π§© Obstacle Prediction Puzzle: Predict obstacles in front of self driving car

π  Start Solving

π Explore Dataset

## π΅πΌββοΈ What Is Obstacle Prediction Puzzle About??

In this puzzle, you will have the radar sensor points mounted on a self-driving car moving through a town. Your goal will be to classify if there we any moving obstacles in front of the self-driving car. These obstacles can be pedestrians or another car within a pre-defined distance threshold. In this binary classification task, an output of 1 means an obstacle, and 0 means there is no obstacle.

## πͺπΌ What Youβll Learn

In this puzzle, you will learn

1. Binary Classification using various sklearn classifiers

Letβs get started! π

In this puzzle, you will use the car radar from the dataset to build an automated algorithm to predict the presence of dynamic objects in front of the self-driving car. This is a binary classification task where an output of 1 means there is an obstacle and 0 means there is no obstacle.

The dataset contains 8000 samples. The training and testing samples are both contained in data.npz. The dataset contains information about the radars points generated from a Carla Simulator. It contains information on whether a dynamic object (pedestrian or vehicle) was within a distance threshold or not.

The individual radar points of single training sample features contain below metadata -

name dtype description
altitude float Altitude angle in radians
azimuth float Azimuth angle in radians.
depth float Distance in meters.
velocity float Velocity towards the sensor.

## π Dataset Files

• data.npz - ( 5000 training and 3000 testing samples )- This npy file contains the training and testing sets. You can use the NumPy function np.load to read the file
• sample_submission.csv - It contains the random labels for testing data used for testing purposes and to make sure that your submission format is correct.

## π Evaluation Criteria

The evaluation metrics for this competition are F1 Score (Primary Score) and Accuracy (Secondary Score)

## π Getting Started

Click here to access the basic starter kit. This will share in-depth instructions to

2. Setup the AIcrow-CLI environment that will help you make a submission directly via a notebook
4. Preprocessing the dataset
5. Creating the model
6. Setting the model
7. Training the model
8. Submitting the result

Check out the starter kit here! π

## π¨ How To Make A Submission

1. Creating a submission directory
2. Use test.csv and fill the corresponding labels.
3. Save the test.csv in the submission directory. The name of the above file should be submission.csv.
4. Inside a submission directory, put the .ipynb notebook from which you trained the model and made inference and save it as original_notebook.ipynb.
5. Overall, this is what your submission directory should look like
submission
βββ submission.csv
βββ original_notebook.ipynb

## π€« Hint to get started

1. Try using various sklearn classifiers and see which one gives the best score.
2. Check out the notebook using one such classifier, Random Forest.

## π Resource Circle

Check all the sklearn classifiers here.