Smart Balancing of E-scooter Sharing Systems via Deep Reinforcement Learning

Nowadays, micro-mobility sharing systems have become extremely popular. Such systems consist in fleets of electric vehicles which are deployed in cities, and used by citizens to move in a more ecological and flexible way. Unfortunately, one of the issues related to such technologies is its intrinsic load imbalance; since the users can pick up and drop off the electric vehicles where they prefer. We present ESB-DQN, a multi-agent system based on Deep Reinforcement Learning that offers suggestions to pick or return e-scooters in order to make the fleet usage and sharing as balanced as possible.

[1]  Longbo Huang,et al.  A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems , 2018, AAAI.

[2]  Jie Wu,et al.  Optimizing Rebalance Scheme for Dock-Less Bike Sharing Systems with Adaptive User Incentive , 2019, 2019 20th IEEE International Conference on Mobile Data Management (MDM).

[3]  Tom Schaul,et al.  Rainbow: Combining Improvements in Deep Reinforcement Learning , 2017, AAAI.

[4]  Feihu Huang,et al.  A Rebalancing Strategy for the Imbalance Problem in Bike-Sharing Systems , 2019, Energies.

[5]  Helge Spieker.  Constraint-Guided Reinforcement Learning: Augmenting the Agent-Environment-Interaction , 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

[6]  Paolo Santi,et al.  Understanding spatio-temporal heterogeneity of bike-sharing and scooter-sharing mobility , 2020, Comput. Environ. Urban Syst..

[7]  Hui Xiong,et al.  Rebalancing Bike Sharing Systems: A Multi-source Data Smart Optimization , 2016, KDD.

[8]  Luca Vassio,et al.  E-Scooter Sharing: Leveraging Open Data for System Design , 2020, 2020 IEEE/ACM 24th International Symposium on Distributed Simulation and Real Time Applications (DS-RT).

[9]  Manfred Morari,et al.  Dynamic Vehicle Redistribution and Online Price Incentives in Shared Mobility Systems , 2013, IEEE Transactions on Intelligent Transportation Systems.

[10]  Will Recker,et al.  Proactive vehicle routing with inferred demand to solve the bikesharing rebalancing problem , 2014 .

[11]  Christine Fricker,et al.  Incentives and redistribution in homogeneous bike-sharing systems with stations of finite capacity , 2012, EURO J. Transp. Logist..

[12]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[13]  Joseph P Schwieterman,et al.  E-Scooter Scenarios: Evaluating the Potential Mobility Benefits of Shared Dockless Scooters in Chicago , 2018 .