Reference : UPR8001-OLISTA-010
Nombre de Postes : 1
Workplace : TOULOUSE
Date of publication : Monday, January 23, 2023
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 22 May 2023
Proportion of work : Full time
Remuneration : Monthly gross salary is fixed by CNRS from 2805€ to 3963€ according to the applicant experience.
Desired level of education : PhD
Experience required : Indifferent
The subject is part of the DFG-ANR project called HoRoPo and led by Gordon Cheng and Olivier Stasse in the Gepetto team at LAAS-CNRS.
The goal of HoRoPo is to develop a new scientific paradigm for motion generation considering humanoid robots equipped with a skin. The aim is to manipulate large objects using torque-controlled and non-torque-controlled humanoid robots and comparing the limitations of the two approaches and to fuse them to a uniformed controller.
The scientific direction will be to develop model predictive control strategies to take advantage of the skin, and the torque- and non-torque control. A scientific question to solve is the complexity arising from the number of contacts created by the object on the robot. HoRoPo will explore and exploit the potential of the skin for full-body manipulation control. It will take its foundation on the work by the German team (TUM-ICS) on the skin and the French team (LAAS-Gepetto) on whole-body predictive control. The former has realized some impressive breakthroughs in making the transmission of contact on skin patches accessible and manageable. The latter has proposed the new algorithm Crocoddyl (C. Mastalli, 2020) for model predictive control for computing whole body motion for a humanoid and make MPC feasible for a torque-controlled robot with state feedback. TUM-ICS has already equipped REEM-C, a full-size humanoid robot (H1), with skin and generated whole body motion using tactile feedback without torque-control. Five years ago, LAAS-Gepetto has proposed improvements with respect to the REEM-C humanoid, in order to have a humanoid which is quite powerful and can be controlled at the torque level for the actuators. The ambition of HoRoPo is to equip a torque-controllable robot TALOS (O. Stasse, 2017) with skin to manipulate heavy objects and investigate a comparable strategy for non-torque-controllable humanoids (H-1).
In this frame, the goal of the post-doctoral position is to develop new algorithms based on the whole body model predictive control scheme developed in the Gepetto team and collaborators in order to fully exploit the skin.
The candidate will be supported by the facilities available at LAAS.
 C. Mastalli, R. Budhiraja, W. Merkt, G. Saurel, B. Hammoud, M. Naveau, J. Carpentier, L. Righetti, S. Vijayakumar, N. Mansard, Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control, Int. Conf. On Robotics and Automation (ICRA), 2020
 E. Dantec, R. Budhiraja, A. Roig, T. Lembono, G. Saurel, O. Stasse, P. Fernbach, S. Tonneau, S. Vijayakumar, S. Calinon, M. Taïx, N. Mansard, Whole body model predictive control with a memory of motion: Experiments on a torque-controlled talos, Int. Conf on Robotics and Automation (ICRA), 2021
 E. L. Dantec, M. Naveau, P. Fernbach, N. Villa, G. Saurel, O. Stasse, M. Taïx, N. Mansard, Whole-Body Model Predictive Control for Biped Locomotion on a Torque-Controlled Humanoid Robot, Int. Conf. On Humanoid Robot (ICHR) 2022
 O. Stasse, T. Flayols, R. Budhiraja, K. Giraud-Esclasse, J. Carpentier, J. Mirabel, A. Del Prete, P. Souères, N. Mansard, F. Lamiraux, J-P Laumond, L. Marchionni, H. Tome, F. Ferro, TALOS: A new humanoid research platform targeted for industrial applications, Int. Conf. on Humanoid Robotics, 2017
 https://www.ce.cit.tum.de/ics/ (TUM-ICS)
 https://ieeexplore.ieee.org/abstract/document/8812712/ G. Cheng, E. Dean-Leon, F. Bergner, J. Rogelio Guadarrama Olvera, Q. Leboutet and P. Mittendorfer, "A Comprehensive Realization of Robot Skin: Sensors, Sensing, Control, and Applications," in Proceedings of the IEEE, vol. 107, no. 10, pp. 2034-2051, Oct. 2019, doi: 10.1109/JPROC.2019.2933348.
- Managing the project
- Theoretical development related to the optimization problem for whole body model predictive control, its implementations and the final test on the humanoid robot.
- Following the implementation of the skin on the TALOS robot with PAL-Robotics.
- Implementing the control on the TALOS.
- Writing, managing and publishing the related papers.
- Travels to Munich for the official project meetings
- PhD in robotics, computer science, control, numerical optimization.
- Extensive experience with deployment of control architecture on real robot
- Experience in team development: github, cmake, ROS, ROS/2, control architecture such as ros_control, OCS2, Croccodyl
- Experience on numerical optimization
- Programming Languages: C++/Python
Gepetto, LAAS is an international research environment and the working language is English. Located in the University town of Toulouse, in the south-west of France, the CNRS-LAAS (Laboratory for the analysis and architecture of systems) laboratory, a 640 man strong research center with about 90 people working in robotics. It benefits from strong connections to the adjoining universities and the space and aeronautics industry.
Constraints and risks
Manipulation of a humanoid robot TALOS 1.75m 100 Kg
We talk about it on Twitter!