BIASED-MPPI for Obstacle Avoidance

This is a dockerized project for Biased Model Predictive Path Integral (MPPI) control in PyBullet.

Biased-MPPI has been implemented in JAX-Python for obstacle avoidance.

MPPI algorithm is at workspace/mppi_jax/mppiJax.py

mppi_jackal.mp4

Steps to Reproduce Results

The project is containerized with Docker. To reproduce the results, follow these steps:

Clone the repository.
From the root directory of the repository, update the absolute path in scripts/deploy/base.sh.
Build the Docker image by running the following command:
```
./scripts/build/project_docker.sh
```

4 . to run the docker image , execute : ./scripts/deploy/devel.sh

5 Once inside the Docker container, navigate to /root/workspace/src and run python3 main.py

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
.vscode		.vscode
docker		docker
scripts		scripts
videos		videos
workspace		workspace
33.gitignore		33.gitignore
README.md		README.md