与并行激光雷达对话：一种基于3D视觉定位的人机交互方法
Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding
AI总结：
本文提出Talk2LiDAR数据集和BEVGrounding方法，通过融合语言与视觉特征实现并行激光雷达的3D视觉定位，提升自动驾驶中人机交互的认知能力。
摘要：
激光雷达传感器在各种应用中扮演着关键角色，尤其是在自动驾驶领域。当前研究主要集中于以点云数据为输入优化感知模型，而对更深层次认知智能的探索仍相对有限。为应对这一挑战，并行激光雷达作为一种面向下一代智能激光雷达系统的新颖理论框架应运而生，该框架紧密整合了物理系统、数字系统和社会系统。为使激光雷达系统具备认知能力，我们将3D视觉定位任务引入并行激光雷达，并提出了一种新颖的激光雷达系统人机交互范式。我们提出了Talk2LiDAR，一个专为自动驾驶中3D视觉定位定制的大规模基准数据集。此外，我们提出了一种两阶段基线方法和一种名为BEVGrounding的高效单阶段方法，该方法通过将粗粒度句子和细粒度词嵌入与视觉特征融合，显著提高了定位精度。我们在Talk2Car-3D和Talk2LiDAR数据集上的实验证明了BEVGrounding的优越性能，为该领域的进一步研究奠定了基础。
英文摘要：
LiDAR sensors play a crucial role in various applications, especially in autonomous driving. Current research primarily focuses on optimizing perceptual models with point cloud data as input, while the exploration of deeper cognitive intelligence remains relatively limited. To address this challenge, parallel LiDARs have emerged as a novel theoretical framework for the next-generation intelligent LiDAR systems, which tightly integrate physical, digital, and social systems. To endow LiDAR systems with cognitive capabilities, we introduce the 3D visual grounding task into parallel LiDARs and present a novel human-computer interaction paradigm for LiDAR systems. We propose Talk2LiDAR, a large-scale benchmark dataset tailored for 3D visual grounding in autonomous driving. Additionally, we present a two-stage baseline approach and an efficient one-stage method named BEVGrounding, which significantly improves grounding accuracy by fusing coarse-grained sentence and fine-grained word embeddings with visual features. Our experiments on Talk2Car-3D and Talk2LiDAR datasets demonstrate the superior performance of BEVGrounding, laying a foundation for further research in this domain.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
