Internship Visual Anomaly Detection For Autonomous Mobile Robots H/F INRIA

Internship : Visual Anomaly Detection for Autonomous Mobile Robots
Le descriptif de l'offre ci-dessous est en Anglais
Type de contrat : Stage

Niveau de diplôme exigé : Bac +4 ou équivalent

Fonction : Stagiaire de l'ingénierie

Contexte et atouts du poste

About the AIO team

Inria-AIO is a leading research team in low-power wireless communications. The team is
designing Tomorrow's Internet of (Important) Things. It pushes the limits of low-power
wireless mesh networking by applying them to critical applications such as robotics,
industrial control loops, with harsh reliability, scalability, security and energy constraints.
Inria-AIO co-chairs the IETF 6TiSCH and IETF LAKE standardization working group and co-
leads Berkeley's OpenWSN project. Inria-AIO is heavily involved in real-world applications,
and oversees over 1,000 sensors deployed on 3 continents for smart agriculture, smart city
and environmental monitoring applications. The team's research program is organized
around 5 pilars: Smart Dust, Low-Power Wireless Networking, Security in Constrained
Systems, Swarm Robotics and Vehicle Area Networking.

The AIO team seeks an intern for the Colibri project, a collaboration between La Poste and
Inria. La Poste needs to monitor swap bodies (mobile containers) used in its logistics
warehouses. When not loaded on trucks, these containers rest on metal support legs
prone to breaking, causing container tipping incidents.
Within this collaboration, the AIO team develops mobile robotic solutions to
autonomously and in real time detect structural anomalies in these container legs,
enabling early identification of legs at risk of breaking before container tipping, so they can
be replaced.

Mission confiée

- Data collection
Participate in the collection of data through 3D printing of test components, data
scraping, and teleoperation of mobile robots within La Poste's warehouses.
- Model development and evaluation
Study and adapt various object and anomaly detection architectures, with or
without deep learning, leveraging point cloud data, RGB/RGB-D vision, or a fusion of
both modalities.
- Algorithm implementation on robotsDeploy and integrate the developed detection algorithms on embedded robotic
platforms for real-time processing.
- Validation in real-world environments
Test and validate the proposed approaches under real operational conditions in La
Poste's logistics facilities, while also studying the reliability of the algorithm to
ensure consistent performance across various scenarios

Principales activités

- Propose suitable solutions for the task of anomaly detection on container legs using
LiDAR or RGB-D sensor data.
- Adapt the selected methods to the specific constraints of the mission, ensuring
they operate in real-time or near real-time while remaining computationally efficient
to be able to run on the robot.

Compétences

- Proficiency in Python or C++
- Computer vision
- Interest for robotic, knowledge of ROS/ROS2 is a plus
- 3D modelling skills are a plus

Avantages

- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage