DEVELOPMENT AND EMPIRICAL EVALUATION OF AN ONLINE COURSE ON INTELLIGENT VEHICLE ENVIRONMENT PERCEPTION
Keywords:
Intelligent vehicle, Environment perception technology, Online course development, ADDIE model, Mixed teaching, Autonomous driving simulationAbstract
Intelligent vehicle environment perception is a core component of automotive engineering education, yet traditional teaching is constrained by costly perception hardware, rapidly changing algorithms, limited simulation time and fragmented learning resources. This study develops an online course for Intelligent Vehicle Environment Perception Technology using the ADDIE instructional design model. The course integrates learner and industry demand analysis, modular digital resources, CARLA-based simulation experiments, multi-sensor fusion cases and hierarchical assessment. Teaching effectiveness was evaluated over 16 weeks across four intact course sections (n=120) using theoretical scores, experiment scores, course completion and student satisfaction. The proposed mixed online-offline course achieved an average theoretical score of 84.6, an experiment score of 82.9 and a completion rate of 95.3%, compared with 72.3, 65.1 and 76.4%, respectively, for pure offline teaching. In the ablation analysis, removing the simulation module reduced experiment performance and satisfaction more than removing the industrial-case module. The findings indicate that systematic digital resources and virtual simulation can complement physical laboratory teaching and support practical learning under hardware constraints. Further replication across institutions and cohorts is required to establish generalisability.References
[1] Caesar H, Bankiti V, Lang A H, et al. nuScenes: A multimodal dataset for autonomous driving. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 11621-11631.
[2] Lang A H, Vora S, Caesar H, et al. PointPillars: Fast encoders for object detection from point clouds. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 12697-12705. DOI: 10.1109/CVPR.2019.01298.
[3] Qian H, Wang M, Zhu M, et al. A review of multi-sensor fusion in autonomous driving. Sensors, 2025, 25(19): 6033. DOI: 10.3390/s25196033.
[4] Vora S, Lang A H, Helou B, et al. PointPainting: Sequential fusion for 3D object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 4604-4612.
[5] Branch R M. Instructional Design: The ADDIE Approach. New York: Springer, 2009. DOI: 10.1007/978-0-387-09506-6.
[6] Molenda M. In search of the elusive ADDIE model. Performance Improvement, 2003, 42(5): 34-36. DOI: 10.1002/pfi.4930420508.
[7] Dosovitskiy A, Ros G, Codevilla F, et al. CARLA: An open urban driving simulator. Proceedings of the 1st Annual Conference on Robot Learning, 2017, 78: 1-16.
[8] Jocher G, Chaurasia A, Qiu J. Ultralytics YOLOv8. Version 8.0.0. Ultralytics, 2023. https://github.com/ultralytics/ultralytics.
[9] Li J, Liang W. Effectiveness of virtual laboratory in engineering education: A meta-analysis. PLoS ONE, 2024, 19(12): e0316269. DOI: 10.1371/journal.pone.0316269.