Welcome to AI Blitz XI! 🚀 | Starter Kit For This Challenge! 🛠

Community Contribution Prizes 📓  |  Find Teammates 👯‍♀️

Easy-2-Follow Notebooks 💻   | Discord AI Community 🎧

🔥 Introduction

Self-driving cars have a number of cameras at every angle to collect maximum data about their surrounding. Along with traditional cameras, they also have advanced radar systems.

What is LiDAR?  

LiDAR is an advanced radar system used by self-driving cars. It is one of the most important technologies that produce a 3D digital representation of cars surrounding environment. This device sends out pulses of light that bounce off an object and returns back to the LiDAR sensor which determines its distance. 

Given 3D LiDar data points, predict how many cars are around your self-driving vehicle. Access the starter kit over here.

✔  The Task

The challenge is to use the 3D car lidar features from the dataset to build an automated algorithm to predict how many vehicles were there in the lidar range:

In machine learning terms: this is a regression task.

🚀 Getting Started

Make your first submission using starter kit. 🚀

💾 Dataset

The dataset represents the 3D lidar points generated using Carla Simulator. 

it contains two columns in which the - 

1. the first column contains the x, y, and z points of the 3D Lidar Data
2. the second column contains the label ( number of vehicles )

📁 Files

Following files are available in theresources section:

• train.npz ( 399 samples ) - The training dataset contains the 3D lidar points in the first column and labels in the second column. To read the file in python, you can use NumPy like this -

   

• test.npz ( 601 samples ) - Unlike the training file, it contains only the 3D lidar points and not the labels. The labels generated will be used for the actual evaluation of the leaderboard score.

📨 How to submit

1. Create a submisison.csvfile inside the submission folder and fill the corresponding predicted no. of cars in a label column.

2. Inside a submission directory, put the .ipynb notebook from which you trained the model and made inference and save it as notebook.ipynb.

3. Zip the submission directory

4. Overall, this is what your submission directory should look like -

    

🖊 Evaluation Criteria

The evaluation metrics for this competition are the Total Error ( Primary Score ) and Max Error ( Secondary Score ) over all corresponding ground truth and predicted labels.

📱 Contact

If you have any questions, consider posting on the Blitz 11 Community Discussion board, or join the party on our Discord!