NeoN: Neuromorphic control for autonomous robotic navigation
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 136-142
Abstract
In this paper we describe the use of a new neuromorphic computing framework to implement the navigation system for a roaming, obstacle avoidance robot. Using a Dynamic Adaptive Neural Network Array (DANNA) structure, our TENNLab (Laboratory of Tennesseans Exploring Neural Networks) hardware/software co-design framework and evolutionary optimization (EO) as the training algorithm, we create, train, implement, and test a spiking neural network autonomous robot control system using an array of neuromorphic computing elements built on an FPGA. The simplicity and flexibility of the DANNA neuromorphic computing elements allow for sufficient scale and connectivity on a Xilinx Kintex-7 FPGA to support sensory input and motor control for a mobile robot to navigate a dynamically changing environment. We further describe how more complex capabilities can be added using the same platform, e.g. object identification and tracking.Keywords
This publication has 21 references indexed in Scilit:
- Frontiers in Neuromorphic EngineeringFrontiers in Neuroscience, 2011
- Compact hardware liquid state machines on FPGA for real-time speech recognitionNeural Networks, 2008
- From Wheels to Wings with Evolutionary Spiking CircuitsArtificial Life, 2005
- Behavior-based neuro-fuzzy controller for mobile robot navigationIEEE Transactions on Instrumentation and Measurement, 2003
- An architecture to coordinate fuzzy behaviors to control an autonomous robotFuzzy Sets and Systems, 2003
- A fuzzy controller with supervised learning assisted reinforcement learning algorithm for obstacle avoidanceIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2003
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002
- Formal spiking neuron models2002
- Neuro-Fuzzy Control for Basic Mobile Robot Behaviours2001
- Fast Sigmoidal Networks via Spiking NeuronsNeural Computation, 1997