{"ID":2835165,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00427","arxiv_id":"2512.00427","title":"Hardware-Software Collaborative Computing of Photonic Spiking Reinforcement Learning for Robotic Continuous Control","abstract":"Robotic continuous control tasks impose stringent demands on the energy efficiency and latency of computing architectures due to their high-dimensional state spaces and real-time interaction requirements. Conventional electronic computing platforms face computational bottlenecks, whereas the fusion of photonic computing and spiking reinforcement learning (RL) offers a promising alternative. Here, we propose a novel computing architecture based on photonic spiking RL, which integrates the Twin Delayed Deep Deterministic policy gradient (TD3) algorithm with spiking neural network (SNN). The proposed architecture employs an optical-electronic hybrid computing paradigm wherein a silicon photonic Mach-Zehnder interferometer (MZI) chip executes linear matrix computations, while nonlinear spiking activations are performed in the electronic domain. Experimental validation on the Pendulum-v1 and HalfCheetah-v2 benchmarks demonstrates the system capability for software-hardware co-inference, achieving a control policy reward of 5831 on HalfCheetah-v2, a 23.33% reduction in convergence steps, and an action deviation below 2.2%. Notably, this work represents the first application of a programmable MZI photonic computing chip to robotic continuous control tasks, attaining an energy efficiency of 1.39 TOPS/W and an ultralow computational latency of 120 ps. Such performance underscores the promise of photonic spiking RL for real-time decision-making in autonomous and industrial robotic systems.","short_abstract":"Robotic continuous control tasks impose stringent demands on the energy efficiency and latency of computing architectures due to their high-dimensional state spaces and real-time interaction requirements. Conventional electronic computing platforms face computational bottlenecks, whereas the fusion of photonic computin...","url_abs":"https://arxiv.org/abs/2512.00427","url_pdf":"https://arxiv.org/pdf/2512.00427v1","authors":"[\"Mengting Yu\",\"Shuiying Xiang\",\"Changjian Xie\",\"Yonghang Chen\",\"Haowen Zhao\",\"Xingxing Guo\",\"Yahui Zhang\",\"Yanan Han\",\"Yue Hao\"]","published":"2025-11-29T10:05:06Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"physics.optics\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}