2025Activity reportProject-Team​​CHROMA

Project-team​​​‌ positioning

The team carries‌ out research across the‌​‌ full (software) stack of​​ an autonomous driving system.​​​‌ This goes from perception‌ of the environment to‌​‌ motion forecasting and trajectory​​ optimization. While most of​​​‌ the techniques that we‌ develop can stand on‌​‌ their own and are​​ typically tested on our​​​‌ experimental platforms, we slowly‌ move towards their complete‌​‌ integration. This will result​​ in a functioning autonomous​​​‌ driving software stack. Beyond‌ that point, we envision‌​‌ focusing our research on​​ developing new methods that​​​‌ improve the individual performance‌ of each of the‌​‌ stack’s components, as well​​ as the global performance.​​​‌ This is similar to‌ how autonomous driving companies‌​‌ operate (e.g. Waymo, Cruise,​​ Tesla). The research topics​​​‌ that we explore are‌ addressed by a very‌​‌ long list of international​​ research laboratories and private​​​‌ companies. However, in terms‌ of scope, we find‌​‌ the research groups of​​​‌ Prof. Dr.-Ing. Christoph Stiller​ (KIT), Prof. Marcelo Ang​‌ (NUS), Prof. Daniela Rus​​ (MIT) and Prof. Wolfram​​​‌ Burgard (TRI California) to​ be the closest to​‌ us; we have active​​ interconnections with these research​​​‌ groups (e.g. in the​ scope of the IEEE​‌ RAS Technical Committee AGV-ITS​​ we are co-chairing any​​​‌ of the related annual​ Workshops). At the national​‌ level, we are cooperating​​ in the framework of​​​‌ several R&D projects with​ UTC, Institut Pascal Clermont-Ferrand,​‌ University Gustave Eiffel, and​​ the Inria Teams ASTRA,​​​‌ ACENTAURI and CONVECS. Our​ main research originality relies​‌ in the combination of​​ Bayesian approaches, AI technologies,​​​‌ Human-Vehicle interactions models, Robust​ State Estimation formalism,​‌ and a mix of​​ Real experiments and Formal​​​‌ methods for validating our​ technologies in complex real-world​‌ dynamic scenarios.

Our research​​ on visual-inertial sensor fusion​​​‌ is closely related to​ the research carried out​‌ by the group of​​ Prof. Stergios Roumeliotis (University​​​‌ of Minnesota) and the​ group of Prof. Davide​‌ Scaramuzza (University of Zurich).​​ Our originality in this​​​‌ context is the introduction​ of closed-form solutions instead​‌ of filter-based approaches.

Collaborations​​

• Philippe Martinet, Research Director​​​‌ at Inria, ACENTAURY team​ (Sophia Antipolis).Co-supervision of a​‌ PhD thesis (K. Bhowmik)​​ with A. Spalanzani. Road​​​‌ users motion prediction. Publications​ 18 and partner in​‌ projects ANR 'Annapolis'.
• Radu​​ Matescu, Research Director at​​​‌ Inria, head of the​ CONVECS team, Grenoble.Co-supervision of​‌ a PhD thesis (J.B.​​ Horel, co-supervised with A.​​​‌ Renzaglia and C. Laugier).​ Joint publications and joint​‌ participation in the PRISSMA​​ project.

Project-team positioning

In his​ reference book Planning algorithms​‌32, S. LaValle​​ discusses the different dimensions​​​‌ that make the motion​ planning a complex problem,​‌ which are the number​​ of robots, the obstacle​​​‌ regions, the uncertainty of​ perception and action, and​‌ the allowable velocities. In​​ particular, it is emphasized​​​‌ that multiple robots planning​ problems in complex environments​‌ are NP-hard problems, which​​ implies that exact approaches​​​‌ have exponential time complexities​ in the worst case​‌ (unless P=NP). Moreover, dynamic​​ and uncertain environments, as​​​‌ human-populated ones, expand this​ complexity. In this context,​‌ we aim at scaling​​ up decision-making in human-populated​​​‌ environments and in multi-robot​ systems, while dealing with​‌ the intrinsic limits of​​ the robots and machines​​​‌ (computation capacity, limited communication).​ To address these challenges,​‌ we explore new algorithms​​ and AI architectures following​​​‌ three directions: online planning/self-organization​ for real-time decision/control, machine​‌ learning to adapt to​​ the complexity of uncertain​​​‌ environments, and combinatorial optimization​ to deal with offline​‌ constrained problems. Combining these​​ approaches, seeking to scale​​​‌ them up, and also​ evaluating them with real​‌ platforms are also elements​​ of originality of our​​​‌ work.

