Website

1. If you are using a Python virtual environment, edit setup.bash to point to the activate script of the virtual environment. One way to do that is:

python3_ver () 
{ 
    python3 -V 2>&1 | sed -e 's/.*3.\([0-9]\).*/py3\1/'
}
mkdir -p .tox/
virtualenv --python=python3 .tox/$(python3_ver)

2. Install gurobi. Edit setup.bash to set GUROBI_LIB_PATH

3. Activate environment and install current package in edit mode

source setup.bash
pip install -e .

pytest

1. To run experiment where unicycle with mean CBF collides with the obstacle run

   python -c 'from bayes_cbf.unicycle_move_to_pose import unicycle_mean_cbf_collides_obstacle; unicycle_mean_cbf_collides_obstacle()'

   

2. To run experiment where unicycle with Bayes CBF drives safely between the obstacles

   python -c 'from bayes_cbf.unicycle_move_to_pose import unicycle_bayes_cbf_safe_obstacle; unicycle_bayes_cbf_safe_obstacle()'

   

3. To run experiment where unicycle gets stuck without learning run

   python -c 'from bayes_cbf.unicycle_move_to_pose import unicycle_no_learning_gets_stuck; unicycle_no_learning_gets_stuck()'

   

4. To run experiment where unicycle passes safely through obstacles due to learning run

   python -c 'from bayes_cbf.unicycle_move_to_pose import unicycle_learning_helps_avoid_getting_stuck; unicycle_learning_helps_avoid_getting_stuck()'

   

1. A script to run pendulum example with random controller (No learning)

run_pendulum_control_trivial

2. A script to run pendulum example with CBF-CLF-controller (No learning)

run_pendulum_control_cbf_clf

3. A script to run Bayesian learning on pendulum example with random controller.

pendulum_learn_dynamics

4. A script to run Bayesian learning on pendulum example with CBF-CLF controller.

pendulum_control_online_learning