CIFRE PhD - Visual servoing tasks planning in robotics (M/F)

Description de l'offre

CIFRE PhD - Visual servoing tasks planning in robotics (M/F)

Airbus Toulouse

Airbus is a global leader in aeronautics, space and related services. In 2017, it generated revenues of € 67 billion and employed a workforce of around 130,000. Airbus offers the most comprehensive range of passenger airliners from 100 to more than 600 seats. Airbus is also a European leader providing tanker, combat, transport and mission aircraft, as well as Europe's number one space enterprise and the world's second largest space business. In helicopters, Airbus provides the most efficient civil and military rotorcraft solutions worldwide.

Our people work with passion and determination to make the world a more connected, safer and smarter place. Taking pride in our work, we draw on each other's expertise and experience to achieve excellence. Our diversity and teamwork culture propel us to accomplish the extraordinary - on the ground, in the sky and in space.

Description of the job

A PhD Thesis opportunity in "Visual servoing tasks planning in robotics (M/F)" has arisen at Airbus Commercial Aircraft in Toulouse.

The task planning problem is linked to automatic collision free trajectory for a robot, starting from an intial configuration pose to a targeted goal configuration, based on geometric model of the robot and the environment. This problem is already well known, when a structured environment is introduced. But inline and autonomous execution on a robot acting in a real environment introduce several issues. They are mainly linked to inaccuracy in the surrounded environment or the execution errors introduced by a gap error between requested positions and applied ones.

The main objective of this thesis is to introduce the conceptual link between task planning and robot control using on one side a model introducing several perception modalities (vision, force) and on the other side the task planning sequence. Therefore development new kind of algorithms is requested, in order to introduce derivative inputs within the task's hierarchy. Then tasks inline re-planning is the last scientific and technology challenge in order to take into account unknown obstacle or mission goals change.
These objectives will be transferred in the context of aircraft manufacturing, where a robot shall execute tasks such as drilling and tightening processes. These tasks introduce high positioning accuracy while the intrinsic robot positioning accuracy is pretty low.

The candidate will also be able to take advantage of the various platforms such as humanoid with Pyrène & Tiago available at the laboratory of Gepetto team (LAAS CNRS).

Profil recherché

Tasks & accountabilities

The thesis targets C ++ algorithms development using the Gepetto SDK called HPP.

·  Year 1: carry out a literature research on the problem and the state of the art. The study will focus on the task planning integration and the multi modal perception system.
·  Year 2: Implementation of the algorithm and evaluation on bigger instances (either in terms of dimensions, or in term of perception modality).
·  Year 3: Integration of the control system on various robots, realization of a demonstrator and live test in a realistic industrial environment. Supported by the submission of a scientific paper and writing of thesis dissertation.

This job requires an awareness of any potential compliance risks and a commitment to act with integrity, as the foundation for the Company's success, reputation and sustainable growth.

Required skills

You have the following skills and experience:

·  MsE or MsR in robotics, automation and control or mechatronics
·  Decent level of competences in robotics and task planner fundamental theories.
·  High level of knowledge in mathematics and programming (especially Python, C++, Corba) on Linux
·  Decent level in English
·  Soft skills: communicating, team spirit, self-reliant, curious and passionate