Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Exploring Latent Pathways: Enhancing the Interpretability of Autonomous Driving with a Variational Autoencoder (2404.01750v1)

Published 2 Apr 2024 in cs.CV

Abstract: Autonomous driving presents a complex challenge, which is usually addressed with artificial intelligence models that are end-to-end or modular in nature. Within the landscape of modular approaches, a bio-inspired neural circuit policy model has emerged as an innovative control module, offering a compact and inherently interpretable system to infer a steering wheel command from abstract visual features. Here, we take a leap forward by integrating a variational autoencoder with the neural circuit policy controller, forming a solution that directly generates steering commands from input camera images. By substituting the traditional convolutional neural network approach to feature extraction with a variational autoencoder, we enhance the system's interpretability, enabling a more transparent and understandable decision-making process. In addition to the architectural shift toward a variational autoencoder, this study introduces the automatic latent perturbation tool, a novel contribution designed to probe and elucidate the latent features within the variational autoencoder. The automatic latent perturbation tool automates the interpretability process, offering granular insights into how specific latent variables influence the overall model's behavior. Through a series of numerical experiments, we demonstrate the interpretative power of the variational autoencoder-neural circuit policy model and the utility of the automatic latent perturbation tool in making the inner workings of autonomous driving systems more transparent.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (22)
  1. J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, and B. Kim, “Sanity checks for saliency maps,” Advances in neural information processing systems, vol. 31, 2018.
  2. S. Ainsworth, N. Foti, A. K. Lee, and E. Fox, “Interpretable vaes for nonlinear group factor analysis,” arXiv preprint arXiv:1802.06765, 2018.
  3. A. Amini, W. Schwarting, G. Rosman, B. Araki, S. Karaman, and D. Rus, “Variational Autoencoder for End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   Madrid: IEEE, Oct. 2018, pp. 568–575. [Online]. Available: https://ieeexplore.ieee.org/document/8594386/
  4. L. Chen, P. Wu, K. Chitta, B. Jaeger, A. Geiger, and H. Li, “End-to-end autonomous driving: Challenges and frontiers,” arXiv preprint arXiv:2306.16927, 2023.
  5. L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), 2018, pp. 801–818.
  6. B. Jiang, S. Chen, Q. Xu, B. Liao, J. Chen, H. Zhou, Q. Zhang, W. Liu, C. Huang, and X. Wang, “Vad: Vectorized scene representation for efficient autonomous driving,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2023, pp. 8340–8350.
  7. T. Jing, H. Xia, R. Tian, H. Ding, X. Luo, J. Domeyer, R. Sherony, and Z. Ding, “Inaction: Interpretable action decision making for autonomous driving,” in European Conference on Computer Vision.   Springer, 2022, pp. 370–387.
  8. Z. Kong and K. Chaudhuri, “Understanding instance-based interpretability of variational auto-encoders,” Advances in Neural Information Processing Systems, vol. 34, pp. 2400–2412, 2021.
  9. M. Lechner, R. Hasani, A. Amini, T. A. Henzinger, D. Rus, and R. Grosu, “Neural circuit policies enabling auditable autonomy,” Nature Machine Intelligence, vol. 2, no. 10, pp. 642–652, 2020.
  10. F. Liu, Z. Lu, and X. Lin, “Vision-based environmental perception for autonomous driving,” Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, p. 09544070231203059, 2022.
  11. W. Liu, R. Li, M. Zheng, S. Karanam, Z. Wu, B. Bhanu, R. J. Radke, and O. Camps, “Towards visually explaining variational autoencoders,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8642–8651.
  12. K. Muhammad, T. Hussain, H. Ullah, J. Del Ser, M. Rezaei, N. Kumar, M. Hijji, P. Bellavista, and V. H. C. de Albuquerque, “Vision-based semantic segmentation in scene understanding for autonomous driving: Recent achievements, challenges, and outlooks,” IEEE Transactions on Intelligent Transportation Systems, 2022.
  13. A.-p. Nguyen and M. R. Martínez, “Learning invariances for interpretability using supervised vae,” arXiv preprint arXiv:2007.07591, 2020.
  14. D. Omeiza, H. Webb, M. Jirotka, and L. Kunze, “Explanations in autonomous driving: A survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 10 142–10 162, 2021.
  15. R. Paleja, Y. Niu, A. Silva, C. Ritchie, S. Choi, and M. Gombolay, “Learning interpretable, high-performing policies for autonomous driving,” arXiv preprint arXiv:2202.02352, 2022.
  16. D. A. Pomerleau, “Progress in neural network-based vision for autonomous robot driving,” in Proceedings of the Intelligent Vehicles92 Symposium.   IEEE, 1992, pp. 391–396.
  17. C. Schockaert, V. Macher, and A. Schmitz, “Vae-lime: deep generative model based approach for local data-driven model interpretability applied to the ironmaking industry,” arXiv preprint arXiv:2007.10256, 2020.
  18. A. Tampuu, T. Matiisen, M. Semikin, D. Fishman, and N. Muhammad, “A survey of end-to-end driving: Architectures and training methods,” IEEE Transactions on Neural Networks and Learning Systems, 2020. [Online]. Available: https://arxiv.org/abs/2003.06404
  19. N. Wang, Y. Luo, T. Sato, K. Xu, and Q. A. Chen, “Does physical adversarial example really matter to autonomous driving? towards system-level effect of adversarial object evasion attack,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), October 2023, pp. 4412–4423.
  20. X. Wang, Z. Zhu, Y. Zhang, G. Huang, Y. Ye, W. Xu, Z. Chen, and X. Wang, “Are we ready for vision-centric driving streaming perception? the asap benchmark,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023, pp. 9600–9610.
  21. Y. Wang, D. Blei, and J. P. Cunningham, “Posterior collapse and latent variable non-identifiability,” Advances in Neural Information Processing Systems, vol. 34, pp. 5443–5455, 2021.
  22. É. Zablocki, H. Ben-Younes, P. Pérez, and M. Cord, “Explainability of deep vision-based autonomous driving systems: Review and challenges,” International Journal of Computer Vision, vol. 130, no. 10, pp. 2425–2452, 2022.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now