Infrastructure-Assisted Collaborative Perception in Automated Valet Parking: A Safety Perspective

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jia, Yukuan, Zhang, Jiawen, Lu, Shimeng, Fan, Baokang, Mao, Ruiqing, Zhou, Sheng, Niu, Zhisheng
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929285989662720
author Jia, Yukuan
Zhang, Jiawen
Lu, Shimeng
Fan, Baokang
Mao, Ruiqing
Zhou, Sheng
Niu, Zhisheng
author_facet Jia, Yukuan
Zhang, Jiawen
Lu, Shimeng
Fan, Baokang
Mao, Ruiqing
Zhou, Sheng
Niu, Zhisheng
contents Environmental perception in Automated Valet Parking (AVP) has been a challenging task due to severe occlusions in parking garages. Although Collaborative Perception (CP) can be applied to broaden the field of view of connected vehicles, the limited bandwidth of vehicular communications restricts its application. In this work, we propose a BEV feature-based CP network architecture for infrastructure-assisted AVP systems. The model takes the roadside camera and LiDAR as optional inputs and adaptively fuses them with onboard sensors in a unified BEV representation. Autoencoder and downsampling are applied for channel-wise and spatial-wise dimension reduction, while sparsification and quantization further compress the feature map with little loss in data precision. Combining these techniques, the size of a BEV feature map is effectively compressed to fit in the feasible data rate of the NR-V2X network. With the synthetic AVP dataset, we observe that CP can effectively increase perception performance, especially for pedestrians. Moreover, the advantage of infrastructure-assisted CP is demonstrated in two typical safety-critical scenarios in the AVP setting, increasing the maximum safe cruising speed by up to 3m/s in both scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15156
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Infrastructure-Assisted Collaborative Perception in Automated Valet Parking: A Safety Perspective
Jia, Yukuan
Zhang, Jiawen
Lu, Shimeng
Fan, Baokang
Mao, Ruiqing
Zhou, Sheng
Niu, Zhisheng
Robotics
Computer Vision and Pattern Recognition
Systems and Control
Environmental perception in Automated Valet Parking (AVP) has been a challenging task due to severe occlusions in parking garages. Although Collaborative Perception (CP) can be applied to broaden the field of view of connected vehicles, the limited bandwidth of vehicular communications restricts its application. In this work, we propose a BEV feature-based CP network architecture for infrastructure-assisted AVP systems. The model takes the roadside camera and LiDAR as optional inputs and adaptively fuses them with onboard sensors in a unified BEV representation. Autoencoder and downsampling are applied for channel-wise and spatial-wise dimension reduction, while sparsification and quantization further compress the feature map with little loss in data precision. Combining these techniques, the size of a BEV feature map is effectively compressed to fit in the feasible data rate of the NR-V2X network. With the synthetic AVP dataset, we observe that CP can effectively increase perception performance, especially for pedestrians. Moreover, the advantage of infrastructure-assisted CP is demonstrated in two typical safety-critical scenarios in the AVP setting, increasing the maximum safe cruising speed by up to 3m/s in both scenarios.
title Infrastructure-Assisted Collaborative Perception in Automated Valet Parking: A Safety Perspective
topic Robotics
Computer Vision and Pattern Recognition
Systems and Control
url https://arxiv.org/abs/2403.15156