Researchers from the Massachusetts Institute of Technology have developed a new algorithm with the ability to control drone swarms. It is a planning algorithm that takes stationary as well as moving obstacles into account.
“The algorithm is for mission control, and it is designed to control how a team of robots move in a coordinated way,” said Javier Alonso-Mora, postdoctoral associate at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL).
According to the researchers, planning algorithms can be either centralized or decentralized. With centralized planning algorithms, one computer makes all the decisions for the team of robots. Decentralized planning algorithms let each robot make decisions based on their own individual observations. The researchers went with a decentralized algorithm because of its ability to handle irregular patterns and collective decision-making, according to Alonso-Mora.
The algorithm also aims to avoid collisions using less communication bandwidth. The researchers tested the algorithm with a team of unmanned vehicles that were able to follow through flight plans and adjust based on obstacles.
“It’s a really exciting result because it combines so many challenging goals,” said Daniela Rus, director of CSAIL. “Your group of robots has a local goal, which is to stay in formation, and a global goal, which is where they want to go or the trajectory along which you want them to move. And you allow them to operate in a world with static obstacles but also unexpected dynamic obstacles, and you have a guarantee that they are going to retain their local and global objectives. They will have to make some deviations, but those deviations are minimal.”