Virtual neurorobotics (VNR) to accelerate development of plausible neuromorphic brain architectures
- 1
Department of Medicine and Program in Biomedical Engineering, University of Nevada, Reno, USA
- 2
Department of Computer Science and Engineering, University of Nevada, Reno, USA
Traditional research in artificial intelligence and machine learning has viewed the brain as a specially adapted information-processing system. More recently the field of social robotics has been advanced to capture the important dynamics of human cognition and interaction. An overarching societal goal of this research is to incorporate the resultant knowledge about intelligence into technology for prosthetic, assistive, security, and decision support applications. However, despite many decades of investment in learning and classification systems, this paradigm has yet to yield truly “intelligent” systems. For this reason, many investigators are now attempting to incorporate more realistic neuromorphic properties into machine learning systems, encouraged by over two decades of neuroscience research that has provided parameters that characterize the brain's interdependent genomic, proteomic, metabolomic, anatomic, and electrophysiological networks. Given the complexity of neural systems, developing tenable models to capture the essence of natural intelligence for real-time application requires that we discriminate features underlying information processing and intrinsic motivation from those reflecting biological constraints (such as maintaining structural integrity and transporting metabolic products). We propose herein a conceptual framework and an iterative method of virtual neurorobotics (VNR) intended to rapidly forward-engineer and test progressively more complex putative neuromorphic brain prototypes for their ability to support intrinsically intelligent, intentional interaction with humans. The VNR system is based on the viewpoint that a truly intelligent system must be driven by emotion rather than programmed tasking, incorporating intrinsic motivation and intentionality. We report pilot results of a closed-loop, real-time interactive VNR system with a spiking neural brain, and provide a video demonstration as online supplemental material.
Keywords:
neurorobotic architecture, human robot interface, virtual reality, artificial intelligence, social robotics, epigenetic robotics, reinforcement learning, neocortex, mesocircuit
Citation:
Philip H. Goodman, Sermsak Buntha, Quan Zou and Sergiu-Mihai Dascalu (2007). Virtual neurorobotics (VNR) to accelerate development of plausible neuromorphic brain architectures. Front. Neurorobot. 1:1. doi: 10.3389/neuro.12/001.2007
Received: 3 September 2007;
Paper pending published: 6 October 2007;
Accepted: 9 October 2007;
Published online: 2 November 2007.
Edited by:
Frederic Kaplan, Ecole Polytechnique Federale De Lausanne, Switzerland
Reviewed by:
Angelo Cangelosi, University of Plymouth, United Kingdom
Jeffrey L. Krichmar, The Neurosciences Institute, San Diego, United States of America
Felix Schürmann, Ecole Polytechnique Federale De Lausanne, Switzerland
Copyright:
© 2007 Goodman, Buntha, Zou, Dascalu. This is an open-access article subject to an exclusive license agreement between the authors and the Frontiers Research Foundation, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are credited.
*Correspondence:
Philip H. Goodman, Department of Medicine and Program in Biomedical Engineering, University of Nevada, Reno, USA. e-mail: goodman@unr.edu