Inspired by Bats, New Drones Use Ultrasonic Technology to Navigate
Using nature as a model, researchers decided to incorporate ultrasound sensors to enable tiny drones to navigate under difficult conditions.
Edited by Terry Persun
Cool Stuff
Jul 7, 2026
Aerospace
Palm-sized drones use ultrasound sensors and a unique form of artificial intelligence to navigate through fog, smoke, and other challenging environmental conditions using limited power. A team led by Worcester Polytechnic Institute (WPI) researcher and assistant professor in the Department of Robotics Engineering, Nitin J. Sanket, has approached drone technology in a new way.
Inspired by how bats use sound to navigate and hunt, this advanced approach indicates that ultrasound may be a relevant alternative to existing navigation technologies that add weight and cost to a drone that may also falter when used under poor environmental conditions. Bats can accurately navigate in dark, damp, and dusty caves by sending out short chirps and listening to the weak echoes.
According to Sanket, “By creating an ultrasound-based system that needs just two tiny sensors and little computation, we can open up opportunities for small aerial robots to perceive their surroundings, make decisions, and independently operate longer in cluttered, hazardous places where current aerial robots struggle.” These drones are perfect for search-and-rescue operations under highly limited conditions.
Sanket’s research focuses on robotics inspired by nature, such as bees and bats. The work featured in Science Robotics was supported by a grant from the National Science Foundation. Most other autonomous drones use sensors, controllers, cameras, a power source, and sophisticated algorithms to perceive their surroundings and make navigational decisions. Some even collect landscape data by analyzing radio waves or light pulses. These methods are power intensive and costly. Plus, darkness, poor weather, and propeller noise can interfere with their operation. All of this takes time and energy.
The team led by Sanket customized an X-shaped aerial quadrotor drone about six inches wide with ultrasound sensors and a physical barrier call an acoustic shield to dampen propeller noise. Through deep learning techniques, the team trained the device’s computer to analyze weak echo patterns similar to how a bat brain processes sound to decipher echoes.
The drone, weighing about one pound, was tested outdoors in a wooded area and indoors in a laboratory furnished with obstacles such as transparent plastic or metal poles. Some indoor tests took place in darkness with black obstacles, while others took place as the researchers blew fog or snow onto the obstacle course. The drone had enough battery power to operate for about five minutes per flight while navigating the course autonomously.
The researchers reported that the robot had a success rate of between 72- and 100-percent in navigating through challenging courses during 180 tests. The drone was less successful at dodging thin objects, such as metal poles, and it struggled to avoid slender tree branches, which weakly reflected signals.
Future work includes using smaller, lighter devices that could fly longer and improve flight speeds. “In a real search-and-rescue mission, a few more seconds of flight time could mean the difference between life and death for a survivor,” Sanket said.
Co-authors with Sanket on the research team included, Manoj Velmurugan, MS ’25; Phillip Brush ’24, MS ’25; Colin Balfour ’26, MS ’27; and Richard Przybyla of TDK InvenSense, Berkeley, Calif.
The next step for bat-inspired drones may be to use smaller, lighter devices that could fly longer using the team’s low-power ultrasound-based system, Sanket said. Future work could also improve flight speeds.
For information:
Worcester Polytechnic Institute