By continuing to browse the site, you are agreeing to our use of cookies. (More details)

PhD in robotics and interactive manipulation

This offer is available in the following languages:
Français - Anglais

Ensure that your candidate profile is correct before applying. Your profile information will be added to the details for each application. In order to increase your visibility on our Careers Portal and allow employers to see your candidate profile, you can upload your CV to our CV library in one click!

Faites connaître cette offre !

General information

Reference : UPR8001-DANSID-006
Workplace : TOULOUSE
Date of publication : Wednesday, August 21, 2019
Scientific Responsible name : Daniel Sidobre
Type of Contract : PhD Student contract / Thesis offer
Contract Period : 36 months
Start date of the thesis : 1 October 2019
Proportion of work : Full time
Remuneration : 2 135,00 € gross monthly

Description of the thesis topic

Title : Human-aware motion planning and control for a flying coworker

In recent years, the scientific and technological progresses in human-robot interaction (HRI) were such
that human-robot collaboration is now the main hallmark of the Industry 4.0[0] and human-robot collaborative task methods start to be implemented. At the same time, substantial advances in the design and control of aerial vehicles have made possible to equip aerial robots (UAV) with manipulators [54] and to carry out physical interaction with novel fully-actuated flying robots [45]. While first Human-UAV studies have been published for tasks involving teleoperation, collaboration between a human and a flying manipulator teammate, however, has not yet been thoroughly investigated or realized. At the same time, substantial advances in the design and control of aerial vehicles have made it possible to equip aerial robots (UAV) with manipulators and to carry out physical interaction with novel fully-actuated flying robots. While first Human-UAV studies have been published for tasks involving teleoperation, collaboration between a human and a flying manipulator teammate, however, has not yet been thoroughly investigated or realized.

The objective of the The_flying_coworker project (https://www.laas.fr/projects/flying_coworker/) that funds this thesis is to combine HRI and Aerial Manipulation for demonstrating the possibility that a flying coworker (FCW), an aerial robot capable of manipulation abilities, physically cooperates with a worker in a safe, effective, acceptable, and fluent manner.

More specifically, this thesis focuses on planning to enable the FCW to plan and execute the movements required for different collaborative tasks in an adaptive manner.

Besides the standard problem of finding and adapting a collision-free path, the problem here is enriched by the need to elaborate a trajectory that takes into account the FCW constraints and the human needs and preferences. Our previous contributions[1, 2] and in particular[3] to the different situations and actions of a robot (approach and disengage motions, hand-over, etc.) could be extended to the case of the FCW. Another key aspect linked to the legibility of the robot intention could not only be based on the shape [4] and the dynamics of the trajectory but also with a pertinent use of a set of programmable colored LEDs [5]. Using a coordinated planning of the robot main body and its arm, we will extend current HRI approaches to account for the robot dynamic, safety and ergonomic constraints.

[0] A. Ajoudani et al. “Progress and Prospects of the Human-Robot Collaboration”. In: Autonomous Robots (2018).
[1] J. Mainprice et al. “Sharing effort in planning human-robot handover tasks”. In: RO-MAN. 2012.
[2] E. A. Sisbot and R. Alami. “A human-aware manipulation planner”. In: IEEE Transactions on Robotics (2012).
[3] H. Khambhaita and R. Alami. “Assessing the Social Criteria for Human-Robot Collaborative Navigation: A Comparison of Human-Aware Navigation Planners”. In: IEEE RO-MAN. 2017.
[4] A. Dragan et al. “Legibility and predictability of robot motion”. In: Int. Conf. on HRI. IEEE. 2013.
[5] M. Monajjemi, S. Mohaimenianpour, and R. Vaughan. “UAV, come to me: End-to-end, multi-scale situated HRI with an uninstrumented human and a distant UAV”. In: IROS. 2016.

Work Context

The Robotics and Interactions (RIS) team is developing new control and planning methods within the robotics department of LAAS-CNRS (Toulouse France). It is based on the technical resources of LAAS-CNRS and in particular on the robotics platform that manages robots and development tools.
This thesis is part of the team's project to develop mobile manipulator robots capable of evolving in the environment and in interaction with humans. It is linked to European, ANR and industrial projects.

We talk about it on Twitter!