We built a drone + dock system that captures inventory intelligence while living permanently inside deep freezer warehouses, all the way down to -20°F (-29°C).
These sub-zero facilities are critical infrastructure for the global supply chain - delivering things like ice cream, meat, eggs, milk, and cheese (and a lot more!) to your local supermarket. (1/x)
very rewarding to have made reliable, infrastructure-free, vision-only drone autonomy a reality with the team at @CorvusRobotics
this, and zero-intervention robotics generally, is a hard problem that I have been working on since @BYU and @MIT.
We cooked! more soon...
2. Get tons of robots permanently living out in the field (well beyond PoCs and pilots), and survive long enough to take advantage of the network effects from them.
(data mine for on-policy failures from the field -> make real progress on solving the long tail -> get enough 9s of reliability to become super sticky in customer workflows)
Spoiler: making indoor GPS-denied autonomous drones operate in really dirty and complex environments for months and months turned out to be really hard. Many had tried and failed before us, and the path to success was not clear at the outset.
(3/x)
About 8 years ago, we started @CorvusRobotics from my dorm room in @MIT - building camera-based autonomous flying robots for capturing inventory data in large industrial warehouses and factories.
This big vision was great, but actually executing on it was extremely nonlinear - the highs were very high, and the lows were veryyy low. We finally feel ready to tell our story now, after having some commercial success under our belts.
At minimum, we hope you get a chuckle out of it – and at best, we hope to inspire other builders in HW/robotics to keep going, even when you really feel like giving up.
(1/x)
8 years of building an autonomous robotics company in ~60 seconds.
Cursing, crashes, breakthroughs -- and a lot of robots in the supply chain.
Here’s why we chose this as our life’s work. (1/5)