WorldSense: Enabling Safe Autonomous Navigation Under Rare Event Scenarios
DOI:
https://doi.org/10.54097/xascnx14Keywords:
Autonomous navigation, Rare event detection, World models, Safety-critical scenarios, Temporal anomaly detection, Long-tail distribution, Variational autoencoder, Bird's-eye viewAbstract
Autonomous vehicle (AV) safety in rare or long-tail driving scenarios remains one of the most intractable challenges in modern intelligent transportation research. This paper presents WorldSense, a unified framework that integrates predictive world modeling, temporal anomaly detection (TAD), and safety-aware planning to enable reliable navigation under infrequent but high-risk conditions. WorldSense encodes the driving environment into a compact latent representation using a convolutional neural network (CNN)-based multi-camera perception backbone, predicts future scene evolution through a recurrent gated memory module, and monitors reconstruction divergence in real time to generate a rarity score that triggers conservative trajectory planning when anomalous events are detected. Evaluations conducted on the CARLA simulator using a custom rare event test suite (RETS) and on the nuScenes benchmark demonstrate that WorldSense reduces collision rates by 34.2% and improves route completion by 14.6 percentage points relative to transformer-based planning baselines under rare event conditions. These results establish WorldSense as a principled and scalable framework for safety-critical autonomous navigation in scenarios underrepresented in standard training distributions.
Downloads
References
[1] Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., ... & Beijbom, O. (2020). nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11621-11631).
[2] Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., ... & Anguelov, D. (2020). Scalability in perception for autonomous driving: Waymo open dataset. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 2446-2454).
[3] Breitenstein, J., Termöhlen, J. A., Lipinski, D., & Fingscheidt, T. (2021). Corner cases for visual perception in automated driving: Some guidance on detection approaches. arXiv preprint arXiv:2102.05897.
[4] Bogdoll, D., Eisen, E., Nitsche, M., Scheib, C., & Zöllner, J. M. (2022). Multimodal detection of unknown objects on roads for autonomous driving. arXiv preprint arXiv:2205.01414.
[5] Zhang, H. (2025). Reinforcement Learning Approaches for Layout Optimization in Electronic Design Automation with Electromagnetic Compatibility Constraints. Frontiers in Robotics and Automation, 2(2), 77-93.
[6] Shen, Z., Zhao, W., Wang, B., Wang, Z., & Shang, W. (2026). CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System Inference. IEEE Access.
[7] Sun, T., Wang, M., & Han, X. (2025). Deep Learning in Insurance Fraud Detection: Techniques, Datasets, and Emerging Trends. Journal of Banking and Financial Dynamics, 9(8), 1-11.
[8] Liu, J., Li, P., & Wang, Y. (2026). Graph Neural Networks for Modeling Complex Dependencies in Global Supply Chain Networks. Journal of Computing and Electronic Information Management, 20(3), 9-20.
[9] Zhang, F., & Wu, B. (2025). Large Language Models as General Purpose Intelligence Systems for Reasoning, Planning and Decision Making. American Journal of Artificial Intelligence and Neural Networks, 6(4), 45-72.
[10] Li, P., Ren, S., Zhang, Q., Wang, X., & Liu, Y. (2024). Think4SCND: Reinforcement learning with thinking model for dynamic supply chain network design. IEEE Access, 12, 195974-195985.
[11] Zhang, F., & Yang, J. S. (2025). Learning Driven Decision Intelligence for Autonomous Driving Through Multimodal Understanding World Modeling and Policy Optimization. Frontiers in Artificial Intelligence Research, 2(3), 616-634.
[12] Wang, B., Wang, Z., Zhao, W., & Liu, Y. (2025). Network Fabric Simulation and Validation for Data Center Routing Convergence Under Large-Scale Failure Scenarios. Computer Science Bulletin, 8(01), 310-326.
[13] Nitsch, J., Itkina, M., Senanayake, R., Nieto, J., Schmidt, M., Siegwart, R., ... & Cadena, C. (2021, September). Out-of-distribution detection for automotive perception. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) (pp. 2938-2943). IEEE.
[14] Fremont, D. J., Dreossi, T., Ghosh, S., Yue, X., Sangiovanni-Vincentelli, A. L., & Seshia, S. A. (2019, June). Scenic: a language for scenario specification and scene generation. In Proceedings of the 40th ACM SIGPLAN conference on programming language design and implementation (pp. 63-78).
