TL;DR
These CIFRE: Augmented Spatio-Temporal Perception Of Complex Environments For Autonomous Robotics (AI/Robotics): Designing and implementing multi-layer, large-scale environment representations for robotics with an accent on integrating geometry, appearance, and semantic information from stereo vision and LiDAR sensors. Focus on leveraging graph-based methods for SLAM, exploration, and navigation, and exploring hybrid AI approaches for real-time decision-making in complex, dynamic environments.
Location: Must be based in Sophia-Antipolis (Valbonne), France
Company
hirify.global designs the processors that power next-generation embedded intelligent systems, ensuring they are safe, secure, fast, and reliable, focusing on efficient vision pipelines on NXP hardware, in collaboration with Inria’s ACENTAURI research team.
What you will do
- Design and implement a multi-layer, large-scale environment representation for robotics.
- Integrate geometry, appearance, and semantic information from stereo vision and LiDAR sensors.
- Develop efficient tools to build, maintain, and query these representations.
- Leverage graph-based methods for tasks like SLAM, exploration, navigation, and place recognition.
- Explore hybrid AI approaches combining rule-based methods with data-driven neural architectures.
- Validate the system through real-world experiments using instrumented robots.
Requirements
- PhD candidate in advanced robotics, multi-sensor perception, or efficient AI architectures.
- Expertise in perception, decision-making, and multi-robot collaboration.
- Proficiency in C/C++ under ROS2.
- Experience with 3D scene graphs and graph-based methods for robotics.
- Familiarity with model-based and data-driven hybrid AI approaches.
- Ability to work in a collaborative research and industrial environment.
Culture & Benefits
- Collaboration between Inria’s ACENTAURI research team and hirify.global.
- Contribution to scientific research and industrial innovation.
- Opportunity to work on real robotic platforms such as autonomous cars, AGVs, and drones.
- Focus on smart territories, smart cities, and smart factories.
- Work with NXP neural processing units (e.g., eIQ Neutron NPU).
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →