M/F] PostDoc in ‘Control-Aware Motion Planning’ for Robotics at LAAS-CNRS, Toulouse

Job title:

M/F] PostDoc in ‘Control-Aware Motion Planning’ for Robotics at LAAS-CNRS, Toulouse

Company:

Job description

Offer DescriptionPractical information:
– Position: Postdoctoral Researcher
– Location: LAAS-CNRS, Toulouse, France
– Starting date (flexible): October 2024 (up to December 2024)
– End date: end of March 2026
– Salary: Between 2991€ et 3417€ gross per month
– Team: RIS (Robotics and InteractionS), see
– Supervisors: Thierry Simeon, Marco Cognetti and Juan CortesSummary
The Laboratory for Analysis and Architecture of Systems (LAAS) is seeking a highly motivated and skilled Postdoctoral Researcher to join the RIS team for an 18-month position.Scientific project description
The context of this PostDoc advertisement is within the CAMP project ( ), whose goal is to develop a general and unified “intrinsically robust and control-aware motion planning framework”. In particular, an effective approach to managing the complexity of robots operating in real (and uncertain) environments is the “feedforward/feedback” or “planning/control” paradigm. This method involves two key steps: 1. Planning (Feedforward): Initially, a suitable nominal trajectory for the robot’s states and controls is planned using available information, such as robot models and its environment. This step is typically conducted offline and can incorporate various constraints (e.g., collision avoidance, limited actuation) and optimize for specific metrics (e.g., time, energy); 2. Control (Feedback): While the planned trajectory provides a foundation, open-loop execution would likely fail due to inevitable uncertainties in the planning information. Therefore, a motion controller is employed to “close the loop” by adjusting the planned motion in real time, ensuring robustness against unforeseen effects and deviations from the planned trajectory. This combined feedforward/feedback approach ensures that robots can effectively and reliably operate even in complex and unpredictable environments.This PostDoc position aims to focus on the first above-mentioned axis (i.e., planning) by extending the results we obtained within the project. In particular, [1][2][3] proposed a motion planner for producing collision-free reference motions that are robust against parametric uncertainties for a large class of complex dynamical systems. It is hinged on the concept of closed-loop sensitivity [4,5], a quantity that relates parameter variations to deviations of the closed-loop trajectory of any given system/controller pair. This metric is used within a sampling-based tree planner in [1,3] for generating trajectories that are intrinsically robust with respect to parameters’ uncertainties.The PostDoc will contribute to further extend the theoretical contributions about fusing motion planning and sensitivity, as well as contributing to the experimental validation of the proposed approaches on real drones (quadrotors and hexarotors), especially in outdoor environments, following the validation performed in indoor environments [6]. To this aim, the PostDoc will benefit from the LAAS-CNRS infrastructures: 1) an indoor arena with dimensions an indoor flight arena of 8x4x7m, equipped with a motion capture system, and an outdoor arena of 15x25x7m. Moreover, a workshop with all the necessary tools for the manufacturing of UAVs is available, as well as more than ten prototype UAVs (quad- and hexa-rotors) and numerous sensors and actuators (GPS, IMU, Lidar altimeter, F/T sensors, ultra-light robotic arm, etc.).Depending on the candidate’s profile, several research directions are possible
– Extend robustness to combined parameters and state estimation uncertainties.
– Multi-objective motion planning to compute Pareto-optimal paths.
– Robust motion planning for multi-robot systems.
– Human-drone (physical) interaction.Key Responsibilities
– Conduct high-quality research and lead the development of the outdoor experimental demonstrator (addressing and mitigating unmodeled effects/uncertainties such as wind and lower perception accuracy).
– Collaborate with the PhD students and permanent staff of the RIS team to fuse motion planning and sensitivity in robotics.About the RIS team at LAAS-CNRS
The “Robotics and InteractionS” (RIS) is an internationally recognized research team at LAAS-CNRS in Toulouse, focused on developing autonomous mobile machines that integrate perception, reasoning, learning, action, and reaction capabilities. The team’s main research areas are: Architectures for Autonomous Robots, Learning, Temporal Planning and Execution Control, and Algorithmic motion planning. RIS is composed of 8 permanent researchers, 4 PostDocs, and several Ph.D. students. More in general, research at LAAS-CNRS spans robotics, optimization, control, telecommunications, and nano-systems. The robotics department at LAAS-CNRS counts more than 100 people and it is supposedly one of the largest and oldest robotic research departments in France. LAAS-CNRS robotics department has made world-class contributions in artificial intelligence, planning, perception, humanoids, and aerial robot design and control.

Supervisors’ profile
– Thierry Simeon:
– Marco Cognetti:
– Juan Cortes:How to apply
Interested candidates are requested to apply by uploading the following documents:
– CV
– Letter of motivation/cover letter
– Contact information of two/three referees
– [Suggested] Research project (max 2 pages), ideally linked to one of the proposed research directions
– [Suggested] Short introduction video where you present yourself, and why you are applying for this PostDoc position at LAAS-CNRS. The video will be eventually requested after performing a shortlist of candidates.
The selection procedures will consist of an interview that will be conducted in English. The candidate will be asked to discuss the project and how their previous experience fits with the project’s objectives. The position will remain open until a satisfactory candidate is found.Where to apply WebsiteRequirementsResearch Field Computer science Education Level PhD or equivalentResearch Field Mathematics Education Level PhD or equivalentLanguages FRENCH Level BasicResearch Field Computer science Years of Research Experience NoneResearch Field Mathematics » Algorithms Years of Research Experience NoneAdditional InformationEligibility criteriaCandidate profile
– Ph.D. degree in robotics, ideally in motion planning&control, aerial robots
– Very good knowledge of motion planning + solid background in mathematics, optimization, and robotics
– Experience with experimental robotics, ideally drones and/or in outdoor settings.
– Very good skills in programming. Especially, C/C++, Python, ROS/ROS2, and, in general, the ability to independently develop and maintain large software
– Scientific curiosity, ability to work independently and in group
– Some experience with robotic simulation (e.g., Gazebo, CoppeliaSim, IsaacSim) but ideally with real drone experimentsWebsite for additional job detailsWork Location(s)Number of offers available 1 Company/Institute Laboratoire d’analyse et d’architecture des systèmes Country France City TOULOUSE GeofieldContact CityTOULOUSE WebsiteSTATUS: EXPIREDShare this page

Expected salary

Location

Laas, Gers – Toulouse

Job date

Wed, 31 Jul 2024 23:17:20 GMT

To help us track our recruitment effort, please indicate in your email/cover letter where (vacanciesineu.com) you saw this job posting.