We share these​ goals with other laboratories/teams​‌ in the world, such​​ as the IntRoLab at​​​‌ Sherbrooke University (Canada) led​ by Prof. F. Michaud​‌ (we have established an​​ associated team since 2024).​​​‌ We can also mention​ the Learning Agents Research​‌ Group (LARG) within the​​ AI Lab at the​​​‌ University of Texas (Austin,​ USA) led by Prof.​‌ P. Stone, the Autonomous​​ Systems Lab at ETH​​ Zurich (Switzerland) led by​​​‌ R. Siegwart, the Robotic‌ Sensor Networks Lab at‌​‌ the University of Texas​​ (Austin, USA) led by​​​‌ Prof. V. Isler, and‌ the Autonomous Robots Lab‌​‌ at NTNU (Norway) to​​ cite a few. At​​​‌ Inria, we share some‌ of the objectives with‌​‌ the LARSEN team in​​ Nancy (multi-agent machine learning,​​​‌ multi-robot planning) and the‌ RAINBOW team in Rennes‌​‌ (multi-UAV planning). We have​​ also collaborations with the​​​‌ ACENTAURY team, in Sophia‌ Antipolis, about autonomous navigation‌​‌ among humans. In France,​​ among other labs involved​​​‌ in similar subjects, we‌ can cite the LAAS/RIS‌​‌ team (CNRS, Toulouse), the​​ ISIR lab/Sorbonne U. Paris​​​‌ (Prof. N. Bredeche on‌ swarm robotics), the CRISTAL‌​‌ Lab in Lille University​​ (eg. the SMAC team​​​‌ led by Prof. P.‌ Mathieu), and the MAD‌​‌ team of GREYC lab​​ in Caen University.

Collaborations​​​‌

• Isabelle Guerin Lassous, Prof.‌ at LIP lab., Univ.‌​‌ Lyon 1. Co-supervision of​​ two PhD thesis, A.​​​‌ Bonnefond and T. Balaguer‌ 26, with O.‌​‌ Simonin. Cooperation on communication​​ in UAV fleets. Publications​​​‌ 15, 16 and‌ partner in projects ANR‌​‌ 'CONCERTO' and Inria/AID 'DynaFlock'.​​
• Isabelle Fantoni, CNRS Research​​​‌ Director at LS2N Lab.,‌ Nantes. Co-supervision of the‌​‌ PhD thesis of T.​​ Balaguer 26 with O.​​​‌ Simonin. Cooperation on control‌ of UAV fleets. Publications‌​‌ 15, 16 and​​ partner in the ANR​​​‌ 'VORTEX' project.
• Laetitia Matignon,‌ Asso. Professor at LIRIS‌​‌ lab., Univ. Lyon. Cooperation​​ on Multi-Robot Deep/RL methods​​​‌ with O. Simonin and‌ J. Saraydaryan. Publications, eg.‌​‌ 31, and partner​​ in 'REMEMBER' AI Chair​​​‌ and ANR/BPI 'SOLAR-Nav' projects.‌
• Lara Brinon Arranz, Asso.‌​‌ Professor INP at GIPSA​​ Lab, Grenoble. Cooperation on​​​‌ multi-robot source seeking with‌ A. Renzaglia 30.‌​‌ Partner in the new​​ ANR 'ARCAVE' project.
• Jaeger​​​‌ Lab at University of‌ Chicago: B. Saintyves is‌​‌ collaborating with Heinrich Jaeger,​​ full professor at University​​​‌ of Chicago, on material‌ testing and physical simulations‌​‌ for Granulobot and on​​ the development of the​​​‌ Shellbot prototype.

the autonomous‌ version of the Renault‌​‌ Zoe car, the Pepper​​ humanoid, the PX4 Vision​​​‌ UAV

the autonomous version‌ of the Renault Zoe‌​‌ car, the Pepper humanoid,​​ the PX4 Vision UAV​​​‌

7.1.1 Aerial Robot platform​​ : "DIONE" project

Participants:​​​‌ Nicolas Valle, Theo​ Porche [INSA intern],​‌ Olivier Simonin.

• Design​​ of a UAV (drone)​​​‌ platform, in collaboration with​ INSA Mechanical Engineering Department​‌ & Ampere Lab (Ludovic​​ Pouliquen, Paolo Masssioni) and​​​‌ the Agora team. This​ project, called DIONE (Drone​‌ Intelligent pour l’Observation et​​ la Navigation autonome multi-Environnement),​​​‌ is led by Nicolas​ Valle and aims to​‌ develop a modular aerial​​ robotics platform. The goal​​​‌ is to obtain a​ four-motor UAV on which​‌ different sensors can be​​ mounted according to the​​​‌ research needs of team​ members. Initially, the robot​‌ will offer several geolocation​​ options (GNSS, GNSS-RTK, indoor​​​‌ infrared LightHouse), and a​ 2-axis mount on the​‌ underside that can accommodate​​ a Livox 360° LiDar.​​​‌ The DIONE project is​ currently being developed in-house​‌ and will eventually be​​ available as open-source.

7.1.2​​​‌ Barakuda

Participants: Lukas Rummelhard​, Thomas Genevois,​‌ Robin Baruffa, Hugo​​ Bantignies, Nicolas Turro​​​‌.

Within the scope​ of the ANR Challenge​‌ MOBILEX, a 4-wheel all-terrain​​ Barakuda robot from Shark​​​‌ Robotics is provided, and​ will be equipped with​‌ sensors and compute capabilities​​ to achieve increasing level​​​‌ of autonomy.

8.2.1 Situation Understanding​​ and Motion Forecasting

Participants:​​​‌ Kaushik Bhowmik, Anne‌ Spalanzani.

