Smart City Gnosys

Smart city article details

Title	Spatio-Temporal Capsule-Based Reinforcement Learning For Mobility-On-Demand Network Coordination
ID_Doc	52545
Authors	He S.; Shin K.G.
Year	2019
Published	The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
DOI	http://dx.doi.org/10.1145/3308558.3313401
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 three large-scale datasets (∼21 million rides from Uber, Yellow Taxis and Didi). 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, often making 30% improvement over state-of-the-arts. © 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License.
Author Keywords	Capsule network; Mobility-on-demand; Reinforcement learning; Ride-sharing platform; Smart city; Smart transportation coordination

Similar Articles

Id	Similarity	Authors	Title	Published
52544	0.997	He S.; Shin K.G.	Spatio-Temporal Capsule-Based Reinforcement Learning For Mobility-On-Demand Coordination	IEEE Transactions on Knowledge and Data Engineering, 34, 3 (2022)
58246	0.869	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)
11602	0.868	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)
8894	0.865	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)
13345	0.862	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)
1389	0.861	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)
38914	0.855	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)
21383	0.853	Ramezani M.; Valadkhani A.H.	Dynamic Ride-Sourcing Systems For City-Scale Networks - Part I: Matching Design And Model Formulation And Validation	Transportation Research Part C: Emerging Technologies, 152 (2023)