Investigating the Requirements of Automated Vehicles for Port-internal Logistics of Containers

Rose, Hendrik; Lange, Ann-Kathrin; Hinckeldeyn, Johannes; Jahn, Carlos; Kreutzfeldt, Jochen

doi:10.1007/978-3-031-05359-7_15

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, the demand for affordable autonomous driving solutions in simpler environments has been ignored. For instance, in uncomplicated settings such as ports (Qin et al, 2020 ; Rose et al, 2022 ), lightweight models with smaller datasets may deliver satisfactory results while minimizing computational requirements and enhancing inference speed. By alleviating the computational demand imposed on deployment hardware, the research on lightweight perception network can potentially pave the way for wider deployment of self-driving.…”

Section: Introductionmentioning

confidence: 99%

Mobip: a lightweight model for driving perception using MobileNet

Ye,

Zhang

2023

Front. Neurorobot.

View full text Add to dashboard Cite

The visual perception model is critical to autonomous driving systems. It provides the information necessary for self-driving cars to make decisions in traffic scenes. We propose a lightweight multi-task network (Mobip) to simultaneously perform traffic object detection, drivable area segmentation, and lane line detection. The network consists of a shared encoder for feature extraction and two decoders for handling detection and segmentation tasks collectively. By using MobileNetV2 as the backbone and an extremely efficient multi-task architecture to implement the perception model, our network has great advantages in inference speed. The performance of the multi-task network is verified on a challenging public Berkeley Deep Drive(BDD100K) dataset. The model achieves an inference speed of 58 FPS on NVIDIA Tesla V100 while still maintaining competitive performance on all three tasks compared to other multi-task networks. Besides, the effectiveness and efficiency of the multi-task architecture are verified via ablative studies.

show abstract

Section: Introductionmentioning

confidence: 99%