Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
76 changes: 76 additions & 0 deletions pages/quest_books/w26_rover_quests.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,76 @@
# WATonomous Quest Book - Winter 2025 (W25)

## The Great Objective: Improve Upon Object Detection Model

The Rover Team is working on improving the object detection model for the [UW Robotics Team](https://github.com/uwrobotics)'s [URC 2026](https://urc.marssociety.org/home/requirements-guidelines) rover. We hope to pass the [System Acceptance Review](https://urc.marssociety.org/home/requirements-guidelines/system-acceptance-review) and do well in next year's competition.

## Term Objectives Summary

The objectives for Winter 2026 focus on integrating hardware, improving the object detection model, and preparing the platform for autonomous operation. These include:

1. **Hardware Integration**
- Interfacing with UWRT's hardware interface to begin autonomous control of the rover.
- Transferring simulated camera logic to real cameras and begin testing of costmap in the real world.
- Testing the object detection model on the rover.

2. **Software Modules**
- Control module: Implementing the control module for the physical rover.
- Refine ML model for more refined object detection.

---

### Term Objectives and Scoring

1. Talk to UWRT Interface to begin control of the rover.

| Score | Criteria |
|-------|-------------------------------------------------------------------------|
| 10/10 | Rover is able to move autonomously from point A to point B. |
| 5/10 | Partially integrated with basic rover movement (not reliable autonomy). |
| 0/10 | No progress. |

**Minimum Requirements:** At least basic functionality implemented and tested for a score above 5/10.

2. Model Optimization and Inference Pipeline

| Score | Criteria |
|-------|-------------------------------------------------------------------------|
| 10/10 | Model running on target hardware and reliably predicting objects. |
| 5/10 | Model running on target hardware but unreliably predicting objects. |
| 0/10 | No progress. |

**Minimum Requirements:** Model running on target hardware for a score above 5/10.

3. Dataset Robustness & Environmental Augmentation

| Score | Criteria |
|-------|-------------------------------------------------------------------------|
| 5/5 | Data is trained on a variety of environments and is robust to changes in lighting, weather, and other environmental factors. |
| 3/5 | Data is trained on a variety of environments but is not robust to changes in lighting, weather, and other environmental factors. |
| 1/5 | Data is trained on a single environment and is not robust to changes in lighting, weather, and other environmental factors. |
| 0/5 | No progress. |

**Minimum Requirements:** Data is trained on a single environment for a score above 1/5.

### Blogs (BONUS)
4. Blogs

| Score | Criteria |
|-------|----------------------------------------------------------|
| 5/5 | Three blogs have been written on simulating software for the rover. |
| 4/5 | Two blogs have been written on simulating software for the rover. |
| 2/5 | One blog has been written on simulating software for the rover. |
| 0/5 | No blogs have been written on simulating software for the rover. |
---

### Scoring Template

| Quest Name | Description | Due Date | Score |
|-------------------------|-------------------------------------------------------|-----------|--------|
| UWRT Interface | Rover autonomous movement from Point A to Point B. | | /10 |
| Sensor Drivers | Target hardware inference and prediction reliability. | | /10 |
| Mounts | Environmental augmentation and lighting resilience. | | /5 |
| Perception Stack | Documentation on simulating software for the rover. | | /5 |

### Comments
This term was heavily influenced by a struggle to get pre-commit working as well as issues later in the term when it came to building and testing the project.