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 data science 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 motion forecasting task is to predict the positions of a tracked object 3 seconds into the future, given an initial 2-second observation. Your knowledge of deep learning will then be required to predict how cars  move in the AV's environment.
The training, validation, and test sequences are taken from different areas of Pittsburgh and Miami so that there is no geographical overlap. Each sequence follows the trajectory of the main agent for 5 seconds, while keeping track of all other agents including cars and pedestrians.   Agents follow very complex trajectories, such as changing lanes, navigating intersections, and turning.  We also provide the HD map information that is associated with the trajectory.
Team Guideline
This is a group project for the class.  You can request the computational resources from UCSD Data Science/Machine Learning platform allocated for this course. See more details on Course Website. 

- Maximum submission per day: 10
- Submission deadline: 11:59 pm May 28, 2021
Acknowledgements
We thank Argoverse for sharing this dataset.