Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Road Planning for Slums via Deep Reinforcement Learning (2305.13060v3)

Published 22 May 2023 in cs.AI and cs.LG

Abstract: Millions of slum dwellers suffer from poor accessibility to urban services due to inadequate road infrastructure within slums, and road planning for slums is critical to the sustainable development of cities. Existing re-blocking or heuristic methods are either time-consuming which cannot generalize to different slums, or yield sub-optimal road plans in terms of accessibility and construction costs. In this paper, we present a deep reinforcement learning based approach to automatically layout roads for slums. We propose a generic graph model to capture the topological structure of a slum, and devise a novel graph neural network to select locations for the planned roads. Through masked policy optimization, our model can generate road plans that connect places in a slum at minimal construction costs. Extensive experiments on real-world slums in different countries verify the effectiveness of our model, which can significantly improve accessibility by 14.3% against existing baseline methods. Further investigations on transferring across different tasks demonstrate that our model can master road planning skills in simple scenarios and adapt them to much more complicated ones, indicating the potential of applying our model in real-world slum upgrading. The code and data are available at https://github.com/tsinghua-fib-lab/road-planning-for-slums.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (74)
  1. Basic costs of slum upgrading in Brazil. Global Urban Development Magazine 3, 1 (2007), 121–131.
  2. Christopher Alexander et al. 2019. A city is not a tree.
  3. Generalizable Floorplanner through Corner Block List Representation and Hypergraph Embedding. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2692–2702.
  4. Evolution of slum redevelopment policy. Current urban studies 1, 04 (2013), 185.
  5. Marc Barthélemy and Alessandro Flammini. 2008. Modeling urban street patterns. Physical review letters 100, 13 (2008), 138702.
  6. Monte Carlo simulation in statistical physics. Computers in Physics 7, 2 (1993), 156–157.
  7. Phillip Bonacich. 1987. Power and centrality: A family of measures. American journal of sociology 92, 5 (1987), 1170–1182.
  8. Somsook Boonyabancha. 2005. Baan Mankong: Going to scale with “slum” and squatter upgrading in Thailand. Environment and Urbanization 17, 1 (2005), 21–46.
  9. Toward cities without slums: Topology and the spatial evolution of neighborhoods. Science advances 4, 8 (2018), eaar4644.
  10. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 3438–3445.
  11. Jason Corburn and Irene Karanja. 2014. Informal settlements and a relational view of health in Nairobi, Kenya: sanitation, gender and dignity. Health promotion international 31, 2 (2014), 258–269.
  12. Eta prediction with graph neural networks in google maps. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 3767–3776.
  13. Efficiently solving the practical vehicle routing problem: A novel joint learning approach. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 3054–3063.
  14. Finding key players in complex networks through deep reinforcement learning. Nature machine intelligence 2, 6 (2020), 317–324.
  15. Incorporating planning intelligence into deep learning: A planning support tool for street network design. Journal of Urban Technology 29, 2 (2022), 99–114.
  16. A review of urban transportation network design problems. European journal of operational research 229, 2 (2013), 281–302.
  17. Discovering faster matrix multiplication algorithms with reinforcement learning. Nature 610, 7930 (2022), 47–53.
  18. Joe Flood. 2004. Cost Estimate for Millennium Development Goal 7, Target 11 on Slums, background report for UN Millennium Project Task Force on Improving the Lives of Slum Dwellers and UN-HABITAT. Urban Resources, Elsternwick, Australia (2004).
  19. Linton C Freeman. 1977. A set of measures of centrality based on betweenness. Sociometry (1977), 35–41.
  20. Linton C Freeman et al. 2002. Centrality in social networks: Conceptual clarification. Social network: critical concepts in sociology. Londres: Routledge 1 (2002), 238–263.
  21. Ahmed Fawzy Gad. 2021. PyGAD: An Intuitive Genetic Algorithm Python Library. arXiv:2106.06158 [cs.NE]
  22. Deep reinforcement learning based dynamic route planning for minimizing travel time. In 2021 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, 1–6.
  23. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.
  24. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In International conference on machine learning. PMLR, 1861–1870.
  25. UN Habitat. 2012. Streets as tools for urban transformation in slums: a street-led approach to citywide slum upgrading. 17 (2012), 2016.
  26. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  27. Lightgcn: Simplifying and powering graph convolution network for recommendation. In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval. 639–648.
  28. Stochastic weight completion for road networks using graph convolutional networks. In 2019 IEEE 35th international conference on data engineering (ICDE). IEEE, 1274–1285.
  29. Graph convolutional networks for road networks. In Proceedings of the 27th ACM SIGSPATIAL international conference on advances in geographic information systems. 460–463.
  30. Generalization in deep learning. arXiv preprint arXiv:1710.05468 (2017).
