Stewart Terrence C, Kleinhans Ashley, Mundy Andrew, Conradt Jörg
Centre for Theoretical Neuroscience, University of Waterloo , Waterloo, ON , Canada.
Mobile Intelligent Autonomous Systems Group, Council for Scientific and Industrial Research , Pretoria , South Africa.
Front Neurorobot. 2016 Feb 15;10:1. doi: 10.3389/fnbot.2016.00001. eCollection 2016.
We demonstrate a hybrid neuromorphic learning paradigm that learns complex sensorimotor mappings based on a small set of hard-coded reflex behaviors. A mobile robot is first controlled by a basic set of reflexive hand-designed behaviors. All sensor data is provided via a spike-based silicon retina camera (eDVS), and all control is implemented via spiking neurons simulated on neuromorphic hardware (SpiNNaker). Given this control system, the robot is capable of simple obstacle avoidance and random exploration. To train the robot to perform more complex tasks, we observe the robot and find instances where the robot accidentally performs the desired action. Data recorded from the robot during these times is then used to update the neural control system, increasing the likelihood of the robot performing that task in the future, given a similar sensor state. As an example application of this general-purpose method of training, we demonstrate the robot learning to respond to novel sensory stimuli (a mirror) by turning right if it is present at an intersection, and otherwise turning left. In general, this system can learn arbitrary relations between sensory input and motor behavior.
我们展示了一种混合神经形态学习范式，该范式基于一小组硬编码反射行为来学习复杂的感觉运动映射。首先，一个移动机器人由一组基本的手动设计的反射行为控制。所有传感器数据通过基于脉冲的硅视网膜相机（eDVS）提供，所有控制通过在神经形态硬件（SpiNNaker）上模拟的脉冲神经元实现。在这个控制系统下，机器人能够进行简单的避障和随机探索。为了训练机器人执行更复杂的任务，我们观察机器人并找到机器人意外执行所需动作的实例。然后，在这些时候从机器人记录的数据用于更新神经控制系统，增加机器人在未来给定类似传感器状态时执行该任务的可能性。作为这种通用训练方法的一个示例应用，我们展示了机器人学习对新的感官刺激（一面镜子）做出反应：如果在十字路口出现镜子，机器人向右转，否则向左转。一般来说，这个系统可以学习感觉输入和运动行为之间的任意关系。
