Many animals meander in environments and avoid collisions. How the underlying neuronal machinery can yield robust behaviour in a variety of environments remains unclear. In the fly brain, motion-sensitive neurons indicate the presence of nearby objects and directional cues are integrated within an area known as the central complex. Such neuronal machinery, in contrast with the traditional stream-based approach to signal processing, uses an event-based approach, with events occurring when changes are sensed by the animal. Contrary to von Neumann computing architectures, event-based neuromorphic hardware is designed to process information in an asynchronous and distributed manner. Inspired by the fly brain, we model, for the first time, a neuromorphic closed-loop system mimicking essential behaviours observed in flying insects, such as meandering in clutter and gap crossing, which are highly relevant for autonomous vehicles. We implemented our system both in software and on neuromorphic hardware. While moving through an environment, our agent perceives changes in its surroundings and uses this information for collision avoidance. The agent's manoeuvres result from a closed action-perception loop implementing probabilistic decision-making processes. This loop-closure is thought to have driven the development of neural circuitry in biological agents since the Cambrian explosion. In the fundamental quest to understand neural computation in artificial agents, we come closer to understanding and modelling biological intelligence by closing the loop also in neuromorphic systems. As a closed-loop system, our system deepens our understanding of processing in neural networks and computations in biological and artificial systems. With these investigations, we aim to set the foundations for neuromorphic intelligence in the future, moving towards leveraging the full potential of neuromorphic systems.
Energy-Aware Spike Budgeting for Continual Learning in Spiking Neural Networks for Neuromorphic Vision
Dept. of Electrical and Electronics Engineering, University of Liberal Arts Bangladesh（乌拉尔大学 bangladesh 电子与电气工程系）；Dept. of Electrical Engineering, Pennsylvania State University（宾夕法尼亚州立大学电气工程系）
A neuromorphic model of the insect visual system for natural image processing
School of Natural Sciences, Macquarie University（麦考瑞大学自然科学学院）；QUT Centre for Robotics, Queensland University of Technology（昆士兰科技大学机器人中心）；College of Medicine and Public Health, Flinders University（弗林德斯大学医学院与公共卫生学院）
Context-aware Sparse Spatiotemporal Learning for Event-based Vision
Faculty of Aerospace Engineering, Delft University of Technology（代尔夫特理工大学航空航天工程学院）；Department of Advanced Computing Sciences, Maastricht University（马斯特里赫特大学先进计算科学系）
Parameter Optimization and Learning in a Spiking Neural Network for UAV Obstacle Avoidance targeting Neuromorphic Processors
Lobula Giant Movement Detector（LGMD）是蝗虫的一个识别神经元，它可以检测到隐约可见的物体并触发昆虫的逃跑反应。理解导致这些快速和鲁棒响应的神经原理和网络结构可以促进机器人应用的有效避障策略的设计。在这里，我们提出了一个神经形态脉冲神经网络模型的LGMD驱动的神经形态动态视觉传感器（DVS），它结合了尖峰频率适应和突触可塑性机制，并可以映射到现有的神经形态处理器芯片的输出。然而，由于该模型的参数范围很广，并且用于实现该模型的混合信号模数电路受到变化性和噪声的影响，因此有必要优化参数以产生鲁棒且可靠的响应。在这里，我们建议使用差分进化（DE）和贝叶斯优化（BO）技术来优化参数空间，并研究使用自适应差分进化（SADE），以改善困难的DE技术找到合适的输入参数。我们量化的性能提出的方法与应用于模型的不同的优化器的全面比较，并证明了使用从安装在无人机上的DVS传感器的记录所提出的方法的有效性。
Differential Evolution and Bayesian Optimisation for Hyper-Parameter Selection in Mixed-Signal Neuromorphic Circuits Applied to UAV Obstacle Avoidance
University of Queensland（昆士兰大学）；CSIRO（联邦科学与工业研究组织）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Institute of Neuroinformatics（神经信息学研究所）
Lobula Giant Movement Detector（LGMD）是蝗虫的一个识别神经元，它可以检测到隐约可见的物体并触发其逃跑反应。理解导致这些快速和鲁棒响应的神经原理和网络可以导致在机器人应用中设计高效的避障策略。在这里，我们提出了一个神经形态的脉冲神经网络模型的LGMD驱动的神经形态的动态视觉传感器（DVS），它已被优化，以产生强大的和可靠的响应，在面对的限制和可变性的混合信号模拟-数字电路的输出。由于该LGMD模型参数较多，我们采用差分进化算法对其参数空间进行优化。我们还研究了使用自适应差分进化（SADE）已被证明，以改善困难，找到合适的输入参数DE。我们探讨使用两种生物学机制：突触可塑性和膜适应性的LGMD。我们应用DE和SADE找到最适合无人机（UAV）避障系统的参数，并显示它如何优于用于比较的最先进的贝叶斯优化。
