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

Uncertainty-aware Semantic Mapping in Off-road Environments with Dempster-Shafer Theory of Evidence (2405.06265v1)

Published 10 May 2024 in cs.RO and cs.CV

Abstract: Semantic mapping with Bayesian Kernel Inference (BKI) has shown promise in providing a richer understanding of environments by effectively leveraging local spatial information. However, existing methods face challenges in constructing accurate semantic maps or reliable uncertainty maps in perceptually challenging environments due to unreliable semantic predictions. To address this issue, we propose an evidential semantic mapping framework, which integrates the evidential reasoning of Dempster-Shafer Theory of Evidence (DST) into the entire mapping pipeline by adopting Evidential Deep Learning (EDL) and Dempster's rule of combination. Additionally, the extended belief is devised to incorporate local spatial information based on their uncertainty during the mapping process. Comprehensive experiments across various off-road datasets demonstrate that our framework enhances the reliability of uncertainty maps, consistently outperforming existing methods in scenes with high perceptual uncertainties while showing semantic accuracy comparable to the best-performing semantic mapping techniques.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. B.-s. Kim, P. Kohli, and S. Savarese, “3d scene understanding by voxel-crf,” in IEEE/CVF International Conference on Computer Vision (CVPR), 2013, pp. 1425–1432.
  2. J. P. Valentin, S. Sengupta, J. Warrell, A. Shahrokni, and P. H. Torr, “Mesh based semantic modelling for indoor and outdoor scenes,” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2067–2074.
  3. S. Sengupta and P. Sturgess, “Semantic octree: Unifying recognition, reconstruction and representation via an octree constrained higher order mrf,” in IEEE International Conference on Robotics and Automation (ICRA), 2015, pp. 1874–1879.
  4. D. Paz, H. Zhang, Q. Li, H. Xiang, and H. I. Christensen, “Probabilistic semantic mapping for urban autonomous driving applications,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, pp. 2059–2064.
  5. A. Asgharivaskasi and N. Atanasov, “Semantic octree mapping and shannon mutual information computation for robot exploration,” IEEE Transactions on Robotics, 2023.
  6. D. Morilla-Cabello, L. Mur-Labadia, R. Martinez-Cantin, and E. Montijano, “Robust fusion for bayesian semantic mapping,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023.
  7. J. M. C. Marques, A. Zhai, S. Wang, and K. Hauser, “On the overconfidence problem in semantic 3d mapping,” IEEE International Conference on Robotics and Automation (ICRA), 2024.
  8. J. Wang and B. Englot, “Fast, accurate gaussian process occupancy maps via test-data octrees and nested bayesian fusion,” in IEEE International Conference on Robotics and Automation (ICRA), 2016, pp. 1003–1010.
  9. W. R. Vega-Brown, M. Doniec, and N. G. Roy, “Nonparametric bayesian inference on multivariate exponential families,” Advances in Neural Information Processing Systems (NeurIPS), vol. 27, 2014.
  10. L. Gan, R. Zhang, J. W. Grizzle, R. M. Eustice, and M. Ghaffari, “Bayesian spatial kernel smoothing for scalable dense semantic mapping,” IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 790–797, 2020.
  11. A. Unnikrishnan, J. Wilson, L. Gan, A. Capodieci, P. Jayakumar, K. Barton, and M. Ghaffari, “Dynamic semantic occupancy mapping using 3d scene flow and closed-form bayesian inference,” IEEE Access, vol. 10, pp. 97 954–97 970, 2022.
  12. J. Wilson, Y. Fu, A. Zhang, J. Song, A. Capodieci, P. Jayakumar, K. Barton, and M. Ghaffari, “Convolutional bayesian kernel inference for 3d semantic mapping,” in IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 8364–8370.
  13. J. McCormac, A. Handa, A. Davison, and S. Leutenegger, “Semanticfusion: Dense 3d semantic mapping with convolutional neural networks,” in IEEE International Conference on Robotics and automation (ICRA), 2017, pp. 4628–4635.
  14. Y. Xiang and D. Fox, “Da-rnn: Semantic mapping with data associated recurrent neural networks,” Robotics: Science and Systems (RSS), 2017.
  15. L. Sun, Z. Yan, A. Zaganidis, C. Zhao, and T. Duckett, “Recurrent-octomap: Learning state-based map refinement for long-term semantic mapping with 3-d-lidar data,” IEEE Robotics and Automation Letters, vol. 3, no. 4, pp. 3749–3756, 2018.
  16. D. Maturana, P.-W. Chou, M. Uenoyama, and S. Scherer, “Real-time semantic mapping for autonomous off-road navigation,” in Field and Service Robotics: Results of the 11th International Conference, 2018, pp. 335–350.