Trajectory forecasting‌​‌ in urban environments is​​ a critical task that​​​‌ needs to be addressed‌ for the safety of‌​‌ autonomous vehicles, particularly in​​ urban road intersection scenarios,​​​‌ where agents exhibit diverse‌ behaviors mainly due to‌​‌ complex interactions between agents​​ and the environment and​​​‌ the diversity of paths‌ available to the agents.‌​‌ Current state-of-the-art methods do​​ not perform well in​​​‌ urban road intersection scenarios.‌ To address this issue,‌​‌ the proposed novel framework​​ CandidateGraph-Net (CG-Net), improves trajectory​​​‌ prediction in urban road‌ intersection scenarios by encoding‌​‌ the available candidate centerlines​​ at the current location​​​‌ of the target agent.‌ The proposed interaction encoder‌​‌ in CG-Net is inspired​​ by human behavior. It​​​‌ is modeled utilizing a‌ bipartite graph attention network‌​‌ to predict the trajectory​​ of the target agent.​​​‌ It estimates the trajectory‌ in the same way‌​‌ as humans anticipate the​​ trajectory of other vehicles​​​‌ and pedestrians in dynamic‌ environments. The agent embeddings‌​‌ in the interaction encoder​​ at each time step​​​‌ pay attention to nearby‌ agents and surrounding scene‌​‌ elements simultaneously. This enables​​​‌ the model to learn​ how to prioritize interactions​‌ between nearby agents and​​ the environment map. Further,​​​‌ CG-Net’s performance is evaluated​ using the Argoverse 2​‌ motion forecasting dataset. The​​ results demonstrate its effectiveness​​​‌ in urban road intersection​ scenarios, with an overall​‌ improvement in key metrics​​ such as minFDE and​​​‌ minADE compared to baseline​ methods. These improvements highlight​‌ CG-Net’s ability to perform​​ better motion forecasting in​​​‌ urban road intersection scenarios.​ This work was accepted​‌ to the IROS 2025​​ conference 18.

8.2.2​​​‌ AI-driven Motion Planning and​ Temporal Multi-Modality Sensor Fusion​‌ for Semantic Grid Prediction​​

Participants: Gustavo Salazar-Gomez,​​​‌ Anne Spalanzani, Lukas​ Rummelhard, Christian Laugier​‌.

Local trajectory planning​​ for autonomous vehicles in​​​‌ urban scenarios requires reliable​ decisions around dense traffic​‌ and several agents' interactions.​​ The planner's input strongly​​​‌ influences its reaction to​ different situations, hence the​‌ importance of choosing the​​ appropriate representation. Birds' eye-​​​‌ view (BEV) grids provide​ spatial coverage, while vectorized​‌ representations offer efficiency but​​ risk missing information. We​​​‌ propose to use flow-guided​ occupancy grids, which are​‌ BEV occupancy maps augmented​​ with cell flow vectors​​​‌ to combine occupancy, motion​ and uncertainty. Based on​‌ this representation, we have​​ developed PlanFlow, a model​​​‌ based on a compact​ CNN as backbone with​‌ a MLP decoder, trained​​ combining L1 and collision​​​‌ aware losses. We trained​ and evaluated PlanFlow on​‌ nuScenes against BEV input​​ baselines, achieving robust accuracy​​​‌ and low collision rates,​ displaying improvement over the​‌ SOTA approaches by using​​ flow-guided grids for trajectory​​​‌ planning reasoning. This work​ will be presented at​‌ IEEE Intelligent Vehicle(IV) 2026.​​

8.2.3 Dynamic Scene Prediction​​​‌ for Urban Driving Scene​ Using Occupancy Grid Maps​‌

Participants: Rabbia Asghar,​​ Lukas Rummelhard, Anne​​​‌ Spalanzani, Christian Laugier​.

Accurate prediction of​‌ driving scenes is essential​​ for road safety and​​​‌ autonomous driving. This remains​ a challenging task due​‌ to uncertainty in sensor​​ data, the complex behaviors​​​‌ of agents, and possibility​ of multiple feasible futures.​‌ Over the course of​​ Rabbia's PhD, we have​​​‌ addressed the prediction problem​ by representing the scene​‌ as dynamic occupancy grid​​ maps (DOGMs) and integrating​​​‌ semantic information. We employ​ deep learning-based spatiotemporal approach​‌ to predict the evolution​​ of scene and learn​​​‌ complex behaviours. We have​ proposed a novel multi-task​‌ framework that leverages dynamic​​ OGMs and semantic information​​​‌ to predict both future​ vehicle semantic grids and​‌ the future flow of​​ the scene. This incorporation​​​‌ of semantic flow not​ only offers intermediate scene​‌ features but also enables​​ the generation of warped​​​‌ semantic grids. Evaluation on​ the real-world NuScenes dataset​‌ demonstrates improved prediction capabilities​​ and enhanced ability of​​​‌ the model to retain​ dynamic vehicles within the​‌ scene 28. We​​ then focused on predicting​​​‌ the behaviors of vehicle​ agents but also identifying​‌ other dynamic entities within​​ the scene and anticipating​​​‌ their possible evolutions. Scene​ evolution is predicted as​‌ agent semantic grids, dynamic​​ occupancy grid maps, and​​​‌ scene flow grids. Leveraging​ flow-guided prediction, these grids​‌ enable diverse future predictions​​ for vehicles and dynamic​​ elements while also capturing​​​‌ inter-grid dependencies through specialized‌ loss functions 29.‌​‌ Rabbia Asghar defended her​​ PhD in July 2025​​​‌ 25.

