[robotics-worldwide] [jobs] PhD Position - Coordinated control of a mobile manipulator carrying out dynamical work in natural environments
In the framework of the research project “Innovative systems and services
for transport and production” IDEX/I-SITE CAP 20-25 (Challenge 2 – Theme :
AgroTechnologies) and the LabEx IMobS3, TSCF-Irstea and Institut Pascal are
offering a PhD position for highly motivated candidates interested in
completing a PhD thesis on robotics.
Mobile manipulators are of great interest to perform tedious and repetitive
tasks on large areas. Several studies have set the first principles to
synchronize the different degrees of freedom provided by the mobile
platform and the robotic arm, as well as to control the nonholonomic
motions of the mobile base.
However, most of these studies focus on the displacements of the robot on
rigid soils within structured and controlled environments, and consider
quite often quasi-static work, i.e. the manipulator arm operates when the
mobile base is stopped. However, for productivity purposes, in particular
in agriculture, it becomes necessary to consider the coordination and a
close coupling of the movements of the robot including in dynamical
conditions, in particular in the case where the manipulation is used to
carry and displace the monitoring and intervention tools (e.g. for
diseases detection, spraying) with respect to a flexible target.
This thesis deals with mobile manipulators operating in natural
environments. It will consider the development of strategies enabling the
accurate control of the treatment body, carried by the manipulator arm,
relatively to flexible target plants, and this in a dynamical context.
First, the aim will be to ensure the accurate control of the 3D
position/orientation of the sensors mounted on the robot end-effector while
synchronizing the motions of the mobile base at low speed. Second, the
thesis will develop perception and control algorithms for the mobile
manipulator taking into account the specific phenomena and perturbations
encountered in off-road conditions. Deep learning techniques could be
evaluated in that way. The objective will be next to couple the motions of
the base and the manipulator to ensure the efficiency of the task at
potentially high speed, requiring to manage in particular the 3D motions
(pitch, roll) inherent to displacements in off-road conditions.
This thesis will be based on several work already initiated on this
thematic and will extend the principles of adaptive and predictive controls
to ensure the efficiency and accuracy of the work in an agricultural
A Master degree in Computer Science, Electrical Engineering, Mechanical
Engineering, Mechatronics or other related areas.
Strong background in mathematics and programming, specially in C++.
Excellent oral and written communication skills in English.
Previous experience and knowledge in one or more of the following areas:
robotics, machine learning, control theory and computer vision.
Previous experience on programming in ROS (Robot Operating System) software
and using Linux operating system.
Previous experience on programming with OpenCV and PCL libraries.
The candidates should send their candidatures via email at
[hidden email] and [hidden email],
including: (1) their CVs, (2) motivation letter, (3) transcripts of
previous university degrees (unofficial are enough now), (4) previous
research publications (if existing) and (5) contact information of 2 or 3
people who could serve as references.