This is the home page of the deep learning class competition (CSE 151b Spring 2022). 
Here is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).


## Background
Autonomous vehicles (AV) are expected to dramatically redefine the future of transportation. However, there are still significant engineering challenges to be solved before one can fully realize the benefits of self-driving cars. One such challenge is building models that reliably predict the movement of traffic agents around the AV, such as cars, cyclists, and pedestrians.

In this competition, you’ll apply your deep learning skills to build motion forecasting models for self-driving vehicles. You'll have access to a large AV motion dataset to train and test your models. The goal of the prediction task is to predict the positions of a tracked AV 6 seconds into the future, given an initial 5-second observation. 

The training, validation, and test sequences are taken from different areas of 6 cities so that there is no geographical overlap. Each sequence follows the trajectory of the main agent for 11 seconds, while keeping track of all other traffic agents including cars and pedestrians. Agents follow very complex trajectories, such as changing lanes, navigating intersections, and turning. 

## Team Guideline
This is a group project for the class. You can request the computational resources from [UCSD Data Science/Machine Learning platform](https://datahub.ucsd.edu/hub/login) allocated for this course. See more details on the [Course Website](https://sites.google.com/view/cse151b/competition).

Maximum submission per day: 10
Submission deadline: 11:59 pm UTC May 29, 2021. 

Please note UTC is 7 hours ahead of PST,

## Evaluation Guideline
See evaluation page for submission format and evaluation metric. The final rank counts towards 10% of the final score. 

## Acknowledgements

We thank [Argo](https://www.argo.ai/) for sharing this dataset.