  31. Kira Kempinska and Roberto Murcio. 2019. Modelling urban networks using Variational Autoencoders. Applied Network Science 4, 1 (2019), 1–11.
  32. Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013).
  33. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
  34. Vijay Konda and John Tsitsiklis. 1999. Actor-critic algorithms. Advances in neural information processing systems 12 (1999).
  35. Joseph B Kruskal. 1956. On the shortest spanning subtree of a graph and the traveling salesman problem. Proceedings of the American Mathematical society 7, 1 (1956), 48–50.
  36. Deep learning. nature 521, 7553 (2015), 436–444.
  37. Reinforcement learning based recommendation with graph convolutional q-network. In Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval. 1757–1760.
  38. Jointly Contrastive Representation Learning on Road Network and Trajectory. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 1501–1510.
  39. Controlling graph dynamics with reinforcement learning and graph neural networks. In International Conference on Machine Learning. PMLR, 7565–7577.
  40. A graph placement methodology for fast chip design. Nature 594, 7862 (2021), 207–212.
  41. Diana Mitlin and David Satterthwaite. 2012. Urban poverty in the global south: scale and nature. Routledge.
  42. Asynchronous methods for deep reinforcement learning. In International conference on machine learning. PMLR, 1928–1937.
  43. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013).
  44. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529–533.
  45. Reinforcement learning for solving the vehicle routing problem. Advances in neural information processing systems 31 (2018).
  46. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019).
  47. Knowledge is power–informal communities assert their right to the city through SDI and community-led enumerations. Environment and Urbanization 24, 1 (2012), 13–26.
  48. Prefixrl: Optimization of parallel prefix circuits using deep reinforcement learning. In 2021 58th ACM/IEEE Design Automation Conference (DAC). IEEE, 853–858.
  49. Modeling relational data with graph convolutional networks. In European semantic web conference. Springer, 593–607.
  50. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017).
  51. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555, 7698 (2018), 604–610.
  52. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484–489.
  53. Mastering the game of go without human knowledge. nature 550, 7676 (2017), 354–359.
  54. UN-Habitat. 2004. The challenge of slums: global report on human settlements 2003. Management of Environmental Quality: An International Journal 15, 3 (2004), 337–338.
  55. UN-Habitat. 2014. A Practical Guide to Designing, Planning, and Executing Citywide Slum Upgrading Programmes.
  56. Attention is all you need. Advances in neural information processing systems 30 (2017).
  57. Graph Attention Networks. In International Conference on Learning Representations.
  58. Automated urban planning for reimagining city configuration via adversarial learning: quantification, generation, and evaluation. ACM Transactions on Spatial Algorithms and Systems 9, 1 (2023), 1–24.
  59. Reimagining city configuration: Automated urban planning via adversarial learning. In Proceedings of the 28th international conference on advances in geographic information systems. 497–506.
  60. Deep human-guided conditional variational generative modeling for automated urban planning. In 2021 IEEE international conference on data mining (ICDM). IEEE, 679–688.
  61. Reinforced imitative graph representation learning for mobile user profiling: An adversarial training perspective. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4410–4417.
  62. Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planning. arXiv preprint arXiv:2212.00904 (2022).
  63. On representation learning for road networks. ACM Transactions on Intelligent Systems and Technology (TIST) 12, 1 (2020), 1–27.
  64. Task-adaptive few-shot node classification. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 1910–1919.
  65. Nervenet: Learning structured policy with graph neural networks. In Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada, Vol. 30.
  66. Jane Weru. 2004. Community federations and city upgrading: the work of Pamoja Trust and Muungano in Kenya. Environment and Urbanization 16, 1 (2004), 47–62.
  67. Amy Wesolowski and Nathan Eagle. 2010. Parameterizing the dynamics of slums. In 2010 AAAI Spring Symposium Series.
  68. Simplifying graph convolutional networks. In International conference on machine learning. PMLR, 6861–6871.
  69. Learning effective road network representation with hierarchical graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 6–14.
  70. Quantifying the spatial homogeneity of urban road networks via graph neural networks. Nature Machine Intelligence 4, 3 (2022), 246–257.
  71. Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions. arXiv preprint arXiv:2205.10218 (2022).
  72. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 974–983.
  73. Graph transformer networks. Advances in neural information processing systems 32 (2019).
  74. RBG: Hierarchically Solving Large-Scale Routing Problems in Logistic Systems via Reinforcement Learning. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 4648–4658.
Citations (9)
View on Semantic Scholar

Summary

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

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