Sociorobotics is a field of research studying the implications, complexities and subsequent design of artificial social, spatial, cultural and haptic behaviours, protocols and interactions of robots with each other and with humans in equal measure. Intrinsically taking into account the structured and unstructured spaces of habitation, including industrial, commercial, healthcare, eldercare and domestic environments. This emergent perspective to robotic research encompasses and surpasses the conventions of Social robotics and Artificial society/social systems research. Which do not appear to acknowledge that numerous robots (humanoid and non-humanoid) and humans are increasingly inhabiting the same spaces which require similar performances and agency of social behaviour, particularly regarding the commercial emergence of workplace, personal and companion robotics.
Approach
Robots in the near future will be required to behave socially and spatially intelligent in all contexts of artificial social interaction, recognising sophisticated cues from both humans and other robots alike, similar in some respects to the required social awareness and generally expected social behaviour of our animal companions. Furthermore, sociorobotics as a research platform also fully accepts that robots can be modular hardware, controlled by pre-programmed disembodied software agency (ubiquitous digital characters) or even 'Wizard of Oz' style teleoperation requiring the same social intelligence, awareness and protocols. Sociorobotics attempts to go further by observing and incorporating the aesthetic assemblages and intricacies of social, spatial, cultural & haptic complexities to study the creation of artificial social behaviours and the subsequent protocol design considerations for contemporary and future robotics. Sociorobotics also recognises the critical interdisciplinarity of contemporary and future robot design; acquiring theoretical foundations and research methodologies from HRI, Human Geography, Interaction Design, Actor-network theory and Social Psychology. These foundations bring together intimate concepts of space, haptics and social/cultural criteria of heterogeneous human-robot interactions (i.e. Real Dolls, Lars and the Real Girl), engendering a more comprehensive and cognizant research approach to successful robot design.
Enabling technologies
Artificial intelligence and machine learning Advances in artificial intelligence and machine learning underpin many social robot capabilities, including vision, speech understanding and affect recognition. Commonly used tools include pose estimation frameworks, word embedding models for dialogue and deep neural networks for gesture generation and behaviour modelling.
Manufacturing and 3D printing Additive manufacturing has made it easier to prototype and customize robot bodies and expressive heads. The open-source InMoov humanoid platform demonstrates how affordable materials and desktop 3D printers can be used to build social robots. Design studies have examined how to refine robot heads based on feedback from both experts and novice users.
Processing hardware and software frameworks Modern social robots typically use embedded processors comparable to general-purpose computers, sometimes supported by graphics processing units for deep learning tasks. Software frameworks such as the Robot Operating System (ROS) and manufacturer-specific middleware like NAOqi provide modular architectures for integrating perception, cognition, navigation and expressive behaviour. Dedicated frameworks for human–robot interaction define standard interfaces for skeleton tracking, affect sensing, and natural language processing.
Concepts and frameworks
Human–robot interaction frameworks Sociorobotics builds on concepts from Human–robot interaction (HRI), including work that describes different perspectives on how humans and robots relate to each other. Kerstin Dautenhahn proposes a conceptual space for HRI that distinguishes three overlapping perspectives: robot-centred HRI, which treats the robot as an autonomous creature with its own drives and goals; human-centred HRI, which focuses on how people perceive and experience robot behaviour; and robot-cognition-centred HRI, which emphasises internal architectures for planning, learning and decision-making. She argues that socially capable robots usually require an integration of all three perspectives rather than isolated, discipline-specific designs.
Human–robot relationships Dautenhahn also distinguishes between a "caretaker" paradigm, in which humans are expected to care for a robot viewed as a dependent creature, and an "assistant" or "companion" paradigm, in which robots primarily act as helpers that adapt to human needs and preferences. She raises ethical and cognitive concerns about expecting people, especially vulnerable users, to invest emotional resources in machines that seek friendship or attachment, arguing that companion robots should focus on usefulness, reliability and socially appropriate behaviour rather than replacing human relationships.
Socially interactive robots In related work on social robotics, Terrence Fong, Illah Nourbakhsh and Dautenhahn use the term "socially interactive robots" for robots in which social interaction with humans is a central feature, rather than a secondary interface for teleoperation or control. They list common characteristics such as the ability to express or perceive emotions, communicate with high-level dialogue, recognise and model other agents, maintain social relationships, use natural social cues (for example gaze and gesture), display a distinctive personality, and develop social competencies over time. These definitions are often used as a reference point when describing robots and systems studied within sociorobotics.
… excerpt ends here. Continue reading the full article.