  17. J. Wilson, J. Song, Y. Fu, A. Zhang, A. Capodieci, P. Jayakumar, K. Barton, and M. Ghaffari, “Motionsc: Data set and network for real-time semantic mapping in dynamic environments,” IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 8439–8446, 2022.
  18. Y. Jin, D. Han, and H. Ko, “Memory-based semantic segmentation for off-road unstructured natural environments,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021, pp. 24–31.
  19. J. Seo, S. Sim, and I. Shim, “Learning off-road terrain traversability with self-supervisions only,” IEEE Robotics and Automation Letters, 2023.
  20. J. Kim, J. Seo, and J. Min, “Evidential semantic mapping in off-road environments with uncertainty-aware bayesian kernel inference,” arXiv preprint arXiv:2403.14138, 2024.
  21. J. Frey, S. Khattak, M. Patel, D. Atha, J. Nubert, C. Padgett, M. Hutter, and P. Spieler, “Roadrunner–learning traversability estimation for autonomous off-road driving,” arXiv preprint arXiv:2402.19341, 2024.
  22. C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On calibration of modern neural networks,” in International Conference on Machine Learning (ICML), 2017, pp. 1321–1330.
  23. P. de Jorge, R. Volpi, P. H. Torr, and G. Rogez, “Reliability in semantic segmentation: Are we on the right track?” in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 7173–7182.
  24. M. Sensoy, L. Kaplan, and M. Kandemir, “Evidential deep learning to quantify classification uncertainty,” Advances in Neural Information Processing Systems (NeurIPS), vol. 31, 2018.
  25. J. Wilson, Y. Fu, J. Friesen, P. Ewen, A. Capodieci, P. Jayakumar, K. Barton, and M. Ghaffari, “Convbki: Real-time probabilistic semantic mapping network with quantifiable uncertainty,” arXiv preprint arXiv:2310.16020, 2023.
  26. D. D. Fan, K. Otsu, Y. Kubo, A. Dixit, J. Burdick, and A. akbar Agha-mohammadi, “STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation,” in Proceedings of Robotics: Science and Systems (RSS), 2021.
  27. U. K. Rakowsky, “Fundamentals of the dempster-shafer theory and its applications to reliability modeling,” International Journal of Reliability, Quality and Safety Engineering, vol. 14, no. 06, pp. 579–601, 2007.
  28. P. Jiang, P. Osteen, M. Wigness, and S. Saripalli, “Rellis-3d dataset: Data, benchmarks and analysis,” in IEEE International Conference on Robotics and Automation (ICRA), 2021, pp. 1110–1116.
  29. K. Doherty, J. Wang, and B. Englot, “Bayesian generalized kernel inference for occupancy map prediction,” in IEEE International Conference on Robotics and Automation (ICRA), 2017, pp. 3118–3124.
  30. Y. Deng, M. Wang, Y. Yang, D. Wang, and Y. Yue, “See-csom: Sharp-edged and efficient continuous semantic occupancy mapping for mobile robots,” IEEE Transactions on Industrial Electronics, 2023.
  31. D. Deng, G. Chen, Y. Yu, F. Liu, and P.-A. Heng, “Uncertainty estimation by fisher information-based evidential deep learning,” International Conference on Machine Learning (ICML), 2023.
  32. D. T. Ulmer, C. Hardmeier, and J. Frellsen, “Prior and posterior networks: A survey on evidential deep learning methods for uncertainty estimation,” Transactions on Machine Learning Research, 2023.
  33. Z. Han, C. Zhang, H. Fu, and J. T. Zhou, “Trusted multi-view classification with dynamic evidential fusion,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 2, pp. 2551–2566, 2022.
  34. J. Han, Y. Min, H.-J. Chae, B.-M. Jeong, and H.-L. Choi, “Ds-k3dom: 3-d dynamic occupancy mapping with kernel inference and dempster-shafer evidential theory,” in IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 6217–6223.
  35. Y. Chang, F. Xue, F. Sheng, W. Liang, and A. Ming, “Fast road segmentation via uncertainty-aware symmetric network,” in IEEE International Conference on Robotics and Automation (ICRA), 2022, pp. 11 124–11 130.
  36. K. Sirohi, S. Marvi, D. Büscher, and W. Burgard, “Uncertainty-aware panoptic segmentation,” IEEE Robotics and Automation Letters, vol. 8, no. 5, pp. 2629–2636, 2023.
  37. X. Cai, S. Ancha, L. Sharma, P. R. Osteen, B. Bucher, S. Phillips, J. Wang, M. Everett, N. Roy, and J. P. How, “Evora: Deep evidential traversability learning for risk-aware off-road autonomy,” arXiv preprint arXiv:2311.06234, 2023.
  38. A. Melkumyan and F. T. Ramos, “A sparse covariance function for exact gaussian process inference in large datasets,” in International Joint Conference on Artificial Intelligence (IJCAI), 2009.
Citations (1)
View on Semantic Scholar

Summary

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

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