Playing urban mobility games with intelligent machines. Framework to discover and mitigate human-machine conflicts.
The COeXISTENCE project explores AI's impact on urban mobility, aiming to identify and mitigate conflicts between machine-driven decisions and human travel needs through multi-objective reinforcement learning.
Projectdetails
Introduction
AI-driven technologies are ready to enter urban mobility. They promise relief to the notoriously congested transport systems in pursuing sustainability goals. Since AI already outperforms humans in the most complex games (chess and Go), it is likely to win the urban mobility games as well, outperforming us in:
- Route choices (to arrive faster)
- Mode choices (to reduce costs)
- Pricing strategies
- Fleet management (to increase market shares and profits)
This tempts us and policymakers to gradually hand over our decisions to intelligent machines.
Challenges of the Revolution
The consequences of this ongoing revolution are challenging to predict and largely unknown. While the abundance of previous studies proves the positive potential of AI in urban mobility (from autonomous vehicles to optimal routing and fleet management), the negative impact is often overlooked.
Conversely, our scenario of interest is the machine-dominated urban mobility system, where (collective) decisions of machine intelligence improve system-wide performance, yet at the cost of humans. This may lead to:
- Longer travel times
- Greater monetary costs
- Nudging individuals to change natural travel habits into the optimal ones desired by the machine-centered system
Exploration of Scenarios
Such scenarios, however, need to be discovered. To this end, COeXISTENCE embarks on an interdisciplinary expedition inside the virtual environment of urban mobility, where machines and humans play the game for limited resources.
In the four pre-identified games, I will:
- Explore the conflict scenarios
- Demonstrate them on reproducible case studies
- Quantify with proposed measures
- Mitigate with a proposed multi-objective reinforcement learning framework, where machines learn to mitigate conflicts while simultaneously reaching their inherently selfish objectives.
Conclusion
Reaching the project's objectives will be groundbreaking when new phenomena are discovered and lead to breakthroughs when they are mitigated, pushing the system towards the synergy of COeXISTENCE.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 1.494.405 |
Totale projectbegroting | € 1.494.405 |
Tijdlijn
Startdatum | 1-3-2023 |
Einddatum | 29-2-2028 |
Subsidiejaar | 2023 |
Partners & Locaties
Projectpartners
- UNIWERSYTET JAGIELLONSKIpenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Urban scAInce: why and how cities transform through artificial intelligence and their associated technologiesThe project aims to assess the impact of AI and smart technologies on urban sustainability by correlating historical data, evaluating AI solutions, and creating a virtual open science city for collaborative change. | ERC Consolid... | € 1.998.348 | 2023 | Details |
Intuitive interaction for robots among humansThe INTERACT project aims to enable mobile robots to safely and intuitively interact with humans in complex environments through innovative motion planning and machine learning techniques. | ERC Starting... | € 1.499.999 | 2022 | Details |
Artificial UserThis project aims to enhance human-computer interaction by developing a simulator that autonomously generates human-like behavior using computational rationality, improving evaluation methods and data generation. | ERC Advanced... | € 2.499.208 | 2024 | Details |
Explaining human decision-making by combining choice and process dataIMMERSION aims to enhance understanding of human decision-making by developing innovative methods to integrate choice and process data for real-world applications in transportation systems. | ERC Starting... | € 1.500.000 | 2024 | Details |
Choice, necessity or chance? Understanding behaviouR chanGE iN TransportURGENT aims to enhance understanding of mobility behavior change through interdisciplinary analysis of individual and contextual factors, using longitudinal data to inform effective transport intervention strategies. | ERC Consolid... | € 1.936.613 | 2022 | Details |
Urban scAInce: why and how cities transform through artificial intelligence and their associated technologies
The project aims to assess the impact of AI and smart technologies on urban sustainability by correlating historical data, evaluating AI solutions, and creating a virtual open science city for collaborative change.
Intuitive interaction for robots among humans
The INTERACT project aims to enable mobile robots to safely and intuitively interact with humans in complex environments through innovative motion planning and machine learning techniques.
Artificial User
This project aims to enhance human-computer interaction by developing a simulator that autonomously generates human-like behavior using computational rationality, improving evaluation methods and data generation.
Explaining human decision-making by combining choice and process data
IMMERSION aims to enhance understanding of human decision-making by developing innovative methods to integrate choice and process data for real-world applications in transportation systems.
Choice, necessity or chance? Understanding behaviouR chanGE iN Transport
URGENT aims to enhance understanding of mobility behavior change through interdisciplinary analysis of individual and contextual factors, using longitudinal data to inform effective transport intervention strategies.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Serious and escape games in virtual reality to improve the capacity of decision makers and citizens for the implementation of air quality plans and actionsThe LIFE V-Air project aims to enhance air quality awareness and decision-making through gamification and VR tools, engaging citizens and policymakers to visualize impacts and drive effective actions. | LIFE Standar... | € 754.479 | 2022 | Details |
AR Urban LegendsHet project onderzoekt de commerciële mogelijkheden van AR Urban Legends, een tool voor urban sports, om een community op te bouwen. | Mkb-innovati... | € 20.000 | 2021 | Details |
AI-based simulator voor CO2-uitstoot van mobiliteitStraTopo ontwikkelt een AI-simulator om CO2-uitstoot van mobiliteit te berekenen, ter ondersteuning van beleidsmakers bij stedelijke ontwikkeling. | Mkb-innovati... | € 20.000 | 2022 | Details |
Project MITH2020 Convious - Crowd controlConvious ontwikkelt een AI-oplossing voor crowd control om bezoekersstromen te optimaliseren, de veiligheid te verhogen en de bezoekerservaring te verbeteren. | Mkb-innovati... | € 20.000 | 2020 | Details |
Take 5 technologische innovaties voor leiderschapsgameTake 5 is een mobiel leiderschapsspel dat AI gebruikt voor adaptieve training, waarbij spelers in vijf minuten vaardigheden oefenen en direct toepassen in realistische situaties. | Mkb-innovati... | € 122.500 | 2019 | Details |
Serious and escape games in virtual reality to improve the capacity of decision makers and citizens for the implementation of air quality plans and actions
The LIFE V-Air project aims to enhance air quality awareness and decision-making through gamification and VR tools, engaging citizens and policymakers to visualize impacts and drive effective actions.
AR Urban Legends
Het project onderzoekt de commerciële mogelijkheden van AR Urban Legends, een tool voor urban sports, om een community op te bouwen.
AI-based simulator voor CO2-uitstoot van mobiliteit
StraTopo ontwikkelt een AI-simulator om CO2-uitstoot van mobiliteit te berekenen, ter ondersteuning van beleidsmakers bij stedelijke ontwikkeling.
Project MITH2020 Convious - Crowd control
Convious ontwikkelt een AI-oplossing voor crowd control om bezoekersstromen te optimaliseren, de veiligheid te verhogen en de bezoekerservaring te verbeteren.
Take 5 technologische innovaties voor leiderschapsgame
Take 5 is een mobiel leiderschapsspel dat AI gebruikt voor adaptieve training, waarbij spelers in vijf minuten vaardigheden oefenen en direct toepassen in realistische situaties.