HPL-ViT: A Unified Perception Framework for Heterogeneous Parallel LiDARs in V2V

TL;DR

This paper introduces HPL-ViT, a novel perception framework for heterogeneous LiDARs in vehicle-to-vehicle communication, featuring a new dataset and a graph-attention Transformer architecture that enhances feature fusion and generalization in autonomous driving.

Contribution

The paper presents a new heterogeneous LiDAR dataset OPV2V-HPL and a novel HPL-ViT architecture utilizing graph-attention Transformers for robust feature fusion in diverse scenarios.

Findings

HPL-ViT achieves state-of-the-art performance across all tested settings.

The framework demonstrates strong generalization capabilities.

The OPV2V-HPL dataset effectively captures heterogeneity in LiDAR data.

Abstract

To develop the next generation of intelligent LiDARs, we propose a novel framework of parallel LiDARs and construct a hardware prototype in our experimental platform, DAWN (Digital Artificial World for Natural). It emphasizes the tight integration of physical and digital space in LiDAR systems, with networking being one of its supported core features. In the context of autonomous driving, V2V (Vehicle-to-Vehicle) technology enables efficient information sharing between different agents which significantly promotes the development of LiDAR networks. However, current research operates under an ideal situation where all vehicles are equipped with identical LiDAR, ignoring the diversity of LiDAR categories and operating frequencies. In this paper, we first utilize OpenCDA and RLS (Realistic LiDAR Simulation) to construct a novel heterogeneous LiDAR dataset named OPV2V-HPL. Additionally, we present HPL-ViT, a pioneering architecture designed for robust feature fusion in heterogeneous and dynamic scenarios. It uses a graph-attention Transformer to extract domain-specific features for each agent, coupled with a cross-attention mechanism for the final fusion. Extensive experiments on OPV2V-HPL demonstrate that HPL-ViT achieves SOTA (state-of-the-art) performance in all settings and exhibits outstanding generalization capabilities.