Leveraging Autonomous Shared Vehicles for Greater Community Health, Equity, Livability, and Prosperity (HELP)
This Smart & Connected Communities (SCC) grant supports fundamental research on a critical challenge facing many cities and communities: how to leverage the emerging autonomous vehicles (AVs) to re-think and re-design future transportation services and enable smart and connected communities where everyone benefits. The research envisages an ambitious "smart cloud commuting system" (SCCS) based on giant pools of shared AVs. The envisaged SCCS has the potential to bring about far-reaching societal changes. It will provide inexpensive mobility services to all people especially people with socio-economic disadvantages, help build stronger family and community ties, and boost economic productivity and equity by mitigating or removing mobility constraints. The research will be carried out in conjunction with five community engagement pilot projects, directly contributing to US prosperity and well-being. The research involves multiple disciplines, including transportation, computer science, data science, operations research, urban design, and public policy. The multi-disciplinary approach will help broaden participation of underrepresented groups in research, and enrich students' educational experience across science, engineering, urban design, and public policy.
The goal of the project is two-fold: (1) to study the feasibility, economic viability, architectural and operational designs of the envisaged SCCS; and (2) to analyze the socioeconomic challenges in realizing the envisaged SCCS to serve communities with diverse socioeconomic backgrounds. In support of these goals, the project will leverage new and emerging data on travel demand, user preferences, and activity-travel constraints to quantify system efficiency gains that can be attained from time-sharing and intelligent control of AVs as well as from ride-sharing and smart trip scheduling of users. The research will also develop optimization models and algorithms that account for essential tradeoffs, including cost, quality of service, and congestion in deciding how best to deploy AVs geographically and temporally, leading to the identification of optimal AV fleet architectures and optimal operational policies. The research will also investigate, using micro-economic/game-theoretic analysis of the incentives of both users and service providers, likely scenarios of vehicle ownership and market structures and study the impact of each scenario on traffic measures including vehicle ownership and traffic volumes as well as societal measures including community health, equity, livability, and prosperity. This research will generate fundamental knowledge on the socioeconomic opportunities and impacts of the envisaged SCCS with shared AVs, and develop guidelines for adapting the design, deployment, and operation of AVs for future smart cities.
-
Performance PeriodSeptember 2018 - August 2022
-
University of Minnesota-Twin Cities
-
Award Number1831140
-
Lead PIZhi-Li Zhang
-
Co-PIYingling Fan
-
Co-PITom Fisher
-
Co-PISaif Benjaafar
-
Co-PIAlireza Khani
Project Material
- Towards an eBPF+XDP Based Framework for Open, Programmable and Scalable NextG RANs
- Kaala 2.0: Scalable IoT/NextG System Simulator
- 5GNN: extrapolating 5G measurements through GNNs
- NFlow and MVT Abstractions for NFV Scaling
- Taproot: Resilient Diversity Routing with Bounded Latency
- Accelerating Distributed Deep Learning using Multi-Path RDMA in Data Center Networks
- Integrating transit systems with ride-sourcing services: A study on the system users’ stochastic equilibrium problem
- Case for 5G-aware video streaming applications
- Towards a Software-Defined, Fine-Grained QoS Framework for 5G and Beyond Networks
- Adaptive Park-and-ride Choice on Time-dependent Stochastic Multimodal Transportation Network
- GlobeSnap: An Efficient Globally Consistent Statistics Collection for Software-Defined Networks
- An algorithm for integrating peer-to-peer ridesharing and schedule-based transit system for first mile/last mile access
- f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learning
- Parking infrastructure design for repositioning autonomous vehicles
- Lumos5G: Mapping and Predicting Commercial mmWave 5G Throughput
- xGAIL: Explainable Generative Adversarial Imitation Learning for Explainable Human Decision Analysis
- Curb-GAN: Conditional Urban Traffic Estimation through Spatio-Temporal Generative Adversarial Networks
- ST-SiameseNet: Spatio-Temporal Siamese Networks for Human Mobility Signature Identification
- Inferring Passengers’ Interactive Choices on Public Transits via MA-AL: Multi-Agent Apprenticeship Learning
- What is the Human Mobility in a New City: Transfer Mobility Knowledge Across Cities
- A First Look at Commercial 5G Performance on Smartphones
- Dynamic Public Resource Allocation Based on Human Mobility Prediction
- Discovering the Hidden Community Structure of Public Transportation Networks
- DHPA: Dynamic Human Preference Analytics Framework: A Case Study on Taxi Drivers’ Learning Curve Analysis
- Identifying Critical Links in Transportation Network Design Problems for Maximizing Network Accessibility
- Mining Spatio-temporal Reachable Regions With Multiple Sources over Massive Trajectory Data
- Transforming Policy via Reward Advancement
- Effective Recycling Planning for Dockless Sharing Bikes
- Unveiling Taxi Drivers' Strategies via cGAIL: Conditional Generative Adversarial Imitation Learning
- Imitation Learning from Human-Generated Spatial-Temporal Data
- TrafficGAN: Off-Deployment Traffic Estimation with Traffic Generative Adversarial Networks
- Forecasting Gathering Events through Trajectory Destination Prediction: a Dynamic Hybrid Model
- Operations Management in the Age of the Sharing Economy: What Is Old and What Is New?
- CB-Planner: A bus line planning framework for customized bus systems
- Interactive Bike Lane Planning using Sharing Bikes' Trajectories
Zhi-Li Zhang joined the faculty of the Department of Computer Science and Engineering at the University of Minnesota as an Assistant Professor in 1997. He is currently the Qwest Chair Professor in Telecommunications. He was named a Distinguished McKnight University Professor in 2013. Zhang received his M.S. degree (1993) and Ph.D. degree (1997) in computer science from the University of Massachusetts. He served as the Associate Director for Research at the Digital Technology Center, University of Minnesota from 2015 to 2021.