Projects per year
Abstract
Mobility-on-demand systems consisting of shared autonomous vehicles (SAVs) are expected to improve the efficiency of urban mobility through reduced vehicle ownership and parking demand. However, several issues in their implementation remain open, such as unifying the vehicle and ride-sharing assignment with rebalancing non-occupied vehicles. Furthermore, proposed SAV systems are evaluated in isolation from other traffic; no congestion is taken into account when assigning requests or calculating routes. To address this gap, we present
Shared Autonomous Mobility-on-Demand system (SAMoD), a reinforcement learning-based approach to vehicle relocation and ride-sharing request assignment. Each vehicle learns its pick-up and rebalancing behaviour based on local current and observed historical demand. We evaluate SAMoD on Manhattan network using NYC taxi data in microsimulator SUMO. We investigate SAMoD performance in the presence of congestion generated by private vehicles, as well as investigate impact of different percentages of SAMoD vehicles in the system on overall traffic network performance
Shared Autonomous Mobility-on-Demand system (SAMoD), a reinforcement learning-based approach to vehicle relocation and ride-sharing request assignment. Each vehicle learns its pick-up and rebalancing behaviour based on local current and observed historical demand. We evaluate SAMoD on Manhattan network using NYC taxi data in microsimulator SUMO. We investigate SAMoD performance in the presence of congestion generated by private vehicles, as well as investigate impact of different percentages of SAMoD vehicles in the system on overall traffic network performance
Original language | English |
---|---|
Journal | IEEE Transactions on Intelligent Transportation Systems |
Publication status | Published - 15 Feb 2020 |
Keywords
- ride-sharing
- mobility-on-demand
- traffic congestion
- shared autonomous vehicles
Fingerprint
Dive into the research topics of 'Shared Autonomous Mobility-on-Demand: Learning-based approach and its performance in the presence of traffic congestion'. Together they form a unique fingerprint.Projects
- 1 Active
-
Spatial Policy and Analysis Laboratory and Research Group
Acheampong, R. A. (Researcher), Wong, C. (Researcher), Baker, M. (Researcher), Schulze Baing, A. (Researcher), Zheng, H. (Researcher), Agyemang, F. (Researcher), Pinto, N. (Researcher), Kingston, R. (Researcher), Deas, I. (Researcher), Koksal, C. (Researcher) & Zhang, A. (Researcher)
1/05/23 → …
Project: Research
-
Imagining urban mobility futures in the era of autonomous vehicles—insights from participatory visioning and multi-criteria appraisal in the UK and Australia
Acheampong, R. A., Legacy, C., Kingston, R. & Stone, J., Jun 2023, In: Transport Policy. 136, p. 193-208 16 p.Research output: Contribution to journal › Article › peer-review
Open AccessFile151 Downloads (Pure) -
Can autonomous vehicles enable sustainable mobility in future cities? Insights and policy challenges from user preferences over different urban transport options
Acheampong, R. A., Cugurullo, F., Dusparic, I. & Gueriau, M., 1 May 2021, In: Cities. 112, 103134.Research output: Contribution to journal › Article › peer-review
Open AccessFile1024 Downloads (Pure) -
Mobility and healthy ageing in the city: exploring opportunities and challenges of autonomous vehicles for older adults’ outdoor mobility
Zandieh, R. & Acheampong, R. A., May 2021, In: Cities. 112, 103135.Research output: Contribution to journal › Article › peer-review