An autonomous learning mobile robot using biological reward modulate STDP

Dynamic Cascade Spiking Neural Network Supervisory Controller for a Nonplanar Twelve-Rotor UAV

Unknown variables in the environment, such as wind disturbance during a flight, affect the accurate trajectory of multi-rotor UAVs. This study focuses on the intelligent supervisory neurocontrol of trajectory tracking for a nonplanar twelve-rotor UAV to address this issue. Firstly, a twelve-rotor UAV is developed with a nonplanar structure, which makes up for the defects of conventional multi-rotors with weak yaw movement. A characteristic model of the twelve-rotor UAV is devised so as to facilitate intelligent controller design without losing model information. For the purpose of achieving accurate and fast trajectory tracking and strong self-learning ability, an intelligent composite controller combining adaptive sliding-mode feedback control and dynamic cascade spiking neural network (DCSNN) supervisory feedforward control is proposed. The novel dynamic cascade network structure is constructed to better adapt to changing data and unstable environments. The weight learning algorithm and dynamic cascade structure learning algorithm work together to ensure network stability and robustness. Finally, comparative numerical simulations and twelve-rotor UAV prototype experiments verify the superior tracking control performance, even outdoors with wind disturbances.

Brain-inspired learning rules for spiking neural network-based control: a tutorial

Robotic systems rely on spatio-temporal information to solve control tasks. With advancements in deep neural networks, reinforcement learning has significantly enhanced the performance of control tasks by leveraging deep learning techniques. However, as deep neural networks grow in complexity, they consume more energy and introduce greater latency. This complexity hampers their application in robotic systems that require real-time data processing. To address this issue, spiking neural networks, which emulate the biological brain by transmitting spatio-temporal information through spikes, have been developed alongside neuromorphic hardware that supports their operation. This paper reviews brain-inspired learning rules and examines the application of spiking neural networks in control tasks. We begin by exploring the features and implementations of biologically plausible spike-timing-dependent plasticity. Subsequently, we investigate the integration of a global third factor with spike-timing-dependent plasticity and its utilization and enhancements in both theoretical and applied research. We also discuss a method for locally applying a third factor that sophisticatedly modifies each synaptic weight through weight-based backpropagation. Finally, we review studies utilizing these learning rules to solve control tasks using spiking neural networks.

Implementation of Field-Programmable Gate Array Platform for Object Classification Tasks Using Spike-Based Backpropagated Deep Convolutional Spiking Neural Networks

This paper investigates the performance of deep convolutional spiking neural networks (DCSNNs) trained using spike-based backpropagation techniques. Specifically, the study examined temporal spike sequence learning via backpropagation (TSSL-BP) and surrogate gradient descent via backpropagation (SGD-BP) as effective techniques for training DCSNNs on the field programmable gate array (FPGA) platform for object classification tasks. The primary objective of this experimental study was twofold: (i) to determine the most effective backpropagation technique, TSSL-BP or SGD-BP, for deeper spiking neural networks (SNNs) with convolution filters across various datasets; and (ii) to assess the feasibility of deploying DCSNNs trained using backpropagation techniques on low-power FPGA for inference, considering potential configuration adjustments and power requirements. The aforementioned objectives will assist in informing researchers and companies in this field regarding the limitations and unique perspectives of deploying DCSNNs on low-power FPGA devices. The study contributions have three main aspects: (i) the design of a low-power FPGA board featuring a deployable DCSNN chip suitable for object classification tasks; (ii) the inference of TSSL-BP and SGD-BP models with novel network architectures on the FPGA board for object classification tasks; and (iii) a comparative evaluation of the selected spike-based backpropagation techniques and the object classification performance of DCSNNs across multiple metrics using both public (MNIST, CIFAR10, KITTI) and private (INHA_ADAS, INHA_KLP) datasets.

Bio-Inspired Autonomous Learning Algorithm With Application to Mobile Robot Obstacle Avoidance

Spiking Neural Networks (SNNs) are often considered the third generation of Artificial Neural Networks (ANNs), owing to their high information processing capability and the accurate simulation of biological neural network behaviors. Though the research for SNNs has been quite active in recent years, there are still some challenges to applying SNNs to various potential applications, especially for robot control. In this study, a biologically inspired autonomous learning algorithm based on reward modulated spike-timing-dependent plasticity is proposed, where a novel rewarding generation mechanism is used to generate the reward signals for both learning and decision-making processes. The proposed learning algorithm is evaluated by a mobile robot obstacle avoidance task and experimental results show that the mobile robot with the proposed algorithm exhibits a good learning ability. The robot can successfully avoid obstacles in the environment after some learning trials. This provides an alternative method to design and apply the bio-inspired robot with autonomous learning capability in the typical robotic task scenario.

R-STDP Spiking Neural Network Architecture for Motion Control on a Changing Friction Joint Robotic Arm

Neuromorphic computing is a recent class of brain-inspired high-performance computer platforms and algorithms involving biologically-inspired models adopting hardware implementation in integrated circuits. The neuromorphic computing applications have provoked the rise of highly connected neurons and synapses in analog circuit systems that can be used to solve today's challenging machine learning problems. In conjunction with biologically plausible learning rules, such as the Hebbian learning and memristive devices, biologically-inspired spiking neural networks are considered the next-generation neuromorphic hardware construction blocks that will enable the deployment of new analog in situ learning capable and energetic efficient brain-like devices. These features are envisioned for modern mobile robotic implementations, currently challenging to overcome the pervasive von Neumann computer architecture. This study proposes a new neural architecture using the spike-time-dependent plasticity learning method and step-forward encoding algorithm for a self tuning neural control of motion in a joint robotic arm subjected to dynamic modifications. Simulations were conducted to demonstrate the proposed neural architecture's feasibility as the network successfully compensates for changing dynamics at each simulation run.