Practical information

• Object: The RIS team at LAAS-CNRS in Toulouse (France) is searching for a Master's student interested in performing his/her internship.
• Location: LAAS-CNRS, Toulouse, France.
• Starting date (flexible): Spring/Summer 2026.
• Duration: 4-6 months.
• Salary: about 650 EUR net per month.

Links to the internships

https://partage.laas.fr/index.php/s/LKKGeTW8GBr33Wf

Scientific project

Summary

The internship aims at developing novel planning and/or control techniques for letting a team of drones to safely fulfill tasks that require interacting with the environment in a coordinated way.

Description of the project

One of the objectives of robotics is to develop autonomous systems capable of assisting humans in challenging, laborious, or hazardous tasks, particularly in environments that are difficult to access, such as high altitudes, space, or places with radiation exposure. To this aim, robots should be able to act and to interact with their surroundings by exerting forces, in contrast to merely observing the environment. In this context, there are scenarios where ground mobile robots encounter difficulties when dealing with uneven terrains or high structures. To overcome these problems, aerial vehicles (a.k.a. drones) are an effective solution. Unfortunately, drones can currently transport a limited payload and the complexity of most tasks involving physical interaction necessitates the use of multiple robots collaborating together in order to mitigate this issue [1]. Thus, this internship will propose novel planning and control methodologies for letting a multi-agent system - composed by multiple aerial robots - to fulfill tasks that require physical interventions (such as carrying and installing an antenna at high altitudes) by the robots.

The internship is part of a larger project (an illustrative figure is available at: https://partage.laas.fr/index.php/s/LKKGeTW8GBr33Wf) in which the considered system is composed of robots that have different sensing and acting capabilities: (i) the main drone team, which is in charge of collaboratively transporting an object; (ii) an aerial manipulator (i.e., a drone with a robotic arm attached under it), for more accurate manipulation of objects; (iii) the support drone team, that is in charge of helping the team in fulfilling an assigned task (e.g., exploring the environment for discovering obstacles and informing the teammates). See the complete internship description at the link provided at the beginning of this post.

Within this context, this internship will focus on a subproblem of the above-cited project, with possible further extensions:

• Collaborative payload transportation: the main research direction focuses on the design of control techniques for payload transportation using a team of aerial robots. Aerial robots have the potential for assisting humans with complex and hazardous tasks such as construction and package delivery. These tasks require aerial robots to possess the capability to transport and manipulate objects. Different mechanisms have been proposed to accomplish these tasks, but cables are particularly advantageous in terms of weight and cost. In this context, in order to be able to manipulate the object in 6 degrees of freedom (DoF) while addressing actuator constraints and avoiding the collision between robots, model predictive control (MPC) [2] can be a promising solution [3, 4].
• Distributed Control techniques (first possible extension): for a multi-robot system, it is possible to classify the control strategies as centralized or distributed. In the former, a single controller computes the control actions for each robot using global information about the entire system. In the latter, each robot computes its own control action using only partial information about the overall system. Considering the advantages related to robustness to faults and scalability to large scale systems, we aim to propose distributed controllers for tasks like navigation of multiple drones and transportation of payloads. Even in this case, an interesting direction is to use a distributed variant of Model Predictive Control [5], which allow us to consider state and input constraints of every robot separately. This will imply the formulation of a distributed optimization problem that can be solved using various techniques such as Consensus-ADMM [6, 7].
• Multi robot planning (second possible extension): there exist different approaches attempting to provide safety guarantees for a robot’s behavior. One interesting direction hinges on the concept of closed-loop sensitivity [8, 9]. The sensitivity locally captures how deviations in the model parameters (with respect to their nominal values) affect the evolution of the system in closed-loop, i.e., while taking into account the particular controller chosen to execute the task. Minimizing the sensitivity norm leads to increased intrinsic robustness of the robot. In our previous works [10, 11, 12], we introduced a motion planner designed to enhance sensitivity for a single mobile robot. The idea is to extend this concept for multi-robot systems carrying payloads.

This internship is within a collaborative project with the Rainbow group in Rennes (headed by Dr. Paolo Robuffo Giordano - https://scholar.google.com/citations?user=dpayTBUAAAAJ) and it will start with a literature review on the selected topic.

Project environment

The student will join the “Robotics and InteractionS” (RIS) team, being one of the three robotic equipes within LAAS-CNRS in Toulouse. RIS is an internationally recognized research team focused on developing autonomous mobile machines that integrate perception, reasoning, learning, action, and reaction capabilities. The main research areas of the team are Architectures for Autonomous Robots, Learning, Temporal Planning and Execution, and Algorithmic Motion Planning and Control. RIS is composed of 11 permanent researchers, 3 PostDocs, and several Ph.D. students.

