The NVIDIA Jetson-powered CUREE robot, developed by researchers from the Woods Hole Oceanographic Institution (WHOI) Autonomous Robotics and Perception Laboratory (WARPLab) and MIT, dives deep to study coral reefs as well as their ecosystems. CUREE (Curious Underwater Robot for Ecosystem Exploration) can collect visual, audio, and other environmental data alongside divers to help them better understand the human impact on reefs and the sea life around them.
CUREE runs on an NVIDIA Jetson-enabled edge AI to build 3D models of reefs and to track creatures, along with plant life. It’s capable of running models to navigate and collect data autonomously. The robot comes equipped with four forward-facing cameras, four hydrophones for underwater audio capture, depth sensors and inertial measurement unit sensors.
- NVIDIA GeForce RTX 3060 12GB GDDR6 dedicated graphics card
- 1710 MHz GPU clock speed and 1807 MHz memory clock speed
- DisplayPort x 3 (v1.4a) and HDMI 2.1 x 1 output interfaces
The problem is that, underwater, the snapping shrimps are loud. If only we could figure out an algorithm to remove the effects of sounds of snapping shrimps from audio, but at the moment we don’t have a good solution. We manually drive the vehicle until we see an animal that we want to track, and then we click on it and have the semi-supervised tracker take over from there,” said Yogesh Girdhar, an associate scientist at WHOI, who leads WARPLab.
[Source]
