Research & Development Specialist in AI & Robotics

Descrizione

Testo originale dell'annuncio (in inglese)

About the SnT The University of Luxembourg is an international research university with a distinctly multilingual and interdisciplinary character. The Interdisciplinary Centre for Security, Reliability and Trust ( SnT ) at the University of Luxembourg is a leading international research and innovation centre in secure, reliable and trustworthy ICT systems and services. We play an instrumental role in Europe by fueling innovation through research partnerships with industry, boosting R&D investments leading to economic growth, and attracting highly qualified talent. We look for researchers from diverse academic backgrounds to contribute to our projects in areas such as: Network Security, Information Assurance, Model-driven Security, Cloud Computing, Cryptography, Satellite Systems, Vehicular Networks, and ICT Services & Applications. Join the defence research project "Autonomous Guided Vehicle Multi-role Defence Platform" (AGVMDP) in collaboration with the company Luxbotix. This project aims to design, build, and validate a 2-ton, fully electric, solar-powered Autonomous Ground Vehicle (AGV) for European defence applications, including autonomous logistics, casualty evacuation (MedEvac), counter-UAS, EOD/demining, and distributed ISR (Intelligence, Surveillance, Reconnaissance). The AGV will operate in GNSS-denied and electronically contested environments, leveraging Vision-Language-Action (VLA) models, multi-sensor fusion (LiDAR, radar, cameras, IMU), semantic SLAM, and EW-resilient mission planning. The platform will feature modular payload interfaces, energy autonomy via solar power, and explainable AI for operator trust and compliance with defence standards. Your role As an RDS at the Ubiquitous and Intelligent Systems (UBIX) Research Group, you will assist a senior researcher in developing prototypes and conducting experiments in collaboration with Luxbotix engineers to transition research into operational systems. Core Research & Development: Develop semantic perception modules using VLMs/VLA models, e.g., RobustVLA, ReinboT, OpenDriveVLA) to classify terrain, obstacles, and mission-relevant objects in real time Implement GNSS-free localisation systems leveraging semantic map-matching, visual odometry, and pre-loaded satellite imagery for loop closure and pose estimation Implement multi-sensor fusion pipelines (LiDAR-radar-camera-IMU) for SLAM and environmental awareness in GNSS-denied conditions Adapt hierarchical mission planners to decompose high-level defence missions into executable, EW-resilient tasks Optimize algorithms for embedded deployment (ROS II, Python/C++) on the AGV's onboard computers, balancing computational efficiency and robustness Collaboration & Validation: Work with Luxbotix to integrate autonomy software into prototype AGVs, ensuring seamless hardware-software interaction Validate systems through simulation, controlled lab tests, and field trials, including EW jamming campaigns Contribute to documentation, safety cases, and test reports for defence stakeholders: Luxembourg MoD, NATO, EDA Support mission equipment integration; e.g., MedEvac stretchers, EOD tools, counter-UAS sensors, and operational scenario testing Your profile Master degree in Computer Science, Robotics, AI, or a related field (completed) Background in one or more of the following: Vision-Language Models (VLMs) or Vision-Language-Action (VLA) models for autonomous systems Multi-sensor fusion, e.g. LiDAR, radar, cameras, IMU, and SLAM, e.g., ORB-SLAM, LIO-SAM Semantic perception: object detection, segmentation, scene understanding GNSS-denied navigation: visual odometry, map-matching, terrain-based localisation Mission planning for autonomous robots: hierarchical task networks, re-planning under uncertainty Proficiency in Python/C++ and experience with ROS Experience with deep learning frameworks: PyTorch, TensorFlow) and LLMs/VLMs Language Skills: Fluent written and verbal communication skills in English (C1) are required IMPORTANT