Salary 18,700 - 25,800 GBP per annum, depending on qualifications, skills and experience
The two posts are associated to two new European FP7 Integrated Projects that will investigate language development using the humanoid robot iCub (post A - Developmental Social Robotics), as well as the development of robot companions suitable for long-term interactions (post B - Cognitive Social Robotics).
The posts offer the opportunity to work within the Adaptive Systems Research Group, a proactive, dynamic and interdisciplinary research team with an excellent international research profile. The group consists of five key academics, 12 postdocs and 16 research assistants/PhD students. Relevant to the posts, the group is leading research in the fields of Social and Developmental Robotics, Human-Robot Interaction and Adaptive Behaviour. Over the past few years the group has attracted substantial research funding in this area.
Robots to be used in the research include:
Note, all applicants must be made formally via the Human Resources department at University of Hertfordshire. The closing dates for the two positions are 20/24 March 2008, as specified below. Find out more details about the posts, as well as application forms here.
Applications from postgraduate/postdoctoral candidates are invited for a full-time research assistantship or research fellowship in developmental social robotics (fixed-term contract up to 3 years). The post offers the opportunity to work within the Adaptive Systems Research Group, a proactive and dynamic research team with an excellent international research profile. The successful candidate will work in the European project ITALK (Integration and Transfer of Action and Language Knowledge in Robot). The ITALK project aims to develop artificial embodied agents able to acquire complex behavioural, cognitive, and linguistic skills through individual and social learning. This will be achieved through the development of cognitive robots that learn to handle and manipulate objects and tools autonomously, to cooperate and communicate with other robots and humans, and to adapt their abilities to changing internal, environmental, and social conditions. The main hypothesis behind the project is that the parallel development of action, conceptualization and social interaction permits the enhancement of language capabilities, which on their part enrich cognitive development. This is possible through the integration and transfer of knowledge and cognitive processes involved in sensorimotor learning and the construction of action categories, imitation and other forms of social learning, the acquisition of grounded conceptual representations and the development of the grammatical structure of language. Such a developmental approach towards the integration of action, conceptualization, social interaction and language has fundamental technological implications for designing communication in robots and overcoming current limitations of natural language interfaces and human-robot communication systems. Different partners in the highly interdisciplinary project consortium cooperate closely in the study of different aspects of this challenging work.
The research team at University of Hertfordshire is involved in the development of software and algorithms that will contribute to the development of complex, compositional and hierarchical behaviour and communication via scaffolded social learning, involving the use of deixis, gesture, reference, negation, imitation, and constructional grounding in embodied human-robot interaction. Processes centering on social learning play an important part in child development in the emergence of linguistic, communicative, and cognitive competencies, and computational algorithms will be developed to study these issues using leading-edge child-sized humanoid robot platforms (KASPAR http://kaspar.feis.herts.ac.uk/ and the iCub http://www.robotcub.org/) available in the group. The work will use the facilities available in the Robotics and Interactive Systems Laboratory, as part of the Adaptive Systems Research Group at University of Hertfordshire which has a strong research record in adaptive behaviour, artificial life, and robot-human interaction. The research involves: a) investigating developmental models for language and communication relying on imitation and social interaction, and their relation to cognition and behavioural scaffolding b) Dealing with the sensori-motor loop of the robot (programming, interfacing sensors and operating actuators), c) designing, conducting and statistically analysing human-robot interacting studies into the development of behavioural and linguistic competences, d) writing and presenting scientific publications and reports documenting the work.
Applicants are expected to have excellent qualifications and experience in biologically-inspired research, Artificial Intelligence, Artificial Life, Machine Learning, Mobile Robotics, or related disciplines. A specialist postgraduate degree or PhD, or other strong evidence of research experience is required, as well as excellent skills in presenting research and writing scientific documents in English. The successful candidate should also be very motivated to working in an interdisciplinary and European research team. A postgraduate applicant may pursue a PhD as part of the research.
The position is based on a fixed-term contract of up to three years. The post is available full-time. Start date: April 2008 or later. Informal enquiries can be made to Prof. Chrystopher L. Nehaniv (C.L.Nehaniv A-T herts.ac.uk).
Applications are invited from postgraduate/postdoctoral candidates for a full-time Research Assistant/Research Fellow post (fixed-term contract up to one year).
The successful candidate will work in the European project LIREC (LIving with Robots and intEractive Companions). LIREC takes social technology to a new state-of-the-art. The project will establish a multi-faceted (memory, emotions, cognition, communication, learning, etc.) theory of artificial long-term companions, embody it in innovative technology, verify the theory and technology experimentally in real social environments, and provide guidelines for designing such companions. Companions will be developed with different capabilities, relating to a common cognitive-affective architecture, depending on their intended use. This may involve the ability to detect and respond sensitively to the user, regard his or her possible motives and intentions, and encompass several forms of communication. The project draws upon skills across a range of scientific disciplines and will develop new theory and experimental methodologies, and consider ethical aspects of human-robot companionship. Different partners in the highly interdisciplinary project consortium cooperate closely in the study of different aspects of this challenging work.
Within LIREC, the research team at University of Hertfordshire is involved in different research activities regarding the embodied and social nature of human-robot interaction as investigated in user studies, as well the development of algorithms to develop a viable model linking long-term memory (LTM) and working memory (WM) to associated human processes of remembering and forgetting. Specifically, the research associated to this post concerns the nature of “autobiographic memory” for companions, i.e. architectures that allow an agent to re-construct meaningful experiences in order to inform decision-making in a current situation. Computational algorithms will be developed to study these issues, implemented and tested on different platforms, including mobile devices and, importantly, physical robots that are available in the research group and which include a child-sized humanoid robot platform (KASPAR http://kaspar.feis.herts.ac.uk/), as well as human-sized mobile robots available in the research group. The work will use the state-of-the-art facilities available in the Robotics and Interactive Systems Laboratory, as part of the Adaptive Systems Research Group at University of Hertfordshire.
Applicants are expected to have previous research experience in developing memory architectures for robotic and/or software agents. A specialist postgraduate degree or PhD, or other strong evidence of research experience is required, as well as excellent skills in presenting research and writing scientific documents in English. Excellent programming skills are essential for this post. The successful candidate should also be highly motivated to working in an interdisciplinary and European research team.
The position is based on a fixed-term contract of up to 1 year. The post is available full-time. Start date: April 2008 or later. Informal enquiries can be made to Prof. Kerstin Dautenhahn (K.Dautenhahn A-T herts.ac.uk).