5 papers
Out of the Past: An AI-Enabled Pipeline for Traffic Simulation from Noisy, Multimodal Detector Data and Stakeholder Feedback
Rex Chen, Karen Wu, John McCartney +2
How can a traffic simulation be designed to faithfully reflect real-world traffic conditions? One crucial step is modeling the volume of traffic demand. But past demand modeling ap…
Making Teams and Influencing Agents: Efficiently Coordinating Decision Trees for Interpretable Multi-Agent Reinforcement Learning
Rex Chen, Stephanie Milani, Zhicheng Zhang +2
Poor interpretability hinders the practical applicability of multi-agent reinforcement learning (MARL) policies. Deploying interpretable surrogates of uninterpretable policies enha…
Missing Pieces: How Do Designs that Expose Uncertainty Longitudinally Impact Trust in AI Decision Aids? An In Situ Study of Gig Drivers
Rex Chen, Ruiyi Wang, Fei Fang +1
Decision aids based on artificial intelligence (AI) induce a wide range of outcomes when they are deployed in uncertain environments. In this paper, we investigate how users' trust…
Purpose in the Machine: Do Traffic Simulators Produce Distributionally Equivalent Outcomes for Reinforcement Learning Applications?
Rex Chen, Kathleen M. Carley, Fei Fang +1
Traffic simulators are used to generate data for learning in intelligent transportation systems (ITSs). A key question is to what extent their modelling assumptions affect the capa…
Understanding How to Inform Blind and Low-Vision Users about Data Privacy through Privacy Question Answering Assistants
Yuanyuan Feng, Abhilasha Ravichander, Yaxing Yao +4
Understanding and managing data privacy in the digital world can be challenging for sighted users, let alone blind and low-vision (BLV) users. There is limited research on how BLV…