ika-rwth-aachen/acdc-notebooks

Stars
152
Rank 243,219 (Top 5 %)
Language
Jupyter Notebook
License
MIT License
Created about 2 years ago
Updated 11 months ago

ika-rwth-aachen/acdc-notebooks

ika-rwth-aachen

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Jupyter Notebooks for the MOOC "Automated and Connected Driving Challenges" available on edX.

Automated and Connected Driving Challenges (ACDC)

This repository belongs to the Automated and Connected Driving Challenges (ACDC), a Massive Open Online Course (MOOC) on edX.org, teaching how to solve current challenges in the field of automated and connected mobility. This repository contains Jupyter Notebook programming tasks.

Watch the Course Trailer for a quick introduction to the course:

Enroll in the course for free here and learn how to shape future automated and connected mobility!

The course is taught by the Institute for Automotive Engineering (ika) of RWTH Aachen University in Germany.

Repository Content

For the complete course content including the solutions to all programming tasks in the course, please enroll in the course.

If you want to get to know the programming tasks of this repository, you can find an overview in this Jupyter Notebook.

We offer additional programming tasks relating to the Robot Operating System (ROS) in the ACDC repository.

Note that Jupyter Notebooks are often not correctly displayed on Github. Use JuypterLab as described below to correctly display the notebooks.

Quick Start

All programming tasks can be run inside of a Docker container, which we provide. Our ACDC-Notebooks Docker container can be used for starting JupyterLab on you local machine. You can use the following instructions to run the container:

Follow all steps described under Installation in the ACDC repository's Wiki.

Clone this repository:

git clone https://github.com/ika-rwth-aachen/acdc-notebooks.git

Pull our ACDC-Notebooks Docker image from our registry:
```
docker pull rwthika/acdc-notebooks:latest
```
In a terminal, navigate to the Docker directory of this repository and launch the ACDC-Notebooks Docker container with the provided run script:
```
# acdc-notebooks/docker
./run.sh
```
The Docker image should start now and your terminal should display some output similar to the one seen in the image below. Open the last link displayed in your terminal and JupyterLab will open in your browser.
Navigate to the /acdc/ directory in JupyterLab and open index.ipynb to get an overview of all available notebooks.

License

MIT License

Copyright 2023 Institute for Automotive Engineering of RWTH Aachen University.

Cam2BEV

TensorFlow Implementation for Computing a Semantically Segmented Bird's Eye View (BEV) Image Given the Images of Multiple Vehicle-Mounted Cameras.

acdc

Code Repository for the MOOC "Automated and Connected Driving Challenges" available on edX.

mqtt_client

ROS / ROS 2 C++ Node for bi-directionally bridging messages between ROS and MQTT

drone-dataset-tools

The goal of this repo is to make the drone datasets as easy to use as possible. For this purpose we provide source code in Python, which allows the import and visualization of the datasets.

docker-ros

docker-ros automatically builds development and deployment Docker images for your ROS-based repositories

libtensorflow_cc

Pre-built libtensorflow_cc.so and Docker Images for TensorFlow C++ API

EviLOG

TensorFlow training pipeline and dataset for prediction of evidential occupancy grid maps from lidar point clouds.

docker-run

'docker run' and 'docker exec' with useful defaults

MultiCorrupt

MultiCorrupt: A benchmark for robust multi-modal 3D object detection, evaluating LiDAR-Camera fusion models in autonomous driving. Includes diverse corruption types (e.g., misalignment, miscalibration, weather) and severity levels. Assess model performance under challenging conditions.

docker-ros-ml-images

Machine Learning-Enabled ROS Docker Images

Point-Cloud-Compression

Implements a deep RNN based Point Cloud Compression approach for Velodyne Point Clouds. Reference implementation of corresponding IEEE IV22 paper.

etsi_its_messages

ROS / ROS 2 Support for ETSI ITS Messages for V2X Communication

PCLSegmentation

Tensorflow 2.9 Pipeline for Semantic Point Cloud Segmentation with SqueezeSeqV2, Darknet21 and Darknet53.

tensorflow_cpp

Helpful model wrappers around TensorFlow C++ API

acdc-research-projects

Research Projects of the MOOC "Automated and Connected Driving Challenges"

Jupyter Notebook

carlos

CARLA Open Simulation Architecture

omega_format

A Python library for reading, writing and visualizing the OMEGA Format, targeted towards storing reference and perception data in the automotive context on an object list basis with a focus on an urban use case.

RoadGeneration

Generation of Complex Road Networks Using a Simplified Logical Description for the Validation of Automated Vehicles

SimDriver

A responsive driver model for traffic simulations to create exact and closed-loop microscopic traffic scenarios.

robotkube

Orchestrating Large-Scale Cooperative Multi-Robot Systems with Kubernetes and ROS

ros-v2x-benchmarking-suite

ROS V2X Benchmarking Suite

mqtt-in-docker

Learn how to combine the MQTT protocol with Docker for applications in the Internet of Things (IoT). Secure your communication with authentication and encryption. Learn how to create a Public-Key Infrastructure.

dorotos

Tooling Suite for Containerized ROS Applications

message_tf_frame_transformer

ROS Node to transform messages of arbitrary type to a different frame using tf2::doTransform

DEviLOG

agent-model-integration

Integration of an Agent Model into an Open Simulation Architecture for Scenario-Based Testing of Automated Vehicles

mqtt_client-release

ROS release repository for mqtt_client

docker-ros-ci

acdc-wiki-pub

Temporary repository