A novel, human-inspired approach to training artificial intelligence systems to identify objects and navigate their surroundings could set the stage for the development of more advanced AI systems to explore extreme environments or distant worlds, according to new research.
"Current approaches in AI use massive sets of randomly shuffled photographs from the internet for training. In contrast, our strategy is informed by developmental psychology, which studies how children perceive the world," said Lizhen Zhu, the lead author and doctoral candidate in the College of Information Sciences and Technology at Penn State.
The scientists created three simulation environments -- House14K, House100K and Apartment14K, with '14K' and '100K' referring to the approximate number of sample images taken in each environment. Then they ran base contrastive learning models and models with the new algorithm through the simulations three times to see how well each classified images. The team found that models trained on their algorithm outperformed the base models on a variety of tasks.
"This approach would be particularly beneficial in situations where a team of autonomous robots with limited resources needs to learn how to navigate in a completely unfamiliar environment," Wang said."To pave the way for future applications, we plan to refine our model to better leverage spatial information and incorporate more diverse environments."