Thesis Code: 24017
Research Area: Connected Systems and Cybersecurity
Description
This thesis investigates the application of NVIDIA Isaac ROS Nvblox for reconstructing 3D scenes of the environment. The primary objective is to evaluate the capability of Nvblox in generating accurate and detailed representations of environment using data from various sensors installed on AMRs. These sensors may include cameras (e.g., front view, side view) and LiDARs (e.g., front-facing solid-state LiDAR, 360° rotating LiDAR). In the proposed scenario, on-board sensors from AMRs are used to capture the scene as they pass across the environment where the robots are deployed. The thesis aims to implement this scenario on a portion of an indoor environment to assess the performance and effectiveness of Nvblox technology in this specific context. The study involves collecting sensor data under controlled conditions and then using Nvblox to reconstruct the scene with the acquired data. The outcomes will provide insights into the feasibility and accuracy of using Nvblox for real-world scenarios, contributing to the fields of building inspection and monitoring.
Requirements
- Computer Science, Mechatronics, or similar background
- C++/Python programming languages
- Some knowledge in communication protocols and computer vision will be considered a plus
- Linux OS knowledge will be considered a plus
- ROS/ROS2 knowledge will be considered a plus
- Proactive mindset, problem-solving oriented
Duration: 6-8 months.
Contacts: send a resume with attached the list of exams to gianluca.prato@linksfoundation.com enrico.ferrera@linksfoundation.com