Internship DYNALOG : Multi-Robot Flow and Local Optimization in Dense Warehouse Environments

Abstract

This internship is part of the CESI LINEACT DYNALOG project, which aims to optimize fleets of autonomous robots[1] in warehouse environments through a dynamic architecture coupled with a digital twin. The objective is to study and compare different local optimisation strategies for multi-robot flows organised globally in a high-density storage environment. The work will combine algorithm design, simulation-based validation, and experimental deployment on real robotic platforms.

Laboratory presentation

CESI LINEACT (UR 7527), Laboratory for Digital Innovation for Businesses and Learning to Support the Competitiveness of Territories, anticipates and accompanies the technological mutations of sectors and services related to industry and construction. The historical proximity of CESI to companies is a determining factor in our research activities. It has led us to focus our efforts on applied research close to companies and in partnership with them. A human-centered approach coupled with the use of technologies, as well as territorial networking and links with training, has enabled the construction of cross-cutting research; it puts humans, their needs, and their uses at the center of its issues and addresses the technological angle through these contributions.

Its research is organized according to two interdisciplinary scientific teams and several application areas.

• Team 1 "Learning and Innovating" mainly concerns Cognitive Sciences, Social Sciences, and Management Sciences, Training Techniques, and those of Innovation. The main scientific objectives are the understanding of the effects of the environment, and, more particularly, of situations instrumented by technical objects (platforms, prototyping workshops, immersive systems...) on learning, creativity, and innovation processes.

• Team 2 "Engineering and Digital Tools" mainly concerns Digital Sciences and Engineering. The main scientific objectives focus on modeling, simulation, optimization, and data analysis of cyber-physical systems. Research also focuses on decision-support tools and on the study of human-system interactions, particularly through digital twins coupled with virtual or augmented environments.

These two teams develop and cross their research in application areas such as

• Industry 5.0,

• Construction 4.0 and Sustainable City,

• Digital Services.

Areas supported by research platforms, mainly the one in Rouen dedicated to Factory 5.0 and the one in Nanterre dedicated to Factory 5.0 and Construction 4.0.

Scientific context 

Optimising fleets of mobile robots in logistics environments poses complex combinatorial problems. As robot density increases, congestion, mutual blocking, resource access conflicts and overall performance degradation become critical issues.

As part of the DYNALOG project, a dynamic architecture combined with a digital twin makes it possible to evaluate the impact of coordination strategies upstream before their actual deployment. The internship is part of CESI LINEACT's "Engineering and Digital Tools" programme, with a strong link between modelling, simulation and experimental validation.

Subject 

The internship focuses on hybrid coordination strategies for dense multi-robot systems in storage environments, combining global Multi-Agent Path Finding (MAPF) with locally autonomous decision-making.

The storage facility is characterised by:

• A large number of robots operating simultaneously,

• Shared and potentially congested areas (aisles, intersections, loading zones),

• Time constraints related to logistics tasks,

• Heterogeneous robots with different kinematic and sensing capabilities.

The objective is to relax its rigidity of Multi-Agent Path Finding (MAPF) by introducing sufficient local autonomy to allow each robot to decide, in real time, whether to:

• Enter or postpone entering a shared area,

• Follow another robot at a safe distance,

• Yield or negotiate passage in case of local conflicts,

• Deviate slightly from its planned trajectory while preserving global consistency.

Scientific and technical challenges include:

• Integration of local reactive navigation,

• Design of decision policies consistent with global spatio-temporal reservations,

• Prevention of deadlocks in high-density scenarios,

• Quantification of the trade-off between global optimality and local robustness,

• Transferability to heterogeneous virtual / physical robots under real sensing and communication constraints.

Prior works in the laboratory 

The CESI LINEACT laboratory has been working on the uses of robotics in industry for several years, either through R&D contracts or research projects (Corot, Oasis, Antihpert, Scopes, Jenii, etc.). Research engineers are dedicated to this work.

Work program

Planned steps (indicative 6-month schedule):

• State of the art on AMR task allocation, dynamic pickup-and-delivery, and storage assignment; definition of KPIs and events.

• Formalization of the problem (tasks, priorities, constraints, objective function) and baseline dispatching heuristics.

• Design of a rolling-horizon scheduler (optimization + fast heuristics), including re-optimization triggers.

• Implementation and testing by simulation of discrete events of benchmark and/or randomly generated scenarios (priority changes, downtime, congestion).

• Results analysis, sensitivity study, and writing of a final report with reproducible code and datasets.

Skills

Scientific and technical skills:

• Mobile robotics and multi-agent systems

• Optimisation and operational research

• Robotic simulation (ROS/ROS2, Gazebo, Webots or equivalent)

• Python (mainly) and C++

• Basic knowledge of distributed architectures and real-time systems

Operating Systems

• LINUX (Ubuntu/WSL2) & WINDOWS

Interpersonal Skills:

• Autonomy and analytical skills

• Methodological rigour

• Ability to formalise and compare approaches

• Teamwork in a project context

Required Profile:

• Research Master 2.

Workplace : CESI Saint-Etienne du Rouvray

Start date : March 2026

Duration : 6 months