Clone https://github.com/Zhehui-Huang/quad-swarm-rl into your home directory
Install dependencies in your conda environment
Note: if you have any error with bezier, run:
The environments can be run from the
quad_swarm_rl folder in the downloaded
quad-swarm-rl directory instead of from
Experiments can be run with the
train script and viewed with the
enjoy script. If you are running custom experiments, it is recommended to use the
quad_multi_mix_baseline runner script and make any modifications as needed. See
sf2_multi_drone runner scripts for an examples.
The quadrotor environments have many unique parameters that can be found in
quadrotor_params.py. Some relevant params for rendering results include
--quads_view_mode which can be set to local or global for viewing multi-drone experiments, and
--quads_mode which determines which scenario(s) to train on, with
mix using all scenarios.
- Comparison using a single drone between normalized (input and return normalization) and un-normalized experiments. Normalization helped the drones learn in around half the number of steps.
- Experiments with 8 drones in scenarios with and without obstacles. All experiments used input and return normalization. Research and development are still being done on multi-drone scenarios to reduce the number of collisions.
|HuggingFace Hub Models
|Single drone with normalization
|0.03 ± 1.86
|Multi drone without obstacles
|-0.40 ± 4.47
|Multi drone with obstacles
|-2.84 ± 3.71
Single drone with normalization flying between dynamic goals.