaction, which has defined the area of social and assistive robotics (SAR).

Human–robot social interaction

including robot devices to provide entertainment, teaching, comfort, and assistance for children and elderly, autistic, and handicapped persons.

Remote control

of space, airborne, terrestrial, and undersea vehicles for nonroutine tasks in hazardous or inaccessible environments. Such machines are called teleoperators if they perform manipulation and mobility tasks in the remote physical environment in correspondence to continuous control movements by the remote human. If a computer is intermittently reprogrammed by a human supervisor to execute pieces of the overall task, such a machine is a telerobot.

Design and Human Factors

The design of the robot is a key element for the HRI that finds its origins in the theoretical and application area of Human-Computer Interaction (HCI) but presents a number of differences due to the physical embodiment in the real world of the robot. The most explored areas in this field are embodiment, anthropomorphism and the simplicity or complexity of design.

Epigenetic Robotics

This area of research focuses on the development of intelligent machines with the ability to acquire skills and information independently.

Educational Robotics

Robotics is an excellent tool for learning and education in science, technology, engineering and mathematics. Educators use robots with both children and high school or university students also to teach the design approach and develop transversal skills such as problem solving.

The Human-Robot Interaction approaches

The Robot-Centred HRI

Intends the robot as an autonomous entity that pursues its objectives based on its motivations, emotions, etc. In this case, the interaction with people serves exclusively to satisfy the needs of the robot, dictated by its internal architecture and aimed at its survival in the external environment. An example concerns the development of motor sensors and actuators or structures for regulating motivations and interactions with the external social environment.

The Human-Centred HRI

The research analyses how the robot can perform its activities in a way that is acceptable and comfortable for humans. The analysis concerns people’s reaction to the robot’s appearance and behaviour, regardless of its internal architecture. The challenges in this respect are many and, for example, concern: finding a balanced and coherent design between behaviour and appearance of the robot; designing socially acceptable behaviours; developing new methods and for the design and evaluation of HRI; identifying the needs of individuals and groups of subjects to which a robot could adapt and respond; avoiding “uncanny valley” (Mori, 1970) . In this approach also concerns the well-known “media equation” (Reeves & Nass, 1996) , according to which people tend to anthropomorphize and socially treat machines, then treat computers and, by extension, all digital products including robots, as if they were people.

The Robot cognition-Centred HRI

Interprets the robot as an intelligent system, i.e. as a machine able to decide and deal with problems independently, in relation to the tasks it has to perform. This approach, focused on the cognitive abilities of the robot, opens up research scenarios related to the cognitive, learning and problem-solving architectures of robots.