Complex driving‌ scene forcasting

8.4.1‌ Motion-planning in dense pedestrian‌​‌ environments

Participants: Anne Spalanzani​​, Jason Chemin,​​​‌ Manuel Diaz Zapata.‌

Under the coordination of‌​‌ Anne Spalanzani, we study​​ new motion planning algorithms​​​‌ to allow robots/vehicles to‌ navigate in human populated‌​‌ environment while predicting pedestrians'​​ motions. We model pedestrians​​​‌ and crowd behaviors using‌ notions of social forces‌​‌ and cooperative behavior estimations.​​ We investigate new methods​​​‌ to build safe and‌ socially compliant trajectories using‌​‌ theses models of behaviors.​​ We propose proactive navigation​​​‌ solutions as well as‌ deep learning ones.

Since‌​‌ 2018 we've been working​​ on modelling crowds and​​​‌ autonomous vehicles using Extended‌ Social Force Models (in‌​‌ the scope of Manon​​ Predhumeau's PhD) and Proactive​​​‌ Navigation for navigating dense‌ human populated environments (in‌​‌ the scope of Maria​​ Kabtoul's PhD). The focus​​​‌ of the first work‌ has been on the‌​‌ realistic simulation of crowds​​ in shared spaces with​​​‌ an autonomous vehicle (AV),‌ see Fig. 4.a.‌​‌ We proposed an agent-based​​ model for pedestrian reactions​​​‌ to an AV in‌ a shared space, based‌​‌ on empirical studies and​​ the state of the​​​‌ art. The model includes‌ an AV with Renault‌​‌ Zoé car's characteristics, and​​ pedestrians' reactions to the​​​‌ vehicle. The model extends‌ the Social Force Model‌​‌ with a new decision​​ model, which integrates various​​​‌ observed reactions of pedestrians‌ and pedestrians groups. The‌​‌ SPACiSS simulator is an​​ opensource simulator still used​​​‌ by the team. In‌ the scope of the‌​‌ Solar-Nav project, we have​​ adapted this work on​​​‌ the Mirokai Robot in‌ an hospital context.

A‌​‌ scene of an Autonomous​​ robot with pedestrians

A​​​‌ scene of an Autonomous‌ robot with pedestrians

8.4.2​​​‌ Attention Graph for Multi-Robot​ Social Navigation with Deep​‌ Reinforcement Learning

Participants: Jacques​​ Saraydaryan, Takieddine Soualhi​​​‌.

Multisoc architecture

Learning robot navigation​​ strategies among pedestrian is​​​‌ crucial for domain based​ applications. Combining perception, planning​‌ and prediction allows to​​ model the interactions between​​​‌ robots and pedestrians, resulting​ in impressive outcomes especially​‌ with recent approaches based​​ on deep reinforcement learning​​​‌ (RL). However, these works​ do not consider multi-robot​‌ scenarios.

In this work,​​ we defined MultiSoc,​​​‌ a new method for​ learning multi-agent socially aware​‌ navigation strategies using RL​​ (see illustration fig. 5​​​‌). Inspired by recent​ works on multi-agent deep​‌ RL, our method leverages​​ graph-based representation of agent​​​‌ interactions, combining the positions​ and fields of view​‌ of entities (pedestrians and​​ agents). We evaluated our​​​‌ approach on simulation and​ provided a series of​‌ experiments in a set​​ of various conditions (number​​​‌ of agents/pedestrians). Empirical results​ show that our method​‌ learns faster than social​​ navigation deep RL mono-agent​​​‌ techniques, and enables efficient​ multi-agent implicit coordination in​‌ challenging crowd navigation with​​ multiple heterogeneous humans. See​​​‌ AAMAS 2024 publication 31​.

This work continued​‌ in 2025 (supported by​​ the SOLAR-Nav project) and​​​‌ aims to integrate the​ real constraints of robots​‌ into an experiment with​​ real robots. The RL​​​‌ simulator has been upgraded​ to incorporate robot probes​‌ (e.g. LiDAR) and a​​ new HAMRON (Human-Aware multi-Robot​​​‌ Navigation) model inspired by​ Multisoc has been trained.​‌ We demonstrate that our​​ navigation policy can handle​​​‌ both human and static​ obstacles thanks its perception​‌ system. This contribution is​​ currently under review at​​​‌ ICRA 2026. We extend​ this work by improving​‌ our robot's social compliance​​ around humans. To achieve​​​‌ this, we are currently​ investigating a new reward​‌ function that takes human​​ proxemics into account. Initial​​​‌ results are promising, showing​ improved performance across the​‌ employed social metrics compared​​ to existing approaches.

