Autonomous vehicles could understand their passengers better with ChatGPT
Briefly

Conducting a new kind of study, researchers found that using AI chatbots allows a vehicle to interpret vague commands and navigate efficiently, enhancing the autonomous experience for users. The vehicles of the future may communicate more naturally, understanding commands like 'I'm in a hurry' without needing explicit directions.
Ziran Wang emphasized that true autonomy requires vehicles capable of comprehending implied commands from passengers, reminiscent of a human driver’s instinctive navigation. Current systems are overly dependent on explicit user input, which limits passenger experience.
Wang remarked on the limitations of existing systems that demand specific interaction, saying, 'The conventional systems in our vehicles have a user interface design where you have to press buttons to convey what you want.' This highlights the shift needed towards more intuitive AI interpretations.
He explained how large language models offer a breakthrough, noting, 'But the power of large language models is that they can more naturally understand all kinds of things you say.' This indicates potential for a seamless interaction between passengers and vehicles.
Read at ScienceDaily
[
|
]