Skip to main content

DeepParking: Deep Learning-Based Planning Method for Autonomous Parking

  • Conference paper
  • First Online:
Spatial Data and Intelligence (SpatialDI 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13887))

Included in the following conference series:

  • 481 Accesses

Abstract

Planning methods for parking are an important topic in the realm of autonomous driving. To achieve successful parking, complicated maneuvers are required to be reasonably performed in a very limited space. Moreover, since unstructured parking scenarios are lack of significant common features, creating useful heuristics manually to adapt to changing conditions is a non-trivial task. Therefore, we propose a two-stage scheme, Deep Neural Networks based path prediction for the first stage and sampling-based optimization for the second stage. Specifically, a customized network is used for predicting a feasible path with a high successful rate and the prediction error is modeled by Gaussian in the second stage. With the modeled error, a variant Bi-RRT\(^*\) method is specially-designed to correct the possible prediction error and further improve the path quality. We carry out experiments to validate the performance of the proposed scheme and compare it to existing methods. Experimental results demonstrated that our planning scheme can infer a path by neural networks within 25 ms and plan a final path around 75 ms.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Banzhaf, H., et al.: Learning to predict ego-vehicle poses for sampling-based nonholonomic motion planning. IEEE Robot. Autom. Lett. 4(2), 1053–1060 (2019)

    Google Scholar 

  2. Chen, C., Rickert, M., Knoll, A.: Path planning with orientation-aware space exploration guided heuristic search for autonomous parking and maneuvering. In 2015 IEEE Intelligent Vehicles Symposium (IV), pp. 1148–1153. IEEE (2015)

    Google Scholar 

  3. Chen, G., et al.: Multiobjective scheduling strategy with genetic algorithm and time-enhanced a* planning for autonomous parking robotics in high-density unmanned parking lots. IEEE/ASME Trans. Mechatron. 26(3), 1547–1557 (2021)

    Article  MathSciNet  Google Scholar 

  4. Dosovitskiy, A., et al.: CARLA: an open urban driving simulator. arXiv preprint arXiv:1711.03938 (2017)

  5. Zhuo, D., Miao, Q., Zong, C.: Trajectory planning for automated parking systems using deep reinforcement learning. Int. J. Automot. Technol. 21(4), 881–887 (2020)

    Article  Google Scholar 

  6. Gibbons, J.D., Chakraborti, S.: Nonparametric Statistical Inference: revised and Expanded. CRC Press (2014)

    Google Scholar 

  7. Jordan, M., Perez, A.: Optimal bidirectional rapidly-exploring random trees (2013)

    Google Scholar 

  8. Kuwata, Y., et al.: Motion planning for urban driving using RRT. In: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1681–1686. IEEE (2008)

    Google Scholar 

  9. Liu, C., Wang, Y., Tomizuka, M.: Boundary layer heuristic for search-based nonholonomic path planning in maze-like environments. In: Intelligent Vehicles Symposium (2017)

    Google Scholar 

  10. Pérez-Higueras, N., Caballero, F., Merino, L.: Learning human-aware path planning with fully convolutional networks. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–5. IEEE (2018)

    Google Scholar 

  11. Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)

  12. Reeds, J., Shepp, L.: Optimal paths for a car that goes both forwards and backwards. Pac. J. Math. 145(2), 367–393 (1990)

    Article  MathSciNet  MATH  Google Scholar 

  13. Tian, W., Salscheider, N.O., Shan, Y., Chen, L., Lauer, M.: A collaborative visual tracking architecture for correlation filter and convolutional neural network learning. IEEE Transactions on Intelligent Transportation Systems (2019)

    Google Scholar 

Download references

Acknowledgement

This research is supported partly by GuangDong Basic and Applied Basic Research Foundation (2020A1515110199), partly by Guangdong HUST Industrial Technology Research Institute Guangdong Provincial Key Laboratory of Manufacturing Equipment Digitization (2020B1212060014) and partly by Shenzhen science and technology program (JCYJ20210324122203009, JCYJ20180508152434975).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Huang Kai .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shan, Y., Zhong, Z., Fan, L., Kai, H. (2023). DeepParking: Deep Learning-Based Planning Method for Autonomous Parking. In: Meng, X., et al. Spatial Data and Intelligence. SpatialDI 2023. Lecture Notes in Computer Science, vol 13887. Springer, Cham. https://doi.org/10.1007/978-3-031-32910-4_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-32910-4_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-32909-8

  • Online ISBN: 978-3-031-32910-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics