Toward Self-Conscious Robotics

Objective. Robot consciousness is an emerging field that addresses the problems of designing and implementing computational models of consciousness in a robot. The target of robot consciousness research is twofold: the possibility of building conscious robots (i.e., facing the hard problem of consciousness) and the analysis of the active role of consciousness in controlling and planning the behavior of a robot. Robot consciousness is
placed at the crossing between technical disciplines (AI, robotics, computer science and engineering), theoretical disciplines (philosophy of mind, linguistics, logic), and empirical disciplines (psychology and neuroscience). It focuses on attempts to apply the methods of AI, robotics and computer science to understand consciousness and to examine the possible role of consciousness in Robotics. On the one hand there is the hope that facing the problem of consciousness would be a decisive move to design really autonomous robots, on the other hand the implementations of robotic models of consciousness could be helpful for understanding natural consciousness.

Outline.The symposium will present the current state of research in robot consciousness and will discuss the theoretical foundations and the experimental results of the field and their importance for the IAS community.

The symposium will be divided in three parts:

- theoretical aspects of consciousness
- models of machine consciousness
- self-consciousness in robotics and AI

Background. In the last few years, the once “incongruous” idea of machine consciousness gained increasing momentum. This upsurge of interest in a such a technological possibility has been encouraged by the parallel increase in consciousness-related research in the field of neuroscience. Are these studies of any relevance in the field of robotics, artificial intelligence, and computer vision? Artificial consciousness, sometimes labeled as machine
consciousness, is the attempt to model and implement those aspects of human cognition that are identified with the often elusive and controversial phenomenon of consciousness. In brief, the tutorial will outline the complete theoretical framework in which current consciousness related scientific research is carried on. The tutorial will also list the most
promising models (Global Work Space, Tononi’s information integration, Embodied Cognition, Damasio's core consciousness model, Externalist approaches to conscious experience) contrasting advantages and shortcomings.

Consciousness and BICA. There is little doubt that - whatever consciousness is - has a decisive selective advantage. Consciousness is related with intentions, cognitive integration, behavioral flexibility, and andling the unexpected. Furthermore, consciousness appears to be related with the control of development and learning. It is thus obvious that the analysis of biological intelligent systems, such as animals and humans, cannot be
separated from that of the cognitive, neural, and phisical underpinnings of a conscious architecture.

Questions to be discussed include: What advantage does consciousness provide to biological agents? Why does the brain produce a conscious representation of cognitive processing? What are the physical underpinnings of phenomenal experience? Couldn’t be the case that conscious experience is the hallmark of a certain style of information processing? Will conscious machines be able to outperform as to autonomy, semantic understanding, dealing with unexpected events, showing personal identity, achieving satisfactory human-machine communication?

http://bicasociety.org/meetings/2014/