Projects

Investigating Sidewalks’ Mobility and Improving it with Robots (ISMIR)
Funded by Digital Futures
2023-2025

A crucial task of the project will focus on integrating prediction models with routing algorithms to discover more effective routing solutions. Another task will involve identifying Walkability KPIs” to describe sidewalk mobility conditions based on the data collected.
Based on empirical data from sidewalk robots’ trips, we will shed light on sidewalk mobility and improve real-world robot delivery operations. Through statistical analysis and Machine Learning (ML), we will assess the efficiency of robots’ paths and its relation to pedestrian infrastructure, interactions with different transport users (such as walkers, cyclists, e-scooters, and motorized vehicles), and other variables (e.g., weather).

Congestion Pricing of the Future: Investigating and Harnessing the Effectsof Shared Autonomous Vehicles
Funded by Trafikverket (Swedish Transport Administration)
2023-2025

This project aims to investigate congestion pricing in future Swedish mobility scenarios involving shared autonomous vehicles (SAVs). Introducing SAVs will alter our transportation systems in terms of travel costs, traffic operations, and travel behavior, ultimately affecting traffic congestion, safety, air pollution, and accessibility. As a result, the (economic) efficiency and effectiveness of well-known policy instruments, like congestion pricing, may differ from the current state. Future congestion pricing schemes must consider how SAVs may affect inequalities among transportation system users (i.e., different socio-demographic groups). So far, despite the significant research effort to predict future systems with connected and automated driving, limited emphasis has been placed on their policy implications from a socioeconomic perspective.
The project will use an agent-based activity-based model to investigate various congestion pricing strategies (e.g., cordon-based, area-based, and distance-based tolls) in potential SAV scenarios for two Swedish regions: Stockholm and Umeå.

WAlking and PArking Dynamics of Drivers (WAPADD): Analysis and Model Development for Sustainable Urban Delivery
Funded by Vinnova (Sweden’s innovation agency)
2024-2025

The project addresses the critical but often overlooked aspects of delivery drivers’ walking and parking behaviors in urban logistics. With 80% of a delivery driver’s time spent outside the vehicle during the last leg of delivery, comprehending these dynamics becomes pivotal for sustainable urban delivery routes. For the first time, KTH Royal Institute of Technology (Sweden) and the University of Washington (US) will work together to address this challenge, with the support of two established logistics companies, UPS (US) and Widriksson Logistik (Sweden), as well as input from Seattle and Stockholm planning agencies.

SPARA: Spatiotemporal Distribution Flexibility for Resource-Efficient Last-Mile Logistics
Lead by Linköping Universitet-Funded by Energimyndigheten (Sweden’s Energy Agency)
2024-2027

This project aims to enhance resource efficiency and reduce climate impact in urban last-mile deliveries. Addressing both business-to-business and business-to-consumer deliveries, the project will identify, analyze, and evaluate strategies to make last-mile distribution more sustainable. A key component of the project is the introduction of spatiotemporal delivery flexibility, i.e. flexibility in both delivery time and location, to reduce environmental impact in last mile deliveries. By leveraging machine learning, the project seeks to optimize routes and consolidate deliveries to improve transport efficiency. A close collaboration between actors in the last mile supply chain as well as academic partners will support the development of innovative solutions targeting increased resource efficiency and reduced environmental impact.

Traffic Simulation and Optimization

Dynamic traffic simulation represents a valuable resource for the evaluation of congestion phenomena and design of traffic management measures. In large traffic networks, efficient and accurate models are critical for the development of effective Intelligent Transportation Systems (ITS) solutions. Some of my current projects involve: surrogate model-based curbside management, traffic state estimation with dashboard cams, reinforcement learning via geofencing, and parking management for urban freight deliveries.