Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving

被引:0
|
作者
Zhou, Hongkuan [2 ]
Sui, Aifen [1 ]
Shi, Letian [2 ]
Li, Yinxian [2 ]
机构
[1] Huawei Munich Res Ctr, Trustworthy Technol & Engn Lab, Munich, Germany
[2] Tech Univ Munich, TUM Sch Computat Informat & Technol, Munich, Germany
关键词
D O I
10.1109/ITSC57777.2023.10422239
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In recent times, there has been a growing focus on end-to-end autonomous driving technologies. This technology involves the replacement of the entire driving pipeline with a single neural network, which has a simpler structure and faster inference time. However, while this approach reduces the number of components in the driving pipeline, it also presents challenges related to interpretability and safety. For instance, the trained policy may not always comply with traffic rules, and it is difficult to determine the reason for such misbehavior due to the lack of intermediate outputs. Additionally, the successful implementation of autonomous driving technology heavily depends on the reliable and expedient processing of sensory data to accurately perceive the surrounding environment. In this paper, we provide penalty-based imitation learning approach combined with cross semantics generation sensor fusion technologies (P-CSG) to efficiently integrate multiple modalities of information and enable the autonomous agent to effectively adhere to traffic regulations. Our model undergoes evaluation within the Town 05 Long benchmark, where we observe a remarkable increase in the driving score by more than 12% when compared to the state-of-the-art (SOTA) model, InterFuser. Notably, our model achieves this performance enhancement while achieving a 7-fold increase in inference speed and reducing the model size by approximately 30%. For more detailed information, including code-based resources, they can be found at https://hk-zh.github.io/p-csg/
引用
收藏
页码:1876 / 1883
页数:8
相关论文
共 50 条
  • [31] End-to-End Deep Conditional Imitation Learning for Autonomous Driving
    Abdou, Mohammed
    Kamal, Hanan
    El-Tantawy, Samah
    Abdelkhalek, Ali
    Adel, Omar
    Hamdy, Karim
    Abaas, Mustafa
    31ST INTERNATIONAL CONFERENCE ON MICROELECTRONICS (IEEE ICM 2019), 2019, : 346 - 350
  • [32] Evaluating Architecture Impacts on Deep Imitation Learning Performance for Autonomous Driving
    Kebria, Parham M.
    Alizadehsani, Roohallah
    Salaken, Syed Moshfeq
    Hossain, Ibrahim
    Khosravi, Abbas
    Kabir, Dipu
    Koohestani, Afsaneh
    Asadi, Houshyar
    Nahavandi, Saeid
    Tunsel, Edward
    Saif, Mehrdad
    2019 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2019, : 865 - 870
  • [33] Imitation Learning for Autonomous Vehicle Driving: How Does the Representation Matter?
    Greco, Antonio
    Rundo, Leonardo
    Saggese, Alessia
    Vento, Mario
    Vicinanza, Antonio
    IMAGE ANALYSIS AND PROCESSING, ICIAP 2022, PT I, 2022, 13231 : 15 - 26
  • [34] PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving
    Pulver, Henry
    Eiras, Francisco
    Carozza, Ludovico
    Hawasly, Majd
    Albrecht, Stefano, V
    Ramamoorthy, Subramanian
    2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 1442 - 1449
  • [35] Cross Validation for CNN based Affordance Learning and Control for Autonomous Driving
    Sun, Chen
    Su, Lang
    Gu, Sunsheng
    Vianney, Jean M. Uwabeza
    Qin, Kongjian
    Cao, Dongpu
    2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC), 2019, : 1519 - 1524
  • [36] Autonomous Driving Based on Nonlinear Model Predictive Control and Multi-Sensor Fusion
    Rick, M.
    Clemens, J.
    Sommer, L.
    Folkers, A.
    Schill, K.
    Bueskens, C.
    IFAC PAPERSONLINE, 2019, 52 (08): : 182 - 187
  • [37] Multimodal Object Detection and Ranging Based on Camera and Lidar Sensor Fusion for Autonomous Driving
    Khan, Danish
    Baek, Minjin
    Kim, Min Young
    Han, Dong Seog
    2022 27TH ASIA PACIFIC CONFERENCE ON COMMUNICATIONS (APCC 2022): CREATING INNOVATIVE COMMUNICATION TECHNOLOGIES FOR POST-PANDEMIC ERA, 2022, : 342 - 343
  • [38] A tree-based approach for visible and thermal sensor fusion in winter autonomous driving
    Boisclair, Jonathan
    Amamou, Ali
    Kelouwani, Sousso
    Alam, M. Zeshan
    Oueslati, Hedi
    Zeghmi, Lotfi
    Agbossou, Kodjo
    MACHINE VISION AND APPLICATIONS, 2024, 35 (04)
  • [39] Autonomous robot navigation based on fuzzy sensor fusion and reinforcement learning
    Tan, KC
    Tan, KK
    Lee, TH
    Zhao, S
    Chen, YJ
    PROCEEDINGS OF THE 2002 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL, 2002, : 182 - 187
  • [40] iCurb: Imitation Learning-Based Detection of Road Curbs Using Aerial Images for Autonomous Driving
    Xu, Zhenhua
    Sun, Yuxiang
    Liu, Ming
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (02) : 1097 - 1104