8.5.1 Navigation​ Among Movable Obstacles (NAMO):​‌ extension to multi-robot and​​ social constraints

Participants: Jacques​​​‌ Saraydaryan, Olivier Simonin​, David Brown.​‌

In CHROMA, we study​​ NAMO (Navigation Among Movable​​​‌ Obstacles) problems since 2018​ . The PhD thesis​‌ of Benoit Renault (2019-23)​​ allowed us to extend​​​‌ existing algorithms with the​ social cost of object​‌ placement (Social-NAMO 35)​​ and the generalisation to​​​‌ multi-robot NAMO problems 34​.

In 2023, we​‌ obtained an Inria ADT​​ project, called NAMOEX, aiming​​​‌ to extend the Benoit​ Renault's NAMO simulator. Thanks​‌ to David Brown (Ing.,​​ 2023-25), we robustified the​​ simulator and studied multi-robot​​​‌ NAMO strategies, leading to‌ a publication in IROS‌​‌ 2024 34. In​​ 2024 and 2025, we​​​‌ developped a connexion between‌ our S-NAMO planner and‌​‌ the Gazebo robotic simulator,​​ also extended as a​​​‌ monitoring tool for experiments‌ with real mobile robots,‌​‌ see Fig. 6.​​ This new simulator, NAMO-SIM,​​​‌ has been published recently‌ in journal JOSS 11‌​‌ (open-source software diffusion).

8.5.2​​ Multi-UAV Exploration and 3D​​​‌ Reconstruction

Participants: Alessandro Renzaglia‌, Benjamin Sportich,‌​‌ Kenza Boubakri, Olivier​​ Simonin.

Illustration of​​​‌ UAV trajectories during an‌ exploration mission.

Multi-robot‌​‌ teams, especially when they​​ include Unmanned Aerial Vehicles​​​‌ (UAVs), are highly efficient‌ systems for assisting humans‌​‌ in gathering information on​​ large and complex environments​​​‌ (see Figure 7).‌ In these scenarios, cooperative‌​‌ exploration and 3D reconstruction​​ are two fundamental problems​​​‌ with numerous important applications,‌ such as mapping, inspection‌​‌ of complex structures, and​​ search and rescue missions.​​​‌ In both cases, the‌ goal of the robots‌​‌ is to navigate through​​ the environment and cooperate​​​‌ to acquire new information‌ in order to complete‌​‌ the mission in the​​ shortest possible time 36​​​‌.

This line of‌ research is mainly carried‌​‌ out within the ANR​​ project AVENUE, which focuses​​​‌ on the coordination of‌ a fleet of UAVs‌​‌ to efficiently explore and​​ reconstruct unknown 3D complex​​​‌ scenes. In particular, both‌ the task execution time‌​‌ and the accuracy of​​ the final map are​​​‌ considered as the key‌ metrics to optimize. First‌​‌ results focused on the​​ single-robot version of the​​​‌ problem, and we proposed‌ a novel modular Next-Best-View‌​‌ (NBV) planning framework that​​ explicitly uses a reconstruction​​​‌ quality objective to guide‌ the exploration planning 27‌​‌. To do so,​​ our approach introduced new​​​‌ and efficient methods for‌ view generation and selection‌​‌ of viewpoint candidates that​​ are adaptive to user-defined​​​‌ quality requirements, fully exploiting‌ the uncertainty encoded in‌​‌ a Truncated Signed Distance​​ Field (TSDF) representation of​​​‌ the environment. This results‌ in informed and efficient‌​‌ exploration decisions tailored towards​​ the predetermined objective. Current​​​‌ work is now focused‌ on extending this solution‌​‌ to multi-UAV systems to​​ coordinate their decision-making in​​​‌ order to fully exploit‌ the capabilities of a‌​‌ fleet of UAVs carrying​​ out the task cooperatively.​​​‌

8.5.3 Multi-robot agricultural itineraries‌ planning (NINSAR project)

Participants:‌​‌ Simon Ferrier, Olivier​​ Simonin, Alessandro Renzaglia​​​‌.

Example of multi-robot‌ Planning simulated in Gazebo‌​‌

The NINSAR project, part‌​‌ of the PEPR AgroEcologie​​ & Numerique, aims to​​​‌ use robots to help‌ the agricultural sector. In‌​‌ the PhD thesis of​​ Simon Ferrier, started on​​​‌ summer 2024, we define‌ and study algorithms for‌​‌ the mission planning of​​ a fleet of mobile​​​‌ robots treating rows of‌ fields of any-shape.

To‌​‌ deal with minimum time​​ mission (makespan), we defined​​​‌ and compared two approaches:‌ 1) a heuristic-based division‌​‌ and allocation of rows​​​‌ to robots 2) a​ Branch and Bound algorithm​‌ computing the optimal solution,​​ and an anytime version​​​‌ combining both. An illustration​ of the problem and​‌ of a solution is​​ presented in figure 8​​​‌. This work is​ under review for publication.​‌

In 2025, we generalized​​ this work to the​​​‌ Multi-Robot Task Allocation (MRTA)​ problem. We propose a​‌ new heuristic-based clustering algorithm​​ (AttrAP), that aims to​​​‌ minimize the maximum cost​ among the robots (makespan).​‌ AttrAP is divided into​​ three parts: (1) heuristic-based​​​‌ allocation of each task​ iteratively to a robot,​‌ (2) solving a TSP​​ for each robot, and​​​‌ (3) improving the solution​ with local optimization. We​‌ compared our approach to​​ a state-of-the-art GA algorithm,​​​‌ showing we obtain generally​ better solutions in shorter​‌ time. This work has​​ been subimitted for publication.​​​‌

Our next objective is​ to integrate reparing plans​‌ within online scenarios having​​ unexpected events.

