An official website of the United States government
One developing approach for robotic control is the use of networks of dynamic neurons connected with conductance-based synapses, also known as Synthetic Nervous Systems (SNS). These networks are often developed using cyclic topologies and heterogeneous mixtures of spiking and non-spiking neurons, which is a difficult proposition for existing neural simulation software. Most solutions apply to either one of two extremes, the detailed multi-compartment neural models in small networks, and the large-scale networks of greatly simplified neural models. In this work, we present our open-source Python package SNS-Toolbox, which is capable of simulating hundreds to thousands of spiking and non-spiking neurons in real-time or faster on consumer-grade computer hardware. We describe the neural and synaptic models supported by SNS-Toolbox, and provide performance on multiple software and hardware backends, including GPUs and embedded computing platforms. We also showcase two examples using the software, one for controlling a simulated limb with muscles in the physics simulator Mujoco, and another for a mobile robot using ROS. We hope that the availability of this software will reduce the barrier to entry when designing SNS networks, and will increase the prevalence of SNS networks in the field of robotic control.
more »
« less
SNS-Toolbox: A Suite of Tools for the Design, Optimization, and Implementation of Synthetic Nervous Systems
In this dissertation I present SNS-Toolbox, an open-source software package for the design and simulation of networks of biologically inspired neurons and synapses, also known as synthetic nervous systems (SNS). SNS-Toolbox allows SNS networks to be designed using a lightweight Python API, simulated in real-time on consumer computer hardware, and executed onboard physical robotic systems. I also present a companion package to SNS-Toolbox which allows simulation and training of large SNS networks using gradient backpropagation. This software is released under an open-source license with online documentation for ease of use, and has been disseminated to other researchers for their use. As a demonstration, I use SNS-Toolbox to implement a stereo visual motion detector, based on circuitry present within the Drosophila melanogaster (fruit fly) optic lobe. This network analyzes local motion at each point within a visual field, and returns an estimate of global motion when subjected to grating stimuli. Finally I showcase the design of FlyWheel, a robotic benchmark for studying models of insect vision and applying SNS networks to physical hardware. This body of work marks the first tool which is capable of simulating SNS networks with hundreds to thousands of neurons and synaptic connections in real-time or faster, optimize networks with chemical reversal potentials using gradient backpropagation, and interface these networks for control of external systems.
more »
« less
- Award ID(s):
- 2015317
- PAR ID:
- 10627505
- Publisher / Repository:
- Ohiolink
- Date Published:
- Format(s):
- Medium: X
- Institution:
- Case Western Reserve University
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We introduce SNS-Toolbox, a Python software package for the design and simulation of networks of conductance-based neurons and synapses, also called Synthetic Nervous Systems (SNS). SNS-Toolbox implements non-spiking and spiking neurons in multiple software backends, and is capable of simulating networks with thousands of neurons in real-time. We benchmark the toolbox simulation speed across multiple network sizes, characterize upper limits on network size in various scenarios, and showcase the design of a two-layer convolutional network inspired by circuits within the Drosophila melanogaster optic lobe. SNSToolbox, as well as the code to generate all of the figures in this work, is located at https://github.com/wnourse05/SNS-Toolbox.more » « less
-
Autonomous drones (UAVs) have rapidly grown in popularity due to their form factor, agility, and ability to operate in harsh or hostile environments. Drone systems come in various form factors and configurations and operate under tight physical parameters. Further, it has been a significant challenge for architects and researchers to develop optimal drone designs as open-source simulation frameworks either lack the necessary capabilities to simulate a full drone flight stack or they are extremely tedious to setup with little or no maintenance or support. In this paper, we develop and present UniUAVSim, our fully open-source co-simulation framework capable of running software-in-the-loop (SITL) and hardware-in-the-loop (HITL) simulations concurrently. The paper also provides insights into the abstraction of a drone flight stack and details how these abstractions aid in creating a simulation framework which can accurately provide an optimal drone design given physical parameters and constraints. The framework was validated with real-world hardware and is available to the research community to aid in future architecture research for autonomous systems.more » « less
-
Asynchronous event-driven computation and communication using spikes facilitate the realization of spiking neural networks (SNN) to be massively parallel, extremely energy efficient and highly robust on specialized neuromorphic hardware. However, the lack of a unified robust learning algorithm limits the SNN to shallow networks with low accuracies. Artificial neural networks (ANN), however, have the backpropagation algorithm which can utilize gradient descent to train networks which are locally robust universal function approximators. But backpropagation algorithm is neither biologically plausible nor neuromorphic implementation friendly because it requires: 1) separate backward and forward passes, 2) differentiable neurons, 3) high-precision propagated errors, 4) coherent copy of weight matrices at feedforward weights and the backward pass, and 5) non-local weight update. Thus, we propose an approximation of the backpropagation algorithm completely with spiking neurons and extend it to a local weight update rule which resembles a biologically plausible learning rule spike-timing-dependent plasticity (STDP). This will enable error propagation through spiking neurons for a more biologically plausible and neuromorphic implementation friendly backpropagation algorithm for SNNs. We test the proposed algorithm on various traditional and non-traditional benchmarks with competitive results.more » « less
-
The growing number of applications in Cyber-Physical Systems (CPS) involving different types of robots while maintaining interoperability and trust is an ongoing challenge faced by traditional centralized systems. This paper presents what is, to the best of our knowledge, the first integration of the Robotic Operating System (ROS) with the Ethereum blockchain using physical robots. We implement a specialized smart contract framework called “Swarm Contracts” that rely on blockchain technology in real-world applications for robotic agents with human interaction to perform collaborative tasks while ensuring trust by motivating the agents with incentives using a token economy with a self-governing structure. The use of open-source technologies, including robot hardware platforms such as TurtleBot3, Universal Robot arm, and ROS, enables the ability to connect a wide range of robot types to the framework we propose. Going beyond simulations, we demonstrate the robustness of the proposed system in real-world conditions with actual hardware robots.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Dissertation:
- The DOI is not currently available.
