路徑規劃對於許多任務至關重要，例如機器人導航和自動駕駛，在復雜的大型環境時，尋找正確的路徑往往會花費大量資源。因此，在本論文中，我們提出了一種階層式的路徑規劃方法以及一個通用的路徑規劃網路，我們將流程分為兩個階段: 整體規劃和局部規劃。 在實行整體規劃時，我們調整地圖的大小並使用八個地圖來表示八個方向的障礙物分佈。 在進行局部規劃時，我們關注在全局路徑中每個點所相對應的局部地圖。為了增加成功率，我們添加了重新規劃和重新選擇方向的機制。在實驗階段，我們評估訓練時間、執行時間和準確性。 此外，我們展示了網絡的靈活性。

Path planning is essential for many tasks, such as robot navigation and autonomous driving. When encountering a complex and large environment, finding the path costs a lot of resources. In this work, we introduce an efficient method with a general planning network. Instead of routing on the original map, we divide the process into two stages: global and detail routing. For the global routing, we resize the map and use eight maps to represent the obstacle distributions over eight directions. For detail routing, we concentrate on the local map corresponding to every point on the global path. To increase the success rate, we add re-routing and re-selection mechanisms. We evaluate our method by the training time, the execution time, and the accuracy. Furthermore, we show the flexibility of our network on action selection.

1 Introduction 8
2 Related Work 10
3 Proposed Method 12
3.1 General Planning Network 12
3.2 Hierarchical Planning 14
3.3 Re-selection and Re-planning 16
4 Experiments 18
4.1 Training 18
4.2 Experimental Results 18
4.3 Ablation Experiments 24
5 Conclusion 28

[1] Z. A. Algfoor, M. S. Sunar, and H. Kolivand. A comprehensive study on pathfind-
ing techniques for robotics and video games. Int. J. Comput. Games Technol.,
2015:736138:1–736138:11, 2015.
[2] S. Beamer, K. Asanovic, and D. A. Patterson. Direction-optimizing breadth-first
search. Sci. Program., 21(3-4):137–148, 2013.
[3] Y. Burda, H. Edwards, D. Pathak, A. J. Storkey, T. Darrell, and A. A. Efros. Large-
scale study of curiosity-driven learning. In ICLR (Poster). OpenReview.net, 2019.
[4] L. Claussmann, M. Revilloud, D. Gruyer, and S. Glaser. A review of motion planning
for highway autonomous driving. IEEE Trans. Intell. Transp. Syst., 21(5):1826–1848,
2020.
[5] E. W. Dijkstra. A note on two problems in connexion with graphs. Numerische
Mathematik, 1:269–271, 1959.
[6] A. Ecoffet, J. Huizinga, J. Lehman, K. O. Stanley, and J. Clune. Go-explore: a new
approach for hard-exploration problems. CoRR, abs/1901.10995, 2019.
[7] J. Ferreira, A. A. F. Júnior, Y. M. Galvão, P. Barros, S. M. M. Fernandes, and B. J. T.
Fernandes. Performance improvement of path planning algorithms with deep learning
encoder model. CoRR, abs/2008.02254, 2020.
[8] S. Gupta, J. Davidson, S. Levine, R. Sukthankar, and J. Malik. Cognitive mapping and
planning for visual navigation. In CVPR, pages 7272–7281. IEEE Computer Society,
2017.
[9] P. E. Hart, N. J. Nilsson, and B. Raphael. A formal basis for the heuristic determina-
tion of minimum cost paths. IEEE Trans. Syst. Sci. Cybern., 4(2):100–107, 1968.
29
[10] M. A. Hossain, I. Ahmedy, M. Z. M. Z. Harith, M. Y. I. B. Idris, T. K. Soon, R. M.
Noor, and S. B. Yusoff. Route optimization by using dijkstra’s algorithm for the waste
management system. In ICISS, pages 110–114. ACM, 2020.
[11] F. Lagos. Exact Algorithms For Routing Problems. PhD thesis, Georgia Institute of
Technology, Atlanta, GA, USA, 2020.
[12] H. Liao, W. Zhang, X. Dong, B. Póczos, K. Shimada, and L. B. Kara. A deep rein-
forcement learning approach for global routing. CoRR, abs/1906.08809, 2019.
[13] L. Lv, S. Zhang, D. Ding, and Y. Wang. Path planning via an improved dqn-based
learning policy. IEEE Access, 7:67319–67330, 2019.
[14] V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D.Wierstra, and M. A.
Riedmiller. Playing atari with deep reinforcement learning. CoRR, abs/1312.5602,
2013.
[15] V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare,
A. Graves, M. A. Riedmiller, A. Fidjeland, G. Ostrovski, S. Petersen, C. Beattie,
A. Sadik, I. Antonoglou, H. King, D. Kumaran, D.Wierstra, S. Legg, and D. Hassabis.
Human-level control through deep reinforcement learning. Nat., 518(7540):529–533,
2015.
[16] A. Naghizadeh, S. Berenjian, D. J. Margolis, and D. N. Metaxas. GNM: gridcell
navigational model. Expert Syst. Appl., 148:113217, 2020.
[17] D. Pathak, P. Agrawal, A. A. Efros, and T. Darrell. Curiosity-driven exploration by
self-supervised prediction. In CVPR Workshops, pages 488–489. IEEE Computer
Society, 2017.
[18] L. G. Polpitiya and K. Premaratne. Real-time detection and prediction of relative
motion of moving objects in autonomous driving. In FLAIRS Conference, pages 136–
141. AAAI Press, 2020.
[19] E. Shelhamer, J. Long, and T. Darrell. Fully convolutional networks for semantic
segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 39(4):640–651, 2017.
30
[20] A. Tamar, Y. Wu, G. Thomas, S. Levine, and P. Abbeel. Value iteration networks. In
IJCAI, pages 4949–4953. ijcai.org, 2017.
[21] J. Wang, Y. Wang, D. Zhang, Y. Yang, and R. Xiong. Learning hierarchical behavior
and motion planning for autonomous driving. CoRR, abs/2005.03863, 2020.
[22] X.Wang, R. B. Girshick, A. Gupta, and K. He. Non-local neural networks. In CVPR,
pages 7794–7803. IEEE Computer Society, 2018.
[23] P. Wu, S. Chen, and D. N. Metaxas. Motionnet: Joint perception and motion pre-
diction for autonomous driving based on bird’s eye view maps. In CVPR, pages
11382–11392. IEEE, 2020.
[24] Y. Xu, N. Zhang, and Q. Pu-Hua. The application of the dijkstra algorithm in the
tourist route planning. In FSDM, volume 320 of Frontiers in Artificial Intelligence
and Applications, pages 1101–1110. IOS Press, 2019.
[25] F. Zeng, C. Wang, and S. S. Ge. A survey on visual navigation for artificial agents
with deep reinforcement learning. IEEE Access, 8:135426–135442, 2020.
[26] Y. Zhang and C. Chu. Gdrouter: interleaved global routing and detailed routing for
ultimate routability. In DAC, pages 597–602. ACM, 2012.