8.6.1 UAV Chain Network​‌ Creation in Cluttered Environment​​ with Flocking Rules and​​​‌ Routing Data

Participants: Théotime​ Balaguer, Olivier Simonin​‌.

Chain creation

Chain​​ creation

In the context​​ of the PhD thesis​​​‌ of Théotime Balaguer and​ the associated team with​‌ Univ. of Sherbrooke (ROBLOC​​ project), we proposed a​​​‌ new decentralized algorithm to​ allow a fleet of​‌ drones to connect a​​ source area to one​​​‌ or several target areas.​ Our approach relies on​‌ the extension of the​​ flocking model. We propose​​​‌ an algorithm ensuring the​ emergence of “mission” communication​‌ paths from a base​​ drone to leaders flying​​​‌ towards their target areas.​ Drones dynamically integrate the​‌ “mission” path while the​​ flocking stretches. We also​​​‌ added a new avoiding​ force close to obstacles​‌ perturbating communication. The originality​​ of the model is​​​‌ to be decentralized and​ to exploit routing data​‌ to optimize dynamically the​​ mission paths in term​​​‌ of distance and QoS.​ This work is illustrated​‌ in figure 9 and​​ was published in the​​​‌ IROS 2025 conference 16​. Théotime Balaguer, co-supervized​‌ by O. Simonin, I.​​ Guérin Lassous (Lyon1/LIP) and​​​‌ I. Fantoni (CNRS/LS2N Nantes),​ defended his PhD thesis​‌ on November 2025 26​​. The relative co-simulator​​​‌ we developed and used,​ DANCERS, has been published​‌ in ECMR 2025 15​​.

8.6.2 Swarm of​​​‌ visualy connected UAVs for​ exploration of unknown subterrean​‌ environments

Participants: Mathis Fleuriel​​, Olivier Simonin,​​​‌ Elena Vanneaux.

The​ use of unmanned aerial​‌ systems (UAS) is a​​ promising solution for search​​​‌ and rescue (SAR) operations​ conducted to find missing​‌ persons. In the ANR​​ VORTEX project, we study​​​‌ how it is possible​ to deploy rapidly autonomous​‌ drones in indoor environments​​ without using conventional communications​​​‌ or mapping but by​ leveraging cameras & vision-based​‌ processes. We propose to​​ explore an approach where​​​‌ a swarm of small​ UAVs (quadrotors) will quickly​‌ deploy in the environment​​ while forming a dynamic​​ mesh of sensors. By​​​‌ flying autonomously but keeping‌ visual contact with at‌​‌ least another UAV, each​​ drone will be able​​​‌ to estimate its relative‌ location but also to‌​‌ communicate information from drone​​ to drone. As a​​​‌ consequence, drones can form‌ a dynamic chain, guided‌​‌ by a leader, allowing​​ the exploration of the​​​‌ environment.

Since 2024 we‌ study exploration stategies through‌​‌ Mathis Fleuriel's PhD thesis​​ (co-supervized by E. Vanneaux​​​‌ and O. Simonin). We‌ proposed a first multi-agent‌​‌ strategy allowing to maintain​​ and reconfigure a chain​​​‌ of drones, following a‌ dynamic leader (the leader‌​‌ role can change when​​ the chain meet a​​​‌ deadend or a detect‌ a loop). This work‌​‌ has been published in​​ ECMR 2025 conference 19​​​‌. In the end‌ of 2025, we proved‌​‌ in discretized environment the​​ termination and completude of​​​‌ the strategy. We also‌ developed a new discrete‌​‌ simulator (based on Mesa)​​ to study different variants​​​‌ of the strategy.

8.6.3‌ Robotic Matter

Participants: Baudouin‌​‌ Saintyves, Olivier Simonin​​.

Tensile test experiment​​​‌ on a passive proof‌ of concept, toward the‌​‌ conception of Shellbots. Full​​ deformation cycle from left​​​‌ to right.

Baudouin Saintyves​​ made progress on the​​​‌ systematic mechanical study of‌ a preliminary passive version‌​‌ of the shellbot,​​ exploring mechanical properties that​​​‌ can be used for‌ a robotic implementation. After‌​‌ a first experimental campaign​​ using a tensile test​​​‌ machine, he is currently‌ building an experimental platform‌​‌ to test the monolayers​​ by controlling more deformation​​​‌ degree of freedom and‌ develop design rules for‌​‌ robotization. In parallel, a​​ project has been submitted​​​‌ to a PEPR Organic‌ Robotics (O2R) call. It‌​‌ aims at funding the​​ study and development of​​​‌ distributed control and tasks‌ in robotic granular shell‌​‌ monolayers, in cooperation with​​ Prof. H. Jaeger from​​​‌ Chicago University.

