Abstract
Developing cost-efficient and reliable perception systems remains a central challenge for automated vehicles. LiDAR and camera-based systems dominate, yet they present trade-offs in cost, robustness and performance under adverse conditions. This work introduces a novel framework for learning-based 3D semantic segmentation using Calyo Pulse, a modular, solid-state 3D ultrasound sensor system for use in harsh and cluttered environments. A 3D U-Net architecture is introduced and trained on the spatial ultrasound data for volumetric segmentation. Results demonstrate robust segmentation performance from Calyo Pulse sensors, with potential for further improvement through larger datasets, refined ground truth, and weighted loss functions. Importantly, this study highlights 3D ultrasound sensing as a promising complementary modality for reliable autonomy.
Abstract (translated)
开发高效且可靠的感知系统仍然是自动驾驶汽车面临的核心挑战。目前，基于LiDAR和摄像头的系统占据主导地位，但它们在成本、鲁棒性和恶劣条件下的性能方面存在权衡。本研究提出了一种新的基于学习的3D语义分割框架，使用Calyo Pulse——一种模块化、固态的3D超声波传感器系统，适用于严苛和复杂的环境。该研究引入并训练了一个3D U-Net架构，利用空间超声数据进行体积分割。实验结果表明，从Calyo Pulse传感器中可以实现稳健的语义分割性能，并且通过更大规模的数据集、更精确的真实标签以及加权损失函数的应用，有望进一步提升性能。尤为重要的是，本研究强调了3D超声波传感作为可靠自主驾驶的一种有前景的互补模式的重要性。
URL
https://arxiv.org/abs/2601.13263
