3D Point Cloud Map Cleaning - Internship Toulouse

EasyMile; Toulouse; Sur place; EUR 10 000 - 12 000; Plein temps

Avantages offerts par ce poste

1000€ gross monthly

Tickets restaurant

CSE

Résumé du poste

EasyMile offers a 6-month internship in Toulouse focused on data classification of accumulated LiDAR PointCloud for Level 4 autonomous driving.

You will work within the Tools and Perception teams to build a tool that cleans dynamic elements from dense 3D maps, exploring 3D perception, point-cloud processing and software development. English and French are required; start March–April 2027.

Qualifications

• Student in computer science.
• Notions in UI/UX and deep learning.
• Languages: English and French.

Responsabilités

• Investigate existing 3D perception approaches (semantic segmentation, object detection or classification).
• Combine perception components into a pipeline and integrate into the internal 3D visualization software.
• Visualize and use results for point cloud cleaning in visualization software.

Connaissances

Python

C++

Deep Learning

UI/UX notions

English

French

Formation

Computer science student

Outils

Internal 3D visualization software

Description du poste

• Duration: 6 months
• Start date: March-April 2027 (flexible)
• Location: Toulouse
• Team: Tools / Perception
• Internship subject: Data classification on accumulated LiDAR PointCloud
• Compensation: 1000€ gross, tickets restaurant, CSE

Internship Context

EasyMile is advancing Level 4 autonomous driving technology, enabling vehicles to operate fully driverless in defined environments. To navigate and localize safely, our vehicles rely on onboard sensors such as LiDARs, radars and cameras.

Static dense 3D point cloud maps, built by accumulating LiDAR measurements along the vehicle’s trajectory, are used as a reference for vehicle localization. However, these maps may contain vehicles, vegetation and other objects that can move or change over time, reducing their quality and reliability.

In the Perception Team, we use several techniques to analyze this dense environment.

In the Tools Team, we develop tools to visualize and manage the data required by our autonomous vehicles.

This internship focuses on creating an intelligent and interactive tool to efficiently clean 3D point cloud maps by detecting and removing dynamic or potentially changing elements.

You will interact with both teams around various themes : 3D perception, point-cloud processing, software development …

Missions / Responsabilities

Under the supervision of his tutor, the intern will be involved in:

• investigating existing 3D perception approaches, such as semantic segmentation, object detection or classification, and select the most relevant components for our use case
• combining these perception components into an effective pipeline and integrate it into our internal 3D visualization software
• Visualizing and using the results in the visualization software for point cloud cleaning

There is no typical profile at EasyMile, we all come from different backgrounds and that is what makes us strong! We are looking for:Student in computer scienceSkills: Object-oriented programming (Python/ C++), Deep Learning, notions in UI/UXSoft skills: Team spirit, autonomy, and curiosityLanguage skills : English and French