MIT engineers have unveiled MiFly, a state-of-the-art system empowering drones to navigate dark, indoor areas using millimeter-wave technology. This breakthrough could revolutionize logistics in low-visibility environments.
Researchers at MIT have developed MiFly, a revolutionary system allowing autonomous drones to self-localize in dark and indoor environments using millimeter-wave technology. This promising breakthrough could pave the way for efficient drone-based operations in diverse commercial settings, including large warehouses.
Traditional navigation methods such as GPS falter indoors, while computer vision and lidar fail in low visibility or featureless areas. However, MiFly employs radio frequency (RF) waves and just one small, low-cost tag to achieve precise localization.
“Here, we’ve looked beyond GPS and computer vision to millimeter waves, and by doing so, we’ve opened up new capabilities for drones in indoor environments that were not possible before,” senior author Fadel Adib, an associate professor in the Department of Electrical Engineering and Computer Science and director of the Signal Kinetics group at the MIT Media Lab, said in a news release.
The system leverages two commercial radars mounted on the drone itself. These radars work in tandem with the drone’s onboard sensors to estimate its six-degree-of-freedom pose — essential for accurate navigation.
The setup includes a horizontal and a vertical radar, each sending signals in different orientations. The reflected millimeter-wave signals, modulated to different frequencies to avoid environmental clutter, are analyzed to determine the drone’s exact location.
“Polarized sunglasses receive a certain polarization of light and block out other polarizations. We applied the same concept to millimeter waves,” co-lead author Maisy Lam, a research assistant, said in the news release.
Early tests have shown remarkable precision, with the drones localizing within 7 centimeters even in completely dark or cluttered indoor environments.
“Now, the reflections from the surrounding environment come back at one frequency, but the reflections from the tag come back at a different frequency. This allows us to separate the responses and just look at the response from the tag,” added co-lead author and research assistant Laura Dodds.
This new method, incorporating advanced radar and signal modulation techniques, opens up a range of potential applications. The flexibility and low-power requirements make it feasible for commercial implementation without extensive infrastructure.
“The infrastructure and localization algorithms we build up for this work are a strong foundation to go on and make them more robust to enable diverse commercial applications,” Lam concluded.
The research will be presented at the IEEE Conference on Computer Communications.
MIT’s breakthrough signifies a significant leap in drone navigation, potentially transforming industries reliant on logistics and inventory management.