A 2.793 \mu W Near-Threshold Neuronal Population Dynamics Trajectory Filter for Reliable Simultaneous Localization and Mapping

• Published in: IEEE transactions on circuits and systems. I, Regular papers Regular papers, 2024-11, p.1-13
• Main Authors: Wei, Zhengzhe, Dong, Boyi, Su, Yuqi, Wang, Yi, Yang, Chuanshi, Lu, Yuncheng, Wang, Chao, Kim, Tony Tae-Hyoung, Zheng, Yuanjin
• Format: Article
• Language: English
• Subjects: Circuits; Computer architecture; finite-difference; Hardware acceleration; Heuristic algorithms; near-threshold computing; Odometry; Power demand; processing-in-memory; Real-time systems; Sensors; Simultaneous localization and mapping; Trajectory; trajectory filter; ultra-low power edge processing
• ISSN: 1549-8328
• DOI: 10.1109/TCSI.2024.3493246

This work presents an algorithm hardware co-design implementing a digital neuronal population dynamics simulator intended for the trajectory error correction task within a simultaneous localization and mapping workflow. A custom discretized procedural algorithm approximating a neuronal population dynamics-based inference operation is developed for mapping onto an ultra-lightweight digital macro featuring massively parallel in-situ processing techniques. Fabricated using a 40nm technology, the test chip features a 22\times 22 neuron array with 0.1358mm ^{2} core area and provides a 12-bit computing precision. A time-multiplexed processing element design prevents the use of excessive silicon area. Accomplished via extensive data reuse through massively parallel processing-in-memory architecture attached to a custom I/O interface, a single inference operation is completed within 3277 clock cycles, providing 200 inferences per second operating at a low frequency of 0.667Mhz with a 0.5V core supply and consuming sub-10- \mu W power.