B. Saintyves‌ is also involved in‌​‌ activities combining robotics, physics,​​ and arts. In 2025,​​​‌ he was invited with‌ his project shapes of‌​‌ emergence for a residency​​ including development and a​​​‌ week of performance and‌ outreach presentations at the‌​‌ Society for Arts and​​ Technologies in Montreal, Canada.​​​‌

9.1.1 IRT Nanoelec PULSE​​​‌ – Security of Autonomous‌ Mobile Robotics (2023-2026)

Participants:‌​‌ Lukas Rummelhard, Robin​​ Baruffa, Hugo Bantignies​​​‌, Jean-Baptiste Horel,‌ Nicolas Turro, Christian‌​‌ Laugier.

CHROMA coord.​​ : Lukas Rummelhard.

CHROMA​​​‌ participates in a project‌ supported by PIA in‌​‌ the scope of the​​ program PULSE of IRT​​​‌ Nanoelec. The objective of‌ this project is to‌​‌ integrate, develop and promote​​ technological bricks of context​​​‌ capture, for the safety‌ of the autonomous vehicle.‌​‌ Building on Embedded Bayesian​​ Perception for Dynamic Environment​​​‌, Bayesian data fusion‌ and filtering technologies from‌​‌ sets of heterogeneous sensors.​​ These software bricks make​​​‌ it possible to secure‌ the movements of vehicles,‌​‌ but also provide them​​​‌ with an enriched and​ useful representation for autonomy​‌ functions themselves. In this​​ context, various demonstrators embedding​​​‌ those technology bricks are​ developed in cooperation with​‌ industrial partners. Current work​​ is mainly focused on​​​‌ adding new sensor modalities​ (radar, ultrasound) in the​‌ perception system, GPU optimization,​​ and integration of Neural-Network-based​​​‌ systems into these probabilistic​ frameworks.

9.2.1 Start-up​​ maturation : Yona-Robotics (2024-2025)​​​‌

Participants: Lukas Rummelhard,​ Christian Laugier.

CHROMA​‌ coord. : Lukas Rummelhard.​​

In order to address​​​‌ the emerging markets for​ mobile robotics, in particular​‌ in industrial contexts (industrial​​ robotics, handling, logistics, agricultural​​​‌ robotics, inspection robots, service​ robots, etc.), a technology​‌ maturation project on the​​ Embedded Bayesian Perception and​​​‌ Navigation systems of the​ team (CMCDOT framework) have​‌ started this year. Thanks​​ to the support of​​​‌ the SATT LINKSIUM GRENOBLE​ ALPES, the start-up Yona-Robotics​‌ was created. See Yona-Robotics​​.

10.1.1 Inria associate team​‌ not involved in an​​ IIL or an international​​​‌ program

Associated Team with​ Univ. Sherbrooke, Canada, 3IT​‌ Institute, IntroLab team,​​ called “ROBLOC" (Robot Localization​​​‌ and Navigation Team), 2024-2026​ (12 K€/year).

• The coordinators​‌ are Olivier Simonin (CHROMA)​​ and François Michaud (U.​​​‌ Sherbrooke / 3IT).
• The​ two teams share common​‌ topics as mapping unknown​​ environments, UAVs (drones) localization​​​‌ and navigation, and human-robot​ interaction. The proposed associate​‌ team aims to explore​​ these subjects to build​​​‌ new research paths by​ sharing respective approaches and​‌ tools. More precisely, the​​ collaboration concerns: 1) UAV​​​‌ fleet navigation, 2) mapping​ for social navigation, 3)​‌ multi-robot path-planning: exploration of​​ underground environments. We are​​​‌ co-supervising several master's students​ and we are preparing​‌ new collaborative projects.

10.2.1​​​‌ Visits of international scientists​

10.2.2​ Visits to international teams​‌

10.3.1​‌ ANR

10.3.2​​​‌ PEPR

10.3.3 INRIA/AID AI​​​‌ projects

11.1.1 Scientific events:​​​‌ organisation

11.1.2 Scientific‌​‌ events: selection

11.1.3​​​‌ Journal

11.1.4 Invited talks

• Olivier​​ Simonin, "Des techniques d'interaction​​​‌ aux stratégies collectives dans​ les essaims de robots",​‌ Sherbrooke University, Canada, July​​ 2025.
• Baudouin Saintyves, "Granulobots:​​​‌ A Self-Coordinating Robotic Aggregate​ using Tunable Material-Like Responses",​‌ Sherbrooke University, Canada, June​​ 2025.

11.1.5 Leadership within​​​‌ the scientific community

• Olivier​ Simonin has been appointed​‌ as member of the​​ scientific board of the​​​‌ GDR Robotique (since 1/1/2025).​
• Olivier Simonin is member​‌ of the Executive Committee​​ of the PEPR O2R​​​‌ (Organic Robotics) 2023-2030 (​www.cnrs.fr/en/pepr/pepr-exploratoire-o2r-robotique).
• Christian Laugier​‌ is member of the​​ GDR Robotique "comité des​​​‌ sages".
• Christian Laugier is​ a founding member and​‌ co-chair of the IEEE​​ RAS Technical Committee on​​​‌ "Autonomous Ground Vehicles and​ Intelligent Transportation Systems".
• Anne​‌ Spalanzani co-animates the TS5​​ "Robotique centrée sur les​​​‌ données" theme for the​ GDR Robotique.
• Anne Spalanzani​‌ chaired the ANR CE33​​ Robotics and Interaction committee.​​​‌

11.1.6 Scientific expertise

• Anne​ Spalanzani is a jury​‌ member of the Georges​​ Giralt best European PhD​​​‌ in Robotic.
• Anne Spalanzani​ chaired the ANR CE33​‌ Robotics and Interaction committee​​ (2023-2025).
• Olivier Simonin is​​​‌ reviewer for the ERC​ european funding program (2025).​‌
• Olivier Simonin is reviewer​​ each year for ANR​​​‌ projects (Robotics and/or AI​ calls).

