Skip to content

About

Task-specific performance guided multirotor design optimization using RL, Bayesian Optimization, and CMA-ES to optimize design directly from flight performance feedback, under physical feasibility constraints.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

Performance-guided Task-specific Optimization for Multirotor Design

Code for Arza et al., Performance-guided Task-specific Optimization for Multirotor Design. This repository is a more efficient rewrite in Newton of the methodology. Getting the result below (evaluating 800 designs + baselines) took 27 h on one RTX 5090 GPU.

Optimized hexarotor (green) flying through gates next to four baseline hexarotors

Setup

You need Linux and an NVIDIA GPU with driver ≥ 580 (the environment installs PyTorch built for CUDA 13.0). Install Miniconda if you don't have conda:

wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh -b -p ~/miniconda3
~/miniconda3/bin/conda init bash
source ~/.bashrc

Then,

git clone https://github.com/ntnu-arl/task-specific-multirotor-optimization.git
cd task-specific-multirotor-optimization
conda env create -f environment.yml
conda activate multirotor-opt

The first run compiles the Warp kernels, which takes a minute.

Usage

Run all commands from the repository folder with the environment active (run conda activate multirotor-opt to activate the environment).

Optimize a design

python evolve.py --run-dir results/myrun                                  # the paper's budget: 400 BO + 400 CMA-ES.
python evolve.py --run-dir results/test --bo-evals 40 --cma-evals 40     # a short test run that should finish in a few hours.

This optimizes for task B of the paper. For task A, set TASK=A on every command of the run (the default budget and seed are the same):

TASK=A python evolve.py --run-dir results/task_A

This should produce results/<run>/ which contains:

File Contents
progress.csv, evaluations.jsonl one line per evaluated design
progress.pdf fitness over evaluations and time
final_design.json the final design
final_comparison.mp4, final_report.pdf, final_metrics.json video and report of the final design against the baselines

A run interrupted after its BO goes on in its own folder (with the same TASK):

python evolve.py --run-dir results/myrun --resume

Evaluate and render one design

python render_evaluation.py --design results/myrun/final_design.json --out results/myrun/render
python render_evaluation.py --design planar --out results/renders/planar   # or franchi, rajappa, shen

Compare designs

python compare.py --out results/compare --seeds 8 --seed 1 \
    --designs planar franchi rajappa shen paper results/myrun/final_design.json

Trains every design 8 times from scratch (sequential halving each time) and evaluates each picked policy on 40960 episodes. paper is the optimized task B design reported on the paper obtained in the legacy codebase.

Troubleshooting

Out of memory error.

With the current setup, rl.py trains 80 controllers at once (TRAIN_CHUNK), which needs about 14 GB of GPU memory. On a smaller GPU, set it lower. It is slower, and the results could change with different parameters.

TRAIN_CHUNK=20 python evolve.py --run-dir results/myrun

Citation

@misc{arza2025performance,
  title         = {Performance-guided Task-specific Optimization for Multirotor Design},
  author        = {Etor Arza and Welf Rehberg and Philipp Weiss and Mihir Kulkarni and Kostas Alexis},
  year          = {2025},
  eprint        = {2510.04724},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url           = {https://arxiv.org/abs/2510.04724}
}

About

Task-specific performance guided multirotor design optimization using RL, Bayesian Optimization, and CMA-ES to optimize design directly from flight performance feedback, under physical feasibility constraints.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages