Xu Liying, Zhu Jiadi, Chen Bing, Yang Zhen, Liu Keqin, Dang Bingjie, Zhang Teng, Yang Yuchao, Huang Ru
National Key Laboratory of Science and Technology on Micro/Nano Fabrication, School of Integrated Circuits, Peking University, 100871, Beijing, China.
School of Micro-Nano Electronics, Zhejiang University, 310058, Hangzhou, Zhejiang, China.
Nat Commun. 2022 Aug 10;13(1):4698. doi: 10.1038/s41467-022-32497-5.
As an important approach of distributed artificial intelligence, multi-agent system provides an efficient way to solve large-scale computational problems through high-parallelism processing with nonlinear interactions between the agents. However, the huge capacity and complex distribution of the individual agents make it difficult for efficient hardware construction. Here, we propose and demonstrate a multi-agent hardware system that deploys distributed Ag nanoclusters as physical agents and their electrochemical dissolution, growth and evolution dynamics under electric field for high-parallelism exploration of the solution space. The collaboration and competition between the Ag nanoclusters allow information to be effectively expressed and processed, which therefore replaces cumbrous exhaustive operations with self-organization of Ag physical network based on the positive feedback of information interaction, leading to significantly reduced computational complexity. The proposed multi-agent network can be scaled up with parallel and serial integration structures, and demonstrates efficient solution of graph and optimization problems. An artificial potential field with superimposed attractive/repulsive components and varied ion velocity is realized, showing gradient descent route planning with self-adaptive obstacle avoidance. This multi-agent network is expected to serve as a physics-empowered parallel computing hardware.
作为分布式人工智能的一种重要方法，多智能体系统提供了一种有效的方式，通过智能体之间的非线性交互进行高并行处理来解决大规模计算问题。然而，单个智能体的巨大容量和复杂分布使得高效的硬件构建变得困难。在此，我们提出并展示了一种多智能体硬件系统，该系统将分布式银纳米团簇作为物理智能体，并利用它们在电场下的电化学溶解、生长和演化动力学来对解空间进行高并行探索。银纳米团簇之间的协作与竞争使得信息能够得到有效表达和处理，从而基于信息交互的正反馈，用银物理网络的自组织取代繁琐的穷举操作，显著降低计算复杂度。所提出的多智能体网络可以通过并行和串行集成结构进行扩展，并展示了对图和优化问题的高效求解。实现了具有叠加吸引/排斥分量和变化离子速度的人工势场，展示了具有自适应避障功能的梯度下降路径规划。这种多智能体网络有望成为一种物理赋能的并行计算硬件。
