Consensus-Based Modular and Heterogeneous Motion Generation for Multi-Purpose Robots (M/F)

Job Description

Missions

This position aims to design a fundamentally new control architecture to address the deployment limitations of multi-purpose robots in shared environments. Rather than a single monolithic controller, the robot is treated as a network of collaborating semi-autonomous agents (a mobile base, an arm, a gripper, a learned policy, a safety module). Each agent runs its own specialized solver and is coordinated to a common, dynamically feasible plan through distributed optimization and consensus.

The successful candidate will develop the algorithmic foundations of this framework—making the motion-generation stack modular and heterogeneous (combining model-based control with learning-based components)—and validate it on real multi-purpose robotic platforms.

Activity

- Algorithmic foundations of modular motion generation: Establish principled ways to decompose a complex motion-generation problem into coordinated subproblems that can be solved separately and reconciled through consensus. Modules must be able to be added, removed, or swapped without restructuring the whole problem. A central question is how best to partition a given task (e.g., by morphology, limb, or objective) to balance computational efficiency and solution quality.

- Heterogeneous and hybrid coordination: Bring together solvers of different natures (gradient-based optimization, sampling-based methods, and learned policies) within a single coordination scheme. This involves assigning each subproblem to the most suitable approach and combining model-based control with learning-based components rather than treating them as competing paradigms. The consensus mechanism will keep the overall behavior coherent and allow learned components to be paired with model-based safety modules.

- Experimental validation: Demonstrate the framework on a multi-purpose mobile manipulator across a progression of tasks, including navigation in cluttered environments, whole-body and bi-manual manipulation, loco-manipulation, and manipulation of deformable objects. This includes showing on-the-fly reconfiguration (e.g., switching end-effectors or objectives) without controller recompilation.

Your Profil

Skills

- Education: Ph.D. degree in Robotics, Control, Optimization, Machine Learning, Computer Vision for Robotics, or related fields.
- Technical Expertise: Strong background in optimization-based and/or learning-based motion generation for robots (particularly aerial drones).
- Development: Proven experience and proficiency in C++ and Python.
- Specific Knowledge: Prior knowledge of event-based vision (neuromorphic engineering) is highly desirable.
- Soft Skills: Scientific curiosity, high degree of autonomy, and the ability to work independently within a collaborative project environment.

Your Work Environment

The PostDoc research will naturally fit into our several activities over the last years about the general problems of motion generation for complex robots.

The facilities in the team include a vicon-instrumented indoor room for experiments with multiple quadrotors, four manipulator arms (two 6-dof industrial manipulators, and two 7-dof torque-controlled manipulators), and state-of-the-art 6-dof haptic devices. Exploiation of the Immersia VR facility (on campus) for running human/multi-robot experiments will also be possible (and encouraged).
Finally, two research engineers (technical staff) will assist the PostDoc for all what concerns hardware/software development and maintenance of the robotic platforms.

Constraints and risks

N/A

Compensation and benefits

Compensation

between 3040€ and 4210€ gross depending on the candidate's experience

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions