# SDC Tracking and Forecasting Competition
###### tags: `Self-Driving Cars`, `ROS`

The goal of this competition is to develop and understand a tracking and forecasting module for the self-driving car. You will be graded based on the your rank on leaderboard and the contribution on solving the problems. You can write your code based on last assignment.
Note1: This is **NOT** a team competition you should complete this competetion **ON YOUR OWN**.
Note2: You are **REQUIRED** to join the [tracking competition](#Tracking-Competition), but [forcasting competition](#Forcasting-Competition) is **optional** that you can get extra points on it.
Note3: In the final competition, you could use a **custom team name**. Please fill in your student ID and your team name (the name you use on the EvalAI leaderboard) in this **[link](https://e3.nycu.edu.tw/mod/groupselect/view.php?id=242189)**. You should make a **unique** team name that can be identifed by TA. **Otherwise, your rank may not be accepted by TA**.

## Schedule

### Competition: 12/5 - 12/28
### Report: 12/28 - 12/29

## Outline
- [Tracking Competition](#Tracking-Competition)
- (Bonus)[Forcasting Competition](#Forcasting-Competition)
- [Submission & Grading](#Submission-amp-Grading)

## Tracking Competition
[](https://eval.ai/web/challenges/challenge-page/453/overview)

### [Competition Link](https://eval.ai/web/challenges/challenge-page/453/overview)

We follow the competition held by ArgoAI. You should submit your results to their website. You can start from baseline code we provided in [last assignment](https://hackmd.io/@Biomotion/HyfrSat_K) but you still need to add your idea to get contribution credits.

## Forcasting Competition

[](https://eval.ai/web/challenges/challenge-page/454/overview)
### [Competition Link](https://eval.ai/web/challenges/challenge-page/454/overview)

### [Baseline Code](https://github.com/jagjeet-singh/argoverse-forecasting)

This competition is for bonus. You will get extra points if you complete the competition and upload your results.
**Note**: You must complete tracking competition first. If you don't have result on tracking, then you'll get 0 point on forcasting competition.

## Submission & Grading

- Tracking Competition Ranking: 60%
- (Bonus) Forcasting Competition Ranking: 60%
- Presentation and Report: 40%

### Competition Ranking

- Please upload your result to the EvalAI competition websites.
- For each competition, you will get your score based on your ranking.
| RANK | SCORE |
| -------- | -------- |
| 1 | 60 |
| 2 | 54 |
| 3 | 48 |
| Top 20% | 42 |
| Top 40% | 36 |
| Above baseline | 30 |
| Equal-to baseline | 15 |
| Below baseline | 0 |
- **Upload your code and the best submission on leaderboard to E3**. We will check if the code can be compiled and executed.
- You may add some **README** if your code needs some extra libraries. Just make sure TAs can compile it properly.
- Naming Rule: `<student_id>_tracking_forcasting_results.zip`
- **Upload Deadline: 12/28 23:59**
- **There is no delay submission accepted. Remember to upload your code befor midnight**

### Presentation and Report

- Required elements:
- **Pipeline**: how your program works
- **Contribution**: the difference between yours and others
- **Problems and Solutions**
- **Other Discussion or Findings** ... etc.
- Naming Rule: `<student_id>_tracking_forcasting_report.pdf`

The contribution part depends on the idea you implement or how you solve the issue you met. If you completely use other's method **without your idea**, you will get ZERO point in the contribution part.
- **Report Deadline: 12/29 12:00** (Note that it's not ended at 22:00 as usuall)