Event cameras are becoming increasingly popular for their low latency and high dynamic range. It's been widely used in high-speed drones or highly dynamic scenes.
The goal of this project is to extend the [TartanAir]( tartanair.org ) dataset with more realistic event data. The task is to first collect event camera data in simulation environments utilizing Unreal Engine. Then we will validate the data by training models on it. Optionally, the project can be extended to deploy the models to drones and vehicles and execute real-world tasks.
- Strong programming
- Strong communication, collaboration, organization, and planning
- Proactive and fast self-learner
- Familiarity with simulation software (Unreal Engine, AirSim)
- Familiarity with machine learning: PyTorch
- Familiarity with software: ROS2, Python, C++, Linux, Bash, Git
- Learn and strengthen the skills above
- Understand the full pipeline required to develop an intelligent robot from start to finish
- Gain hands on experience with drones
Not a hard limit. We care more about talent and potential.