Internship details
- Duration: 6 months (starting date is flexible)
- Location: Toulouse
- Internship subject: Development of LiDAR based Terrain Estimator
- Team: EZDrive (Detection)
- Internship tutor: Ariane Spaenlehauer and Elio Vicente as technical advisor
- Monthly gratuity: 1000€ gross, tickets restaurant Swile, CSE
Missions
Ground segmentation is crucial for terrestrial mobile platforms to perform navigation or neighboring object detection. Unfortunately, the ground is not flat, as it features steep slopes; bumpy roads, estimating a model to properly render the terrain is challenging. Furthermore ground LiDAR perception depends on the weather conditions.
The objective of this internship is to identify solutions to upgrade our current ground segmentation and improve operational performance. The intern is expected to understand the terrain estimator algorithm that runs on the EM autonomous vehicles, as well as its limitations and effects on operational performance. Simultaneously, the intern must perform and document a state of the art about terrain estimation for autonomous driving. Based on the identified limitations and the state-of-the-art, a solution must be selected and prototyped. The prototype should be evaluated using recorded data and metrics, and tested using test-means (bench, vehicle).
The main tasks are:
- Analysis of the current state: Understand the perception software stack, including the limitations and operational impacts
- State-of-the-art: Survey the literature about terrain estimation for terrestrial vehicles and robots
- Solution design: Select a solution that could minimize the limitations of the current algorithm.
- Develop a prototype: Implement the solution in a first prototype that can be tested and evaluated
- Evaluate the solution: The prototype should be evaluated using recorded data and metrics, and tested using test-means (bench, vehicle).
Profile:
There is no typical profile at EasyMile, we all come from different backgrounds and that is what makes us strong! Don't hesitate to apply if you are motivated and interested in innovative transportation and technologies.
We are looking for:
- Master Degrees student;
- Strong mathematical/physics background
- C++ familiarity
- Python familiarity
- Linux familiarity
- Familiar with research paper reading
Desirable:
- Self-sufficient and proactive
- Cuda knowledge
Recruitment process:
- 30 minutes call with a recruitment team
- Meeting with the team, technical tests
- One hour interview with the tutor and recruitment team