AI models struggle to accurately predict social interactions

Technology
Humans outperform current AI models in accurately describing and interpreting social interactions
(Web Desk) - Johns Hopkins study reveals AI models struggle to accurately predict social interactions.
A recent study led by researchers at Johns Hopkins University reveals that humans outperform current AI models in accurately describing and interpreting social interactions within dynamic scenes. This capability is critical for technologies such as autonomous vehicles and assistive robots, which rely heavily on AI to safely navigate real-world environments.
The research highlights that existing AI systems struggle to grasp the nuanced social dynamics and contextual cues essential for effectively interacting with people. Furthermore, the findings suggest that this limitation may stem fundamentally from the underlying architecture and infrastructure of current AI models.
“AI for a self-driving car, for example, would need to recognize the intentions, goals, and actions of human drivers and pedestrians. You would want it to know which way a pedestrian is about to start walking, or whether two people are in conversation versus about to cross the street,” said lead author Leyla Isik, an assistant professor of cognitive science at Johns Hopkins University. “Any time you want an AI to interact with humans, you want it to be able to recognize what people are doing. I think this sheds light on the fact that these systems can’t right now.”
Kathy Garcia, a doctoral student working in Isik’s lab at the time of the research and co–first author, recently presented the research findings at the International Conference on Learning Representations on April 24.
The research highlights that existing AI systems struggle to grasp the nuanced social dynamics and contextual cues essential for effectively interacting with people. Furthermore, the findings suggest that this limitation may stem fundamentally from the underlying architecture and infrastructure of current AI models.
“AI for a self-driving car, for example, would need to recognize the intentions, goals, and actions of human drivers and pedestrians. You would want it to know which way a pedestrian is about to start walking, or whether two people are in conversation versus about to cross the street,” said lead author Leyla Isik, an assistant professor of cognitive science at Johns Hopkins University. “Any time you want an AI to interact with humans, you want it to be able to recognize what people are doing. I think this sheds light on the fact that these systems can’t right now.”