Experiment on quadrotor tracking a target ball using only a 64×64 image
What happened
Guyuehome published a tutorial on loading the official pretrained policy in Isaac Lab to make a quadrotor track a yellow target ball using only a 64×64 camera image. According to the tutorial, in the experiment the target visibility rate was about 40%, and after losing the target the aircraft can autonomously hover in place to search for it again. The tutorial also discusses known gaps when transferring this policy to a real DJI Tello, but does not provide real-world tracking results.
AI 根据报道生成 · 5 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- GuyuehomeDeep reinforcement learning-based quadrotor target tracking control: experiments with 64×64 visual input in Isaac Lab
A quadrotor tracks a yellow target ball using only a 64×64 camera image. The official pretrained policy was loaded to complete tracking experiments in Isaac Lab, with the target visible about 40% of the time and the quadrotor autonomously hovering to reacquire the target after losing it. The article also discusses known gaps when migrating the policy to the DJI Tello.
Activity for this event
- Current
- 3
- Peak
- 9Nov 5 22:00
- Past 24 hours
- -50%
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.