(Teaching kites to fly using) Reinforcement Learning

[Windy_Skies]

Using something like Tesla FSD to fly a kite

Continuing the discussion from Random Engineering, Physics, …, Concepts and Ideas:

Using something like Tesla FSD to fly a kite

I experimented with a neural network to steer the kite for the first AWE system I developed. (Supervised learning). It did work, but didn’t really provide any benefits (in my case) beyond traditional path planning and actuator control. [Kite On Its Own Succesful Flight] http://legacy.kitex.tech/prototypes/AK002-first-self-flying-kite/ The network: https://github.com/aokholm/KiteXMissionControl/blob/master/src/ai.js We have considered using reinforcement learning to optimise the c…

Using something like Tesla FSD to fly a kite

The software Ampyx presented at AWEC2019 had a whole load of sensing, smarts, redundant levels, sanity checks. I think it was able to adapt it’s working model to multiple simultaneous flaws and was able to recover the plane from serious failures, tangles and inversions. The software seemed to have been planned and written meticulously. Such a shame there’s still no sign of that video on AWEC2019 videos - #49 by rschmehl Couple more videos still missing there too…