/knk-autonomous

K and K Autonomous is an autonomous driving system that leverages the power of Occupancy Networks and Reinforcement Learning-based planning. The system is designed to assist in driving by maintaining lane centering and providing driving assistance.

Primary LanguagePythonMIT LicenseMIT

K and K autonomous

knk_logo

K and K Autonomous is an autonomous driving system that leverages the Deep Learning methods for depth estimation,object detection,lane segmentation and Rule-based planning. The system is designed to assist in driving by maintaining lane centering and providing driving assistance.

Knk-Vision

KNK-Vision is a computer vision module used for vehicle detection, lane detection, and depth estimation from monocular camera images.KNK-Vision uses the YOLOP for real-time lane segmentation and vehicle detection. Depth estimation is done using Vidar

Demo

example

After inference

infer_res

MetaDrive inference

meta_infer

Installation

Follow these steps to set up the KNK-Vision environment and install the necessary dependencies:

  1. Clone the repository: git clone https://github.com/geci-final/knk-autonomous

  2. Navigate to the cloned repository:

    cd knk-autonomous

  3. clone the submodules

    git submodule update --init --recursive

  1. If you haven't already, install conda.

  2. Create a new conda environment from the environment.yaml file:

    conda env create -f environment.yml

  3. Activate the new environment:

    conda activate knk-autonomous

Contributing

We welcome contributions!