A complete neuromorphic solution to outdoor navigation and path planning

Recent developments in neuromorphic engineering have enabled low-powered processing and sensing in robotics, leading to more efficient brain-like computation for many robotic tasks such as motion planning and navigation. However, present experiments in neuromorphic robotic systems have mostly been performed under controlled indoor settings, often with unlimited power supply. While this may be suitable for many applications, these algorithms often fail in outdoor dynamic environments that could benefit the most from the low size, weight, and power of neuromorphic devices. We present the current challenges of outdoor robotics, how current neuromorphic solutions can address these problems, our current approaches to the task, and what further needs to be achieved to create a complete neuromorphic solution to outdoor navigation and path planning.

[1]  Lydia E. Kavraki,et al.  Motion Planning , 2011, Springer Handbook of Robotics, 2nd Ed..

[2]  R. Douglas Fields,et al.  A new mechanism of nervous system plasticity: activity-dependent myelination , 2015, Nature Reviews Neuroscience.

[3]  Sebastian Thrun,et al.  Adaptive Road Following using Self-Supervised Learning and Reverse Optical Flow , 2005, Robotics: Science and Systems.

[4]  Joel G. Morillon,et al.  Robust perception algorithms for road and track autonomous following , 2004, SPIE Defense + Commercial Sensing.

[5]  Hissam Tawfik,et al.  Path planning in construction sites: performance evaluation of the Dijkstra, A*, and GA search algorithms , 2002, Adv. Eng. Informatics.

[6]  S. LaValle,et al.  Motion Planning , 2008, Springer Handbook of Robotics.

[7]  Andreas G. Andreou,et al.  Path planning on the TrueNorth neurosynaptic system , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[8]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[9]  Narayan Srinivasa,et al.  Energy-Efficient Neuron, Synapse and STDP Integrated Circuits , 2012, IEEE Transactions on Biomedical Circuits and Systems.

[10]  Jörg Conradt,et al.  Trainable sensorimotor mapping in a neuromorphic robot , 2015, Robotics Auton. Syst..

[11]  Timothy K. Horiuchi,et al.  Path planning by spike propagation , 2015, 2015 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[12]  Andrew S. Cassidy,et al.  Convolutional networks for fast, energy-efficient neuromorphic computing , 2016, Proceedings of the National Academy of Sciences.

[13]  Helmut Alt,et al.  Computing the Fréchet distance between two polygonal curves , 1995, Int. J. Comput. Geom. Appl..

[14]  Gert Cauwenberghs,et al.  Neuromorphic Silicon Neuron Circuits , 2011, Front. Neurosci.

[15]  Jeffrey L. Krichmar,et al.  Smartphone Based Robotics : Powerful , Flexible and Inexpensive Robots for Hobbyists , Educators , Students and Researchers , 2013 .

[16]  Scott Koziol,et al.  A Neuromorphic Approach to Path Planning Using a Reconfigurable Neuron Array IC , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[17]  Jeffrey L. Krichmar,et al.  Adaptive Robot Path Planning Using a Spiking Neuron Algorithm With Axonal Delays , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[18]  Jean Ponce,et al.  General Road Detection From a Single Image , 2010, IEEE Transactions on Image Processing.

[19]  Jeffrey L. Krichmar,et al.  Path planning using a spiking neuron algorithm with axonal delays , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[20]  Er. Waghoo Parvez,et al.  Path planning in construction sites : performance evaluation of the Dijkstra , A * , and GA search algorithms , 2013 .

[21]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[22]  Michaël Soulignac,et al.  Feasible and Optimal Path Planning in Strong Current Fields , 2011, IEEE Transactions on Robotics.

[23]  Jeffrey L. Krichmar,et al.  A self-driving robot using deep convolutional neural networks on neuromorphic hardware , 2016, 2017 International Joint Conference on Neural Networks (IJCNN).