Welcome to EC-RIDER

Explainable AI Methods for Human-Centric Shared Mobility Services

The EC-RIDER research project studies socio-technical challenges that hamper sustainable shared urban mobility. An explainable, human-centric AI-enabled approach is proposed for tackling hard coordination and optimization problems in flexible on-demand ridesharing (including and combining carpooling and ridehailing). Our novel focus is on maximizing user satisfaction while respecting overarching societal goals and constraints. Towards this end, we argue that it is vital to provide affected users with adequate explanations for decisions made by the abovementioned AI algorithms.

While our focus is on applications in the area of shared mobility, we follow a “design-for generalizability” approach fuelled by the expectation that some key problems, models and methods (e.g. linking explanation and feedback with AI optimization algorithms) generalize beyond ridesharing and can cross-fertilize a wide range of future “AI for social good” applications, e.g., in healthcare, education and intelligent tutoring, gaming, planning and scheduling, or dating/matchmaking.

EC-RIDER is supported by Volkswagen Foundation through a Planning Grant in the Artificial Intelligence and the Society of the Future programme.       

Recent research activities

Winner of Blue Sky Award at the AAAI-20 Senior Member Presentation Track


We are happy to announce that our paper "AI for Explaining Decisions in Multi-Agent Environments" accepted for  the AAAI-20 Senior Member Presentation Track has been honored with the Blue Sky Award sponsored by the Computing Community Consortium (CCC).

S. Kraus, A. Azaria, J. Fiosina, M. Greve, N. Hazon, L. Kolbe, T.Lembcke, J. P. Müller, S. Schleibaum, M. Vollrath. (2020) AI for Explaining Decisions in Multi-Agent Environments, Blue Sky Paper, AAAI 2020 : The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 (accepted) (Preprint)

 

Presentation of the EC-RIDER project at kick-off Symposium "AI and the Society of the Future"


On November 7 and 8, 2019, we presented the results of the EC-RIDER Planning Grant project and the concept of the Full Grant Proposal in a Lightning Talk and a Poster session  at the Kick-off Symposium "AI and the Society of the Future"  in Hannover Herrenhausen Palace.

Joint paper: AI for Explaining Decisions in Multi-Agent Environments


A joint paper by the consortium has been accepted for publication in the Senior Member Track at AAAI'2020.

Starting from the observation that generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: Explainable decisions in Multi-Agent Environments (xMASE). We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from decisions of AI systems taken in multi-agent environments.

 

S. Kraus, A. Azaria, J. Fiosina, M. Greve, N. Hazon, L. Kolbe, T.Lembcke, J. P. Müller, S. Schleibaum, M. Vollrath. (2020) AI for Explaining Decisions in Multi-Agent Environments, Blue Sky Paper, AAAI 2020 : The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 (accepted) (Preprint)

 

Joint study and paper on user preferences in ridesharing


We have carried out joint research combining a literature study with an online survey. Results of the literature survey indicate that, while there is a considerable body of research on users preferences related to shared mobility, a comprehensive account on the preferences relevant for assigning travellers or drivers to vehicles, to each other, and to routes is missing. We therefore devised an online survey covering (1) present and future usage of ridesharing, (2) preferences of passengers, and (3) information relevant for ride-matching algorithm.

Support EC-RIDER by participating in the survey! (English version, German version; Hebrew version to come ...)

Schleibaum, S.; Greve, M.; Lembcke T.-B; Azaria, A.; Fiosina, J.; Hazon N.; Kolbe, L.; Kraus, S.; Müller J.P.; Vollrath, M. (2020). How did you like this ride? An analysis of user preferences in ride-sharing assignments(Preprint).

Recent conference organization activities


Prof. Sarit Kraus has served as the Program  Chair at  the 28th International Joint Conference on Artificial Intelligence (IJCAI 2019).

Prof. Jörg P. Müller has served as IJCAI 2019 Demonstration Track Co-Chair.

FAMAS@AAMAS 2019: Presentation on fair allocation of ridesharing cost


Dr. Noam Hazon and Dr. Amos Azaria from Ariel University presented a paper associated with the project at the International Workshop on Fair Allocation in Multiagent Systems (FAMAS) held at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2019.

Chaya Levinger, Noam Hazon and Amos Azaria. Cost Allocation for Prioritized Ridesharing. Fair Allocation in Multiagent Systems Workshop (FAMAS), 2019

ABMUS@AAMAS 2019: Presentation on human-centric ridesharing


Dr. Noam Hazon and Dr. Amos Azaria from Ariel University presented a paper associated with the project at the 4th International Workshop on Agent-Based Modelling of Urban Systems (ABMUS-2019) held in conjunction with the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2019.

Chaya Levinger, Noam Hazon and Amos Azaria. A Method for Maximizing Human Satisfaction in Ridesharing. The 4th International Workshop on Agent-Based Modelling of Urban Systems (ABMUS-2019), 2019