Research on Multi-tasking Smart Cars Based on Autonomous Driving Systems

被引:0
|
作者
Ding S. [1 ]
Qu J. [1 ]
机构
[1] Faculty of Engineering and Technology, Panyapiwat Institute of Management, Nonthaburi
关键词
Autonomous Driving System; Jetson Nano; Multi-tasking autonomous driving; Neural networks; TensorRT;
D O I
10.1007/s42979-023-01740-1
中图分类号
学科分类号
摘要
Using fewer sensors to achieve more autonomous driving tasks has become a challenge. Some of the existing research implements a single neural network model and achieves the goal of input information diversification and multi-task autonomous driving functionality by adding external devices. However, it adds the burden of designing complex modules. Existing methods with only one sensor (camera) can only achieve two tasks of road tracking and obstacle avoidance. In contrast to existing research, this paper proposed a novel Autonomous Driving System (ADS) that is capable of performing five tasks simultaneously with a single camera: road tracking (Task 1), turn sign recognition (Task 2), lane changing and obstacle avoidance when encountering other cars (Task 3), stopping when encountering obstacles (Task 4), and traffic light recognition (Task 5). The ADS fuses the End-to-end model (Efficientnet_b0-SA-RE) and the Safety-assisted model (Efficientnet_b0-CA), which can be switched between to perform autonomous driving tasks depending on the different road conditions. Additionally, a new Robustness Error (RE) loss function and a new Smoothing Activation (SA) function are presented to optimize both models. The ADS also contains our proposed novel Custom Conversion Scheme (CCS), which integrates TensorRT and half-precision technology (FP16) for accelerating the model, and successfully deploys the dual model on the embedded device Jetson Nano. Furthermore, the untrained environment Track 1–4 is designed to test smart cars. The experimental results demonstrate that our method can complete five tasks simultaneously and achieve a F1 score of 85% in the most challenging Track 4, which is 32% higher than existing methods. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.
引用
收藏
相关论文
共 50 条
  • [1] Multi-Tasking POM Systems
    Sullivan, Kevin P.
    Yin, Qiushi
    Collins-Wildman, Daniel L.
    Tao, Meilin
    Geletii, Yurii V.
    Musaev, Djamaladdin G.
    Lian, Tianquan
    Hill, Craig L.
    [J]. FRONTIERS IN CHEMISTRY, 2018, 6
  • [2] CONFIGURING MULTI-TASKING SYSTEMS
    PATRICK, RL
    [J]. DATAMATION, 1966, 12 (09): : 68 - 69
  • [3] A cognitive model of multi-tasking while driving
    Deml, Barbara
    Halbruegge, Marc
    Neumann, Hendrik
    [J]. INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2008, 43 (3-4) : 759 - 759
  • [4] Psychophysiological strain at work with multi-tasking systems
    Schaefer, F
    Schäfer, R
    [J]. JOURNAL OF PSYCHOPHYSIOLOGY, 1998, 12 (03) : 319 - 320
  • [5] PERFORMANCE METRICS FOR HYBRID MULTI-TASKING SYSTEMS
    Rupnow, Kyle
    Adriaens, Jacob
    Fu, Wenyin
    Compton, Katherine
    [J]. FPL: 2009 INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE LOGIC AND APPLICATIONS, 2009, : 547 - 550
  • [6] Editorial: Cognitive-Motor Interference in Multi-Tasking Research
    Zentgraf, Karen
    Mueller, Hermann
    Hazeltine, Eliot
    [J]. FRONTIERS IN PSYCHOLOGY, 2019, 10
  • [7] Polydopamine-based nanostructures: A new generation of versatile, multi-tasking, and smart theranostic tools
    Battaglini, Matteo
    Emanet, Melis
    Carmignani, Alessio
    Ciofani, Gianni
    [J]. NANO TODAY, 2024, 55
  • [8] Interruptions and multi-tasking: moving the research agenda in new directions
    Westbrook, Johanna I.
    [J]. BMJ QUALITY & SAFETY, 2014, 23 (11) : 877 - 879
  • [9] Learning Applications of Multi-tasking Signal Analysis of Fourier Transform Based on Smart Mobile Devices
    Li, Zhengzhe
    Zhao, Teng
    Ren, Dong
    Zhang, Yang
    Wang, Lei
    [J]. PROCEEDINGS OF THE 50TH ANNUAL ASSOCIATION FOR COMPUTING MACHINERY SOUTHEAST CONFERENCE, 2012,
  • [10] Multipopulation-based multi-tasking evolutionary algorithm
    Li, Xiaoyu
    Wang, Lei
    Jiang, Qiaoyong
    [J]. APPLIED INTELLIGENCE, 2023, 53 (04) : 4624 - 4647