Adaptive motor control and learning in a spiking neural network realised on a mixed-signal neuromorphic processor
Autor: | Ning Qiao, Raphaela Kreiser, Julien N. P. Martel, Yulia Sandamirskaya, Sebastian Glatz |
---|---|
Přispěvatelé: | University of Zurich |
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
FOS: Computer and information sciences
Computer Science::Neural and Evolutionary Computation Computer Science - Emerging Technologies 2207 Control and Systems Engineering 1702 Artificial Intelligence 02 engineering and technology Computer Science::Robotics Computer Science::Emerging Technologies Control theory 0202 electrical engineering electronic engineering information engineering Sociology Neural and Evolutionary Computing (cs.NE) 10194 Institute of Neuroinformatics Spiking neural network Artificial neural network Quantitative Biology::Neurons and Cognition business.industry 2208 Electrical and Electronic Engineering Computer Science - Neural and Evolutionary Computing Motor control Mixed-signal integrated circuit 020202 computer hardware & architecture 1712 Software Emerging Technologies (cs.ET) Neuromorphic engineering Proof of concept Robot 570 Life sciences biology 020201 artificial intelligence & image processing business Computer hardware |
Zdroj: | ICRA |
Popis: | Neuromorphic computing is a new paradigm for design of both the computing hardware and algorithms inspired by biological neural networks. The event-based nature and the inherent parallelism make neuromorphic computing a promising paradigm for building efficient neural network based architectures for control of fast and agile robots. In this paper, we present a spiking neural network architecture that uses sensory feedback to control rotational velocity of a robotic vehicle. When the velocity reaches the target value, the mapping from the target velocity of the vehicle to the correct motor command, both represented in the spiking neural network on the neuromorphic device, is autonomously stored on the device using on-chip plastic synaptic weights. We validate the controller using a wheel motor of a miniature mobile vehicle and inertia measurement unit as the sensory feedback and demonstrate online learning of a simple 'inverse model' in a two-layer spiking neural network on the neuromorphic chip. The prototype neuromorphic device that features 256 spiking neurons allows us to realise a simple proof of concept architecture for the purely neuromorphic motor control and learning. The architecture can be easily scaled-up if a larger neuromorphic device is available. Comment: 6+1 pages, 4 figures, will appear in one of the Robotics conferences |
Databáze: | OpenAIRE |
Externí odkaz: |