当前位置: X-MOL 学术arXiv.cs.ET › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Closed-loop spiking control on a neuromorphic processor implemented on the iCub
arXiv - CS - Emerging Technologies Pub Date : 2020-09-01 , DOI: arxiv-2009.09081
Jingyue Zhao, Nicoletta Risi, Marco Monforte, Chiara Bartolozzi, Giacomo Indiveri, and Elisa Donati

Despite neuromorphic engineering promises the deployment of low latency, adaptive and low power systems that can lead to the design of truly autonomous artificial agents, the development of a fully neuromorphic artificial agent is still missing. While neuromorphic sensing and perception, as well as decision-making systems, are now mature, the control and actuation part is lagging behind. In this paper, we present a closed-loop motor controller implemented on mixed-signal analog-digital neuromorphic hardware using a spiking neural network. The network performs a proportional control action by encoding target, feedback, and error signals using a spiking relational network. It continuously calculates the error through a connectivity pattern, which relates the three variables by means of feed-forward connections. Recurrent connections within each population are used to speed up the convergence, decrease the effect of mismatch and improve selectivity. The neuromorphic motor controller is interfaced with the iCub robot simulator. We tested our spiking P controller in a single joint control task, specifically for the robot head yaw. The spiking controller sends the target positions, reads the motor state from its encoder, and sends back the motor commands to the joint. The performance of the spiking controller is tested in a step response experiment and in a target pursuit task. In this work, we optimize the network structure to make it more robust to noisy inputs and device mismatch, which leads to better control performances.

中文翻译:

在 iCub 上实现的神经形态处理器上的闭环尖峰控制

尽管神经形态工程有望部署低延迟、自适应和低功耗系统,从而设计出真正自主的人工智能体,但仍然缺乏完全神经形态人工智能体的开发。虽然神经形态感知和感知以及决策系统现在已经成熟,但控制和驱动部分却落后了。在本文中,我们提出了一种使用尖峰神经网络在混合信号模拟-数字神经形态硬件上实现的闭环电机控制器。该网络通过使用尖峰关系网络对目标、反馈和误差信号进行编码来执行比例控制动作。它通过连接模式不断计算误差,该模式通过前馈连接将三个变量联系起来。每个种群内的循环连接用于加速收敛,减少不匹配的影响并提高选择性。神经形态电机控制器与 iCub 机器人模拟器连接。我们在单个关节控制任务中测试了我们的尖峰 P 控制器,特别是针对机器人头部偏航。尖峰控制器发送目标位置,从其编码器读取电机状态,并将电机命令发送回关节。在阶跃响应实验和目标追踪任务中测试了尖峰控制器的性能。在这项工作中,我们优化了网络结构,使其对噪声输入和设备失配更加鲁棒,从而获得更好的控制性能。神经形态电机控制器与 iCub 机器人模拟器连接。我们在单个关节控制任务中测试了我们的尖峰 P 控制器,特别是机器人头部偏航。尖峰控制器发送目标位置,从其编码器读取电机状态,并将电机命令发送回关节。在阶跃响应实验和目标追踪任务中测试了尖峰控制器的性能。在这项工作中,我们优化了网络结构,使其对噪声输入和设备失配更加鲁棒,从而获得更好的控制性能。神经形态电机控制器与 iCub 机器人模拟器连接。我们在单个关节控制任务中测试了我们的尖峰 P 控制器,特别是针对机器人头部偏航。尖峰控制器发送目标位置,从其编码器读取电机状态,并将电机命令发送回关节。在阶跃响应实验和目标追踪任务中测试了尖峰控制器的性能。在这项工作中,我们优化了网络结构,使其对噪声输入和设备失配更加鲁棒,从而获得更好的控制性能。并将运动命令发送回关节。在阶跃响应实验和目标追踪任务中测试了尖峰控制器的性能。在这项工作中,我们优化了网络结构,使其对噪声输入和设备失配更加鲁棒,从而获得更好的控制性能。并将运动命令发送回关节。在阶跃响应实验和目标追踪任务中测试了尖峰控制器的性能。在这项工作中,我们优化了网络结构,使其对噪声输入和设备失配更加鲁棒,从而获得更好的控制性能。
更新日期:2020-09-22
down
wechat
bug