Event-based neural computing on an autonomous mobile platform

Abstract

Abstract-Living organisms are capable of autonomously adapting to dynamically changing environments by receiving inputs from highly specialized sensory organs and elaborating them on the same parallel, power-efficient neural substrate. In this paper we present a prototype for a comprehensive integrated platform that allows replicating principles of neural information processing in real-time. Our system consists of (a) an autonomous mobile robotic platform, (b) on-board actuators and multiple (neuromorphic) sensors, and (c) the SpiNNaker computing system, a configurable neural architecture for exploration of parallel, brain-inspired models. The simulation of neurally inspired perception and reasoning algorithms is performed in real-time by distributed, low-power, low-latency event-driven computing nodes, which can be flexibly configured using C or specialized neural languages such as PyNN and Nengo. We conclude by demonstrating the platform in two experimental scenarios, exhibiting real-world closed loop behavior consisting of environmental perception, reasoning and execution of adequate motor actions.

Scalable energy-efficient, low-latency implementations of trained spiking Deep Belief Networks on SpiNNaker

“…It is an excellent fit for simulating the stereotypical neural updates and relatively sparse connections of deep networks in real-time and with minimal power consumption. Combining spiking neural networks and this hardware platform is thus an ideal fit for mobile or robotics applications [26], which require fast responses while interacting with the environment, and have only a limited power budget compared to currently popular GPU-or cloudbased solutions.…”

Pose Estimation and Map Formation with Spiking Neural Networks: towards Neuromorphic SLAM

“…Probabilistic models and graphbased methods are typically used to integrate sensory inputs and update the map of the environment, delivering successful solutions to the SLAM problem [1]. However, when computational and power resources are limited, as in mobile applications, aerial vehicles, or robotic insects, more efficient solutions are needed to enable real-time processing and long operating time for embedded SLAM systems [2], [3], [4].…”

A self-driving robot using deep convolutional neural networks on neuromorphic hardware

“…However, less work has been done embedding the neuromorphic hardware on mobile platforms. An example includes NENGO simulations embedded on SpiNNaker boards controlling mobile robots [11], [12]. Addressing the challenges of physically connecting these components, as well as creating a data pipeline for communication between the platforms is an open issue, but worth pursuing given the small size, weight and power of neuromorphic hardware.…”