New AI model is shockingly good at 'reading' human minds

(Web Desk) - Researchers from the Texas A&M University College of Engineering and the Korea Advanced Institute of Science and Technology have introduced a new artificial intelligence (AI) system called OmniPredict, designed to improve safety for self-driving cars.

OmniPredict is the first system to use a Multimodal Large Language Model (MLLM) to forecast how pedestrians may behave. It draws on the same kind of underlying technology used in advanced chatbots and image recognition, but its goal is different.

By pairing what it sees with contextual details, the system aims to predict, in real time, what a person is likely to do next.

Early testing has attracted attention, indicating that OmniPredict can deliver notably high accuracy even without specialized training.

“Cities are unpredictable. Pedestrians can be unpredictable,” said Dr. Srinkanth Saripalli, the project’s lead researcher and director of the Center for Autonomous Vehicles and Sensor Systems. “Our new model is a glimpse into a future where machines don’t just see what’s happening, they anticipate what humans are likely to do, too.”

As developers push to make autonomous driving safer, OmniPredict adds a new layer of street awareness that moves closer to human-like intuition.

Instead of only responding to a pedestrian’s current movement, it attempts to anticipate what that person will do next. If it works as intended, this approach could influence how autonomous vehicles operate in dense urban settings and navigate busy streets more smoothly.

“It opens the doors for safer autonomous vehicle operation, fewer pedestrian-related incidents and a shift from reacting to proactively preventing danger,” Saripalli said.

“We are opening the door for exciting applications,” Saripalli said. “For instance, the possibility of a machine to capably detect, recognize, and predict outcomes of a person displaying threatening cues could have important implications.”