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 NCARS dataset. In this manner, our SNN4Agents framework paves the way toward enabling energy-efficient embodied SNN deployments for autonomous agents.

翻译：近期趋势表明，自主智能体（如自主地面车辆AGV、无人机UAV和移动机器人）能有效提升人类解决多样化任务的生产力。然而，由于这些智能体通常由便携式电池供电，其运行需满足极低的功耗/能耗要求以实现长续航。为应对这一挑战，神经形态计算已成为一种前景广阔的解决方案，其通过受生物启发的脉冲神经网络（SNN）利用基于事件的相机或数据转换预处理产生的脉冲，高效执行稀疏计算。然而，针对自主智能体的SNN部署研究仍处于早期阶段，尚未系统性地定义实现高效嵌入式SNN部署的优化流程。为此，我们提出一种名为SNN4Agents的新型框架，该框架包含一系列面向自主智能体应用的节能嵌入式SNN设计优化技术。我们的SNN4Agents采用权重量化、时间步长缩减和注意力窗口缩减技术，在保持高精度的同时，协同提升能效、减少内存占用并优化处理延迟。在评估中，我们研究了基于事件的车辆识别用例，并探索了精度、延迟、内存和能耗之间的权衡关系。实验结果表明，在NCARS数据集上，相较于现有先进工作，我们提出的框架在保持高精度（即84.12%准确率）的同时，可实现68.75%的内存节省、3.58倍的加速比以及4.03倍的能效提升。由此，我们的SNN4Agents框架为自主智能体实现节能嵌入式SNN部署开辟了新路径。