NeoN: Neuromorphic control for autonomous robotic navigation

Mitchell, J. Parker; Bruer, Grant; Dean, Mark E.; Plank, James S.; Rose, Garrett S.; Schuman, Catherine D.

doi:10.1109/iris.2017.8250111

Cited by 28 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas in our analysis, the spike representation resulted in a data reduction of 25% down from the original size and yet the effects of the peripheral dynamics were still detectable. Research on neuromorphic signal processing based on spikes [103,104] has a demonstrated potential for applications in autonomous navigation with respect to representing sensor input and carry-ing out motor control of a robot [105]. Furthermore, neuromorphic signal representations and processing have been used in conjunction with vision sensors to solve the challenges of autonomous navigation and obstacle avoidance in robots in cluttered environments [106].…”

Section: Discussionmentioning

confidence: 99%

“…This combination of hardware and software can build upon existing efforts which have implemented spike based signal processing [103,104] in autonomous navigation of robots. Research has demonstrated that neuromorphic signal processing can be utilized in autonomous navigation applications to represent sensor input and can that such sensory input can be used to control a robot [105].…”

Section: Discussion Of Findingsmentioning

confidence: 99%

See 1 more Smart Citation

Biomimetic detection of dynamic signatures in foliage echoes

Bhardwaj¹,

Khyam²,

Müller³

2021

Bioinspir. Biomim.

View full text Add to dashboard Cite

I would like to thank Dr. Rolf Müller for giving me the opportunity to pursue this research. I appreciate immensely his trust and guidance throughout my time working on this research.His leadership, approach to problem-solving, attention to detail, and seemingly limitless wide-ranging knowledge of science, are the reference points I will always aspire to reach in my career. I would also like to thank my committee members, Dr. Alexander Leonessa and Dr. Michael Roan, for their mentorship and technical advice. I wish to acknowledge Dr.Mohammad Omar Khyam and David Alexandre, who contributed to a significant part of this research. I'd also like to acknowledge Liujun Zhang, for his help in collecting the data for this project, and for his friendship. I'd also like to thank the other grad students in the lab

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussion Of Findingsmentioning

confidence: 99%

Biomimetic detection of dynamic signatures in foliage echoes

Bhardwaj¹,

Khyam²,

Müller³

2021

Bioinspir. Biomim.

View full text Add to dashboard Cite

show abstract

“…For the applications, we tested Hierarchical-PABO on both control and classification tasks. Pole-balance (Wieland, 1991 ; Gomez et al, 2006 ), and RoboNav (Mitchell et al, 2017 ) were the two selected control applications. Pole-balance is a control benchmark in engineering which involves a pole connected to a cart through a joint that allows single axis movement.…”

Section: Methodology and Experimental Setupmentioning

confidence: 99%

“…The goal of this control application is to keep the pole from falling by moving the cart either direction. RoboNav is an autonomous navigation system for robotic applications and is meant to be deployed on a specific robot (Mitchell et al, 2017 ). We also used the Iris (Dua and Graff, 2017 ) and Radio (Reynolds et al, 2018 ) datasets for classification tasks.…”

Section: Methodology and Experimental Setupmentioning

confidence: 99%

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design

et al. 2020

Self Cite

View full text Add to dashboard Cite

In resource-constrained environments, such as low-power edge devices and smart sensors, deploying a fast, compact, and accurate intelligent system with minimum energy is indispensable. Embedding intelligence can be achieved using neural networks on neuromorphic hardware. Designing such networks would require determining several inherent hyperparameters. A key challenge is to find the optimum set of hyperparameters that might belong to the input/output encoding modules, the neural network itself, the application, or the underlying hardware. In this work, we present a hierarchical pseudo agent-based multi-objective Bayesian hyperparameter optimization framework (both software and hardware) that not only maximizes the performance of the network, but also minimizes the energy and area requirements of the corresponding neuromorphic hardware. We validate performance of our approach (in terms of accuracy and computation speed) on several control and classification applications on digital and mixed-signal (memristor-based) neural accelerators. We show that the optimum set of hyperparameters might drastically improve the performance of one application (i.e., 52–71% for Pole-Balance), while having minimum effect on another (i.e., 50–53% for RoboNav). In addition, we demonstrate resiliency of different input/output encoding, training neural network, or the underlying accelerator modules in a neuromorphic system to the changes of the hyperparameters.

show abstract

“…The results show that the vehicles with different connections between front sensors and rear wheels exhibit entirely different behaviors under the same stimulus. This famous thought experiment has inspired the development of autonomous robots that are capable of avoiding obstacles and path tracking as well as navigation . In spite of much success in achieving autonomous robots based on this vehicle model, the processors of the smart robots are still based on von Neumann architectures .…”

Section: Introductionmentioning

confidence: 99%

A Braitenberg Vehicle Based on Memristive Neuromorphic Circuits

Yang

Wang

et al. 2019

Advanced Intelligent Systems

View full text Add to dashboard Cite

The Braitenberg vehicle as a simple conceptual model to characterize the response behaviors of animals or insects under a stimulus is widely used to develop autonomous vehicles able to adapt to the varying environments. Considerable effort has been devoted to building neuromorphic processors with the software in the vehicles; however, there has been no demonstration of Braitenberg vehicle with neuromorphic hardware so far. Herein, a Braitenberg vehicle with simple memristive neuromorphic circuits is built for the first time. This vehicle exhibits adaptive behaviors in the supervised learning process and is eventually trained to conduct the task of tracking path. Moreover, the memristive circuit in the vehicle demonstrates a very short response latency (%56 ns) to input sensory information. Herein, an alternative promising solution to build selfadaptive robots and pave the way for the realization of autonomous robots based on memristive neuromorphic circuits is offered.

show abstract

NeoN: Neuromorphic control for autonomous robotic navigation

Cited by 28 publications

References 21 publications

Biomimetic detection of dynamic signatures in foliage echoes

Biomimetic detection of dynamic signatures in foliage echoes

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design

A Braitenberg Vehicle Based on Memristive Neuromorphic Circuits

Contact Info

Product

Resources

About