Power Optimization Of FPGAs Used In Autonomous Vehicles

Autonomous vehicles represent the forefront of modern technology, integrating robotics, machine learning, and advanced hardware systems for tasks such as object detection and real-time decision-making. This research focuses on enhancing the power efficiency of Field Programmable Gate Arrays (FPGAs), a key hardware choice due to their flexibility and parallel processing capabilities. By leveraging Dynamic Voltage and Frequency Scaling (DVFS) alongside a Self-Feedback Convolutional Neural Network (CNN), the proposed system achieves a significant reduction in energy consumption while maintaining performance. The system, implemented on a Xilinx Virtex7 FPGA and tested with the KITTI dataset, demonstrates a power reduction of 65.9% without compromising detection accuracy. This scalable solution provides a foundation for energy-efficient operations in autonomous vehicles.