Abstract
This paper describes the design and modus of operation of a neuromorphic robotic platform based on SpiNNaker, and its implementation on the goalkeeper task. The robotic system utilises an address event representation (AER) type of camera (dynamic vision sensor (DVS)) to capture features of a moving ball, and a servo motor to position the goalkeeper to intercept the incoming ball. At the backbone of the system is a microcontroller (Arduino Due) which facilitates communication and control between different robot parts. A spiking neuronal network (SNN), which is running on SpiNNaker, predicts the location of arrival of the moving ball and decides where to place the goalkeeper. In our setup, the maximum data transmission speed of the closed-loop system is approximately 3000 packets per second for both uplink and downlink, and the robot can intercept balls whose speed is up to 1 m/s starting from the distance of about 0.8 m. The interception accuracy is up to 85%, the response latency is 6.5 ms and the maximum power consumption is 7.15 W. This is better than previous implementations based on PC. Here, a simplified version of an SNN has been developed for the ‘interception of a moving object’ task, for the purpose of demonstrating the platform, however a generalised SNN for this problem is a nontrivial problem. A demo video of the robot goalie is available on YouTube.
Highlights
IntroductionA robotic goalkeeper based on the DVS128, designed by Delbruck and Lang [23], achieves 3 ms reaction time
Neuromorphic engineering is inspired by the human neural system to address abstraction and automate human-type activities [1]
This system is using a PC to process data, which is reducing its mobility and power efficiency, and it cannot capture rich non-linear structures of visual input since neuronal networks are not applied in the system
Summary
A robotic goalkeeper based on the DVS128, designed by Delbruck and Lang [23], achieves 3 ms reaction time This system is using a PC to process data, which is reducing its mobility and power efficiency, and it cannot capture rich non-linear structures of visual input since neuronal networks are not applied in the system. The interface developed in this paper uses a single microcontroller to establish low-latency communication between DVS, SpiNNaker and a servo motor It is the first neuromorphic interface based on SpiNNaker that supports a servo to precisely control the position of the robotic arm. It does not require a second chip to convert the communication protocol between microcontroller and SpiNNaker, which reduces power consumption. This neuromorphic system offers a platform for many other applications at low-cost and simple for further development
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
