The research team has developed an AI chip which makes it possible to use hand gestures and an image sensor to operate a drone
Professors at the National Tsing Hua University Tang Kea-tiong and Lo Chung-chuan have recently developed an AI chip that mimics the optical nerves of the fruit fly.
Intrigued by the fruit fly’s ability to avoid obstacles, Tang realized it might be possible to replicate the optical nerve of the tiny insect and adapt it to AI applications. The researchers believe drones could automatically avoid obstacles while remaining in an ultra-power-saving mode.
Firstly, the researchers had to solve the problem of information overload. According to Tang, the image sensor currently used in cameras and mobile phones have millions of pixels, whereas the eye of a fruit fly has only about 800 pixels.
When the fruit fly’s brain processes visual signals, it uses a kind of detection mechanism which automatically filters out unimportant data.
According to the information, the drone is taught to focus on what’s most important, and then it’s taught how to judge distance and the likelihood of a collision.
Earlier, Lo conducted an investigation on how the fruit fly detects optical flow. For this purpose, he made extensive use of the fruit fly’s neural pathways maps produced by the Brain Research Center at NTHU.
- How technologies will transform cities
- 10 cutting-edge solutions presented at CES 2019
- Top 10 uses for drones