Goto

Collaborating Authors

 help robot navigate


Sound location inspired by bat ears could help robots navigate outdoors

Engadget

Sound location technology has often been patterned around the human ear, but why do that when bats are clearly better at it? Virginia Tech researchers have certainly asked that question. They've developed a sound location system that mates a bat-like ear design with a deep neural network to pinpoint sounds within half a degree -- a pair of human ears is only accurate within nine degrees, and even the latest technology stops at 7.5 degrees. The system flutters the outer ear to create Doppler shift signatures related to the sound's source. As the patterns are too complex to easily decipher, the team trained the neural network to provide the source direction for every received echo.


The Secrets of Bat Echolocation Could Help Robots Navigate With Sound

#artificialintelligence

This Tech Note column appeared in the December 2020 issue as "Cut the Clutter." One rainy night in March 2007, graduate student Ralph Simon found himself alone in the Cuban rainforest. He was following a hunch, based on a picture he'd seen in a magazine. He was after a specific dish-shaped leaf, which belonged to the native Marcgravia evenia vine. The leaves looked like they'd be ideal for reflecting sound, and Simon suspected they would efficiently lure bat pollinators to their flowers in the dark.


Magnetic Control Could Help Robots Navigate Inside Your Body

IEEE Spectrum Robotics

There are two options for controlling a robot inside of the human body: Either you try and build some sort of intricate and tiny robot submarine with self contained propulsion and navigation, which would be really really hard to do, or you just make the robot with a tiny bit of something that responds to magnetic fields, and control it externally with some big magnets. The latter approach is vastly less complicated, but it has one major drawback, which is that it's very hard to manage multiple robots. Here's the problem: Magnetic fields, being fields, aren't easily constrained to specific areas. Realistically, if you're using something like a clinical MRI scanner to create a magnetic field, whatever gradient you give the field will affect everything inside of the MRI, whether you've got one single microbot or a vast swarm of them. If you want two different robots to do two different things, you're out of luck.