Smart City Gnosys
Smart city article details
| Title | Spatio-Temporal Capsule-Based Reinforcement Learning For Mobility-On-Demand Coordination |
|---|---|
| ID_Doc | 52544 |
| Authors | He S.; Shin K.G. |
| Year | 2022 |
| Published | IEEE Transactions on Knowledge and Data Engineering, 34, 3 |
| DOI | http://dx.doi.org/10.1109/TKDE.2020.2992565 |
| Abstract | As an alternative means of convenient and smart transportation, mobility-on-demand (MOD), typified by online ride-sharing and connected taxicabs, has been rapidly growing and spreading worldwide. The large volume of complex traffic and the uncertainty of market supplies/demands have made it essential for many MOD service providers to proactively dispatch vehicles towards ride-seekers. To meet this need effectively, we propose STRide, an MOD coordination learning mechanism reinforced spatio-temporally with capsules. We formalize the adaptive coordination of vehicles into a reinforcement learning framework. STRide incorporates spatial and temporal distributions of supplies (vehicles) and demands (ride requests), customers' preferences and other external factors. A novel spatio-temporal capsule neural network is designed to predict the provider's rewards based on MOD network states, vehicles and their dispatch actions. This way, the MOD platform adapts itself to the supply-demand dynamics with the best potential rewards. We have conducted extensive data analytics and experimental evaluation with five large-scale datasets (∼27 million rides from Uber, NYC/Chicago Taxis, Didi and Car2Go). STRide is shown to outperform state-of-the-arts, substantially reducing request-rejection rate and passenger waiting time, and also increasing the service provider's profits. © 2020 IEEE. |
| Author Keywords | Coordination; Human and vehicle mobility; Mobility-on-demand; Reinforcement learning; Ride-sharing platform; Smart city; Smart transportation; Spatio-temporal capsule network |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
52545  | 0.997 | He S.; Shin K.G. | Spatio-Temporal Capsule-Based Reinforcement Learning For Mobility-On-Demand Network Coordination | The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (2019) |
| 11602 | 0.861 | Li J.; Allan V.H. | Balancing Taxi Distribution In A City-Scale Dynamic Ridesharing Service: A Hybrid Solution Based On Demand Learning | 2020 IEEE International Smart Cities Conference, ISC2 2020 (2020) |
| 58246 | 0.86 | Abdelmoumene H.; Boussahoul S. | Towards Optimized Dynamic Ridesharing System Through Multi-Objective Reinforcement Learning | 2024 IEEE International Multi-Conference on Smart Systems and Green Process, IMC-SSGP 2024 (2024) |
| 8894 | 0.858 | Chen Z.; Li P.; Xiao J.; Nie L.; Liu Y. | An Order Dispatch System Based On Reinforcement Learning For Ride Sharing Services | Proceedings - 2020 IEEE 22nd International Conference on High Performance Computing and Communications, IEEE 18th International Conference on Smart City and IEEE 6th International Conference on Data Science and Systems, HPCC-SmartCity-DSS 2020 (2020) |
| 1389 | 0.856 | Wang Y.; Zhang T.; Wei Z. | A Deep Reinforcement Learning Approach For Online Taxi Dispatching | Proceedings - 2023 International Conference on Networking and Network Applications, NaNA 2023 (2023) |
| 13345 | 0.854 | Rao B.; Zhang X.; Zhu T.; You Y.; Li Y.; Duan J.; Zhou Z.; Chen X. | Can You Do Both? Balancing Order Serving And Crowdsensing For Ride-Hailing Vehicles | IEEE International Workshop on Quality of Service, IWQoS (2024) |
| 38914 | 0.85 | Xiang C.-C.; Li Y.-Y.; Feng L.; Chen C.; Guo S.-T.; Yang P.-L. | Near-Optimal Vehicular Crowdsensing Task Allocation Empowered By Deep Reinforcement Learning; [基于深度强化学习的智联网汽车感知任务分配] | Jisuanji Xuebao/Chinese Journal of Computers, 45, 5 (2022) |