More generally, 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 one of the largest and oldest robotic research departments in France.

The LAAS-CNRS robotic department has made world-class contributions in artificial intelligence, planning, perception, and autonomous robotic systems, such as humanoids and aerial robots.

Useful links:

• RIS webpage: https://www.laas.fr/public/en/ris
• LAAS-CNRS homepage: https://www.laas.fr/public/en

Candidate profile

• Essential – Bachelor’s degree in robotics, engineering, applied mathematics (or related fields)
• Essential – Very good knowledge of control theory
• Essential – Solid background in mathematics, optimization, and robotics
• Essential – Scientific curiosity and “thirst for knowledge” approach for learning, a.k.a. “hardworking” attitude
• Essential – Ability to work independently and in a group.
• Essential – Very good skills in programming. Especially, C/C++, Python, ROS/ROS2 (not necessary since we use custom software), and, in general, the ability to independently manage a large software
• Desired – Experience with drones, in robotic simulations (e.g., CoppeliaSim, Gazebo, Isaac) but ideally with real-world platforms

Supervisor’s profile

The main advisor is Dr. Marco Cognetti (https://scholar.google.com/citations?user=NAq-dYcAAAAJ). The student will be co-supervised by Alessia Fusco, a PhD student at LAAS-CNRS.

How to apply

Interested candidates are requested to apply by sending their CV and a motivation letter to and with the subject [Internship LAAS - multirobot]. The selection procedures will consist of an interview that will be organized in English. The candidate will be asked to present his/her previous experience and to discuss the project. The candidate will also be asked to solve a small exercise to assess his/her mathematical and programming skills. The position will remain open until satisfactory candidates are found.

Internship duration/funding/Ph.D. opportunity

The internship will (ideally) last 6 months, and each student will receive about 650 EUR net per month as reimbursement of expenses. The internship can lead to a Ph.D. in the RIS team if both the student and the supervisor are interested. Starting internship date (flexible): spring/summer 2026.

References

[1] J. J. Roldan-Gomez and A. Barrientos. “Special Issue on Multi-Robot Systems: Challenges, Trends, and Applications”. In: Applied Sciences 11.24 (2021). ISSN: 2076-3417.

[2] C. E. Garcia et al. “Model predictive control: Theory and practice- A survey”. In: Automatica 25.3 (1989), pp. 335–348.

[3] G. Li and G. Loianno. “Nonlinear Model Predictive Control for Cooperative Transportation and Manipulation of Cable Suspended Payloads with Multiple Quadrotors”. In: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2023, pp. 5034–5041.

[4] S. Sun and A. Franchi. Nonlinear MPC for Full-Pose Manipulation of a Cable-Suspended Load using Multiple UAVs. 2023. arXiv: 2301.08545 [cs.RO].

[5] N. De Carli et al. “Distributed NMPC for Cooperative Aerial Manipulation of Cable-Suspended Loads”. In: IEEE Robotics and Automation Letters 10.10 (2025), pp. 10546–10553.

[6] T. Halsted et al. A Survey of Distributed Optimization Methods for Multi-Robot Systems. 2021. arXiv: 2103.12840 [cs.RO].

[7] J. Chen. A Brief Tutorial on Consensus ADMM for Distributed Optimization with Applications in Robotics. 2024. arXiv: 2410.03753 [math.OC].

[8] P. Robuffo Giordano et al. “Trajectory generation for minimum closed-loop state sensitivity”. In: Proc. IEEE Int. Conf. on Robotics and Automation (ICRA). 2018, pp. 286–293.

[9] A. Afifi et al. “Safe and Robust Planning for Uncertain Robots: A Closed-Loop State Sensitivity Approach”. In: IEEE Robotics and Automation Letters 9.11 (2024), pp. 9962–9969.

[10] S. Wasiela et al. “A Sensitivity-Aware Motion Planner (SAMP) to Generate Intrinsically-Robust Trajectories”. In: Proc. IEEE Int. Conf. on Robotics and Automation (ICRA). 2023, pp. 1–7.

[11] S. Wasiela et al. “Learned Uncertainty Tubes via Recurrent Neural Networks for Planning Robust Robot Motions”. In: 27th European Conference on Artificial Intelligence (ECAI). 2024.

[12] S. Wasiela et al. “Robust Motion Planning With Accuracy Optimization Based on Learned Sensitivity Metrics”. In: IEEE Robotics and Automation Letters 9.11 (2024), pp. 10113–10120.