用脉冲神经网络让机器人在毫秒级反应中学会打冰球
Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
- 用随机连接的脉冲神经元+局部学习规则，实现事件驱动的快速训练
- 仅需少量试错就能在高速冰球任务中成功击打，实现实时学习
- 适合需要持续学习的智能机器人系统，如自动驾驶与人机交互
冰球运动要求在极高球速下做出瞬时决策，本文通过部署于混合信号模拟/数字类脑处理器上的紧凑脉冲神经网络解决该问题。通过软硬件协同设计，系统在极少数试验内即通过强化学习实现成功击球。网络利用固定随机连接以捕捉任务的时间结构，并在读出层采用局部e-prop学习规则，利用事件驱动活动实现快速高效学习。整个系统由计算机与类脑芯片构成闭环，在线实现实时学习，为脉冲神经网络在机器人自主系统中的实用化训练提供可行路径。该工作将神经科学启发的硬件与真实机器人控制结合，证明脑启发方法可应对高速交互任务，并支持智能机器人的持续学习能力。
原文摘要 · Abstract (English)
Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning algorithms, we train the system to achieve successful puck interactions through reinforcement learning in a remarkably small number of trials. The network leverages fixed random connectivity to capture the task's temporal structure and adopts a local e-prop learning rule in the readout layer to exploit event-driven activity for fast and efficient learning. The result is real-time learning with a setup comprising a computer and the neuromorphic chip in-the-loop, enabling practical training of spiking neural networks for robotic autonomous systems. This work bridges neuroscience-inspired hardware with real-world robotic control, showing that brain-inspired approaches can tackle fast-paced interaction tasks while supporting always-on learning in intelligent machines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。