Students from the University of Buffalo’s SMART Motion Capture Lab create a simulated environment to show how autonomous air and ground robots can operate alongside each other. (Image Credit: Douglas Levere/University of Buffalo)
Studying brainwaves and eye movement of gamers might be a key factor in improving robot swarm technology for the military. Researchers from the University of Buffalo’s Artificial Intelligence Institute have received a $316,000 grant from DARP for this new study. The goal is to improve strategy and organization for both air and ground robots.
Even though swarm robotic research is usually inspired by nature, such as ant colonies and schooling fish, researchers believe that AI systems can be improved through humans. The study focuses on real-time strategy games similar to StarCraft, Stellaris and Company of Heroes, which are time-based and involve using resources to build units and defeat opponents.
“The idea is to eventually scale up to 250 aerial and ground robots, working in highly complex situations. For example, there may be a sudden loss of visibility due to smoke during an emergency. The robots need to be able to effectively communicate and adapt to challenges like that,” says the grant’s principal investigator, Souma Chowdhury, assistant professor of mechanical and aerospace engineering, School of Engineering and Applied Sciences.
The students involved in the study will be playing a basic real-time strategy game developed by the research team. While recording every decision a gamer makes, the researchers will also track their eye movements using high-speed cameras and monitor their brain activity through electroencephalograms.
Afterward, from the collected data, the researchers will build new artificial intelligence algorithms that will guide autonomous air and ground robots for the military.
“We don’t want the AI system just to mimic human behavior; we want it to form a deeper understanding of what motivates human actions. That’s what will lead to more advanced AI,” Chowdhury says.
The researchers will eventually merge and evaluate artificial intelligence they create into more advanced virtual environments developed by DARPA’s partner organization.
“This project is one example of how machine intelligence systems can address complex, large-scale heterogeneous planning tasks, and how the University at Buffalo Artificial Intelligence Institute is tackling fundamental issues at the forefront of AI,” says Doermann.
Have a story tip? Message me at: cabe(at)element14(dot)com