Putra Rachmad Vidya Wicaksana, Marchisio Alberto, Shafique Muhammad
eBrain Lab, Division of Engineering, New York University (NYU) Abu Dhabi, Abu Dhabi, United Arab Emirates.
Front Robot AI. 2024 Jul 26;11:1401677. doi: 10.3389/frobt.2024.1401677. eCollection 2024.
Recent trends have shown that autonomous agents, such as Autonomous Ground Vehicles (AGVs), Unmanned Aerial Vehicles (UAVs), and mobile robots, effectively improve human productivity in solving diverse tasks. However, since these agents are typically powered by portable batteries, they require extremely low power/energy consumption to operate in a long lifespan. To solve this challenge, neuromorphic computing has emerged as a promising solution, where bio-inspired Spiking Neural Networks (SNNs) use spikes from event-based cameras or data conversion pre-processing to perform sparse computations efficiently. However, the studies of SNN deployments for autonomous agents are still at an early stage. Hence, the optimization stages for enabling efficient embodied SNN deployments for autonomous agents have not been defined systematically. Toward this, we propose a novel framework called SNN4Agents that consists of a set of optimization techniques for designing energy-efficient embodied SNNs targeting autonomous agent applications. Our SNN4Agents employs weight quantization, timestep reduction, and attention window reduction to jointly improve the energy efficiency, reduce the memory footprint, optimize the processing latency, while maintaining high accuracy. In the evaluation, we investigate use cases of event-based car recognition, and explore the trade-offs among accuracy, latency, memory, and energy consumption. The experimental results show that our proposed framework can maintain high accuracy (i.e., 84.12% accuracy) with 68.75% memory saving, 3.58x speed-up, and 4.03x energy efficiency improvement as compared to the state-of-the-art work for the NCARS dataset. In this manner, our SNN4Agents framework paves the way toward enabling energy-efficient embodied SNN deployments for autonomous agents.
最近的趋势表明，自主代理，如自主地面车辆（AGV）、无人驾驶飞行器（UAV）和移动机器人，在解决各种任务时能有效提高人类生产力。然而，由于这些代理通常由便携式电池供电，它们需要极低的功耗/能耗才能在长寿命期内运行。为了解决这一挑战，神经形态计算已成为一种有前途的解决方案，其中受生物启发的脉冲神经网络（SNN）利用基于事件的相机的脉冲或数据转换预处理来高效执行稀疏计算。然而，针对自主代理的SNN部署研究仍处于早期阶段。因此，尚未系统地定义用于实现自主代理高效实体SNN部署的优化阶段。为此，我们提出了一个名为SNN4Agents的新颖框架，该框架由一组优化技术组成，用于设计针对自主代理应用的节能实体SNN。我们的SNN4Agents采用权重量化、时间步长减少和注意力窗口减少来共同提高能源效率、减少内存占用、优化处理延迟，同时保持高精度。在评估中，我们研究了基于事件的汽车识别用例，并探索了准确性、延迟、内存和能耗之间的权衡。实验结果表明，与NCARS数据集的最新工作相比，我们提出的框架可以保持高精度（即84.12%的准确率），同时节省68.75%的内存，加速3.58倍，能源效率提高4.03倍。通过这种方式，我们的SNN4Agents框架为实现自主代理的节能实体SNN部署铺平了道路。