[15] Chitta, K., Prakash, A., Jaeger, B., Yu, Z., Renz, K., & Geiger, A. (2022). Transfuser: Imitation with transformer-based sensor fusion for autonomous driving. IEEE transactions on pattern analysis and machine intelligence, 45(11), 12878-12895.
[16] Chitta, K., Prakash, A., & Geiger, A. (2021). Neat: Neural attention fields for end-to-end autonomous driving. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 15793-15803).
[17] Feng, D., Harakeh, A., Waslander, S. L., & Dietmayer, K. (2021). A review and comparative study on probabilistic object detection in autonomous driving. IEEE Transactions on Intelligent Transportation Systems, 23(8), 9961-9980.
[18] Malinin, A., & Gales, M. (2020). Uncertainty estimation in autoregressive structured prediction. arXiv preprint arXiv:2002.07650.
[19] Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., ... & Dai, J. (2024). Bevformer: learning bird’s-eye-view representation from lidar-camera via spatiotemporal transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(3), 2020-2036.
[20] Liu, J., Wang, J., Chen, H., Guinness, J., Martin, R., & Kulkarni, C. S. (2019). Optimal Level Crossing Predictions for Electronic Prognostics. In AIAA Scitech 2019 Forum (p. 1962).
[21] Chen, J., Cui, Y., Zhang, X., Yang, J., & Zhou, M. (2024). Temporal convolutional network for carbon tax projection: A data-driven approach. Applied Sciences, 14(20), 9213.
[22] Wei, Z., Sun, T., & Zhou, M. (2024). LIRL: Latent Imagination-Based Reinforcement Learning for Efficient Coverage Path Planning. Symmetry, 16(11), 1537.
[23] Zhang, S., Qiu, L., & Zeng, Z. (2026). Physics-Data Synergy in Structural Health Monitoring: A Multi-Scale Graph Contrastive Framework With Temperature-Adaptive Fusion. IEEE Access.
[24] Zeng, Z., Lin, H., Zhang, S., & Wang, B. (2026). Adaptive Robust Watermarking for Large Language Models via Dynamic Token Embedding Perturbation. IEEE Access, 14, 9319-9339.
[25] Qiu, L. (2025). Multi-Agent Reinforcement Learning for Coordinated Smart Grid and Building Energy Management Across Urban Communities. Computer Life, 13(3), 8-15.
[26] Zhao, W., Chen, T., Yang, J. S., & Qiu, L. (2026). AutoML-Pipeline: A RAG-enhanced code generation framework with pre-validation for cloud-native machine learning workflows. IEEE Access.
[27] Yang, Y., & Yang, J. (2026). Synthetic Data Meets Finance: Generative Models for Privacy Preserving Analytics. Journal of Banking and Financial Dynamics, 10(4), 1-8.
[28] Wang, Z., Shen, Z., Wang, B., & Shang, W. (2025). Modernizing Enterprise Analytics through Low-Code Automation and Cloud-Native Data Architectures. Asian Business Research Journal, 10(12), 20-33.
[29] Zhao, X., Sun, T., Ren, S., Yang, J., & Liu, Y. (2025). RAG-Based AI Agents for Enterprise Software Development: Implementation Patterns and Production Deployment. Frontiers in Artificial Intelligence Research, 2(3), 501-520.
[30] Li, P., Liu, J., & Qiu, L. (2026). Deep Learning Methods for Demand Forecasting and Inventory Optimization in Modern Supply Chains. Asian Business Research Journal, 11(3), 21-29.
[31] Qiu, L. (2025). Reinforcement Learning Approaches for Intelligent Control of Smart Building Energy Systems with Real-Time Adaptation to Occupant Behavior and Weather Conditions. Journal of Computing and Electronic Information Management, 18(2), 32-37.
[32] Hanselmann, N., Renz, K., Chitta, K., Bhattacharyya, A., & Geiger, A. (2022, October). King: Generating safety-critical driving scenarios for robust imitation via kinematics gradients. In European Conference on Computer Vision (pp. 335-352). Cham: Springer Nature Switzerland.
[33] Wu, P., Jia, X., Chen, L., Yan, J., Li, H., & Qiao, Y. (2022). Trajectory-guided control prediction for end-to-end autonomous driving: A simple yet strong baseline. Advances in Neural Information Processing Systems, 35, 6119-6132.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Computing and Electronic Information Management
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
