FPPS: An FPGA-Based Point Cloud Processing System

2026-02-27

AI Summary

This work addresses the dual challenges of real-time performance and energy efficiency in point cloud processing for autonomous driving. The authors propose a novel FPGA-based hardware acceleration framework that, for the first time, efficiently implements the Iterative Closest Point (ICP) algorithm on an FPGA. By optimizing data flow and parallel computation architecture, the design achieves significant performance gains while preserving registration accuracy. Experimental evaluation on the KITTI dataset demonstrates up to a 35× speedup (15.95× weighted average) over state-of-the-art CPU baselines, along with an 8.58× improvement in average energy efficiency. These results establish the proposed approach as a highly efficient solution for 3D localization and perception in resource-constrained embedded autonomous driving platforms.

Technology Category

• Machine Learning: Hardware-aware ML
• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: 3D Computer Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Point cloud processing is a computational bottleneck in autonomous driving systems, especially for real-time applications, while energy efficiency remains a critical system constraint. This work presents FPPS, an FPGA-accelerated point cloud processing system designed to optimize the iterative closest point (ICP) algorithm, a classic cornerstone of 3D localization and perception pipelines. Evaluated on the widely used KITTI benchmark dataset, the proposed system achieves up to 35$\times$ (and a runtime-weighted average of 15.95x) speedup over a state-of-the-art CPU baseline while maintaining equivalent registration accuracy. Notably, the design improves average power efficiency by 8.58x, offering a compelling balance between performance and energy consumption. These results position FPPS as a viable solution for resource-constrained embedded autonomous platforms where both latency and power are key design priorities.

Problem

• point cloud processing
• autonomous driving
• real-time applications
• energy efficiency
• computational bottleneck

Innovation

• FPGA acceleration
• point cloud processing
• Iterative Closest Point (ICP)
• energy efficiency
• autonomous driving