11.1.7 Research administration​‌

• Olivier Simonin was appointed​​ deputy director of the​​​‌ FIL (Federation Informatique de​ Lyon) at the end​‌ of 2025.
• Olivier Simonin​​ is member of the​​​‌ Inria Lyon COS (Comité​ d'orientation scientifique).
• Olivier Simonin​‌ as been appointed scientific​​ director of the robotics​​​‌ hall of the I-Factory​ (since Dec. 2025).

11.2.1 Supervision​

Phd in progress :​‌

• Mathis Fleuriel,"Exploration coopérative et​​ distribuée en intérieur par​​​‌ des flottes de drones​ avec des communications limitées",​‌ co-supervized by Olivier Simonin​​ (Chroma) and Elena Vanneaux​​​‌ (ENSTA Paris, U2IS), ANR​ "VORTEX" grant.
• Simon Ferrier,​‌ "Planification d'itinéraires multi-robots hétérogènes​​ pour des opérations culturales",​​​‌ co-supervized by Olivier Simonin​ and Alessandro Renzaglia, ANR​‌ NINSAR/PEPR "AgroEcol. & Numerique"​​ grant.
• Kaushik Bhowmik, "Modeling​​​‌ and prediction of pedestrian​ behavior on bikes, scooters​‌ or hoverboards", co-supervized by​​ A. Spalanzani (CHROMA) and​​​‌ P. Martinet (ACENTAURI, Sophia​ Antipolis).
• Benjamin Sportich, "Next-Best-View​‌ Planning for 3D Reconstruction​​ with Cooperative Multi-UAV Systems",​​​‌ co-supervized by A. Renzaglia,​ O. Simonin (ANR AVENUE).​‌
• Manuel Diaz Zapata, "AI-based​​ Framework for Scene Understanding​​​‌ and Situation Awareness for​ Autonomous Vehicles", co-supervized by​‌ C. Laugier, J. Dibangoye,​​ O. Simonin.
• Jean-Baptiste Horel,​​​‌ "Validation des composants de​ perception basés sur l’IA​‌ dans les véhicules autonomes",​​ co-supervized by R. Mateescu​​​‌ (Inria Convecs), A. Renzaglia,​ C. Laugier (funded by​‌ PRISSMA project).
• Gustavo Salazar​​ Gomez, "AI-driven safe motion​​ planning and driving decision-making​​​‌ for autonomous driving", co-supervized‌ by A. Spalanzani, C.‌​‌ Laugier.

Phd defended in​​ 2025 :

• Rabbia Asghar,​​​‌ "Real-time analysis of complex‌ traffic situations by Predicting/Characterizing‌​‌ Abnormal Behaviors and Dangerous​​ Situations", co supervissed by​​​‌ A. Spalanzani, C. Laugier,‌ L. Rummerhard. Defended on‌​‌ july 10 2025.
• Théotime​​ Balaguer, "Cooperative UAV Fleet​​​‌ based on Wireless Communication,‌ a Flocking Perspective", O.‌​‌ Simonin (INSA/Inria Chroma), I.​​ Guérin Lassous (Lyon1/LIP), I.​​​‌ Fantoni (CNRS/LS2N Nantes). Defended‌ in on November, 25th,‌​‌ 2025.

11.2.2 Juries

Anne​​ Spalanzani reported on the​​​‌ following PhD and HDR:‌

• Charlotte Beaune, Thèse de‌​‌ l'école centrale de Nantes,​​ Déc 2025.
• Adam Gouget,​​​‌ Thèse de l'Université de‌ Lille, Déc 2025 (President‌​‌ of the jury).
• Louis​​ Dambacher, Thèse de l'Université​​​‌ Clermont-Auvergne, Juillet 2025.
• Yunzhong‌ Zhou, Thèse de l'Université‌​‌ de Delft, Industrial Design​​ Engineering, Mars 2025.
• Kai​​​‌ Zhang, Thèse de l'Institut‌ Polytechnique de Paris, Mars‌​‌ 2025.

Anne Spalanzani examined​​ the following PhD

• Emmanuel​​​‌ Alao, Thèse de l'Université‌ de Technologie de Compiègne,‌​‌ décembre 2025.
• Emilie Leblong,​​ Thèse de l'Université de​​​‌ Rennes, Juillet 2025.

Olivier‌ Simonin reported on the‌​‌ following PhD:

• Ikrame Yazidi,​​ Thèse de l'Université Marie​​​‌ et Louis Pasteur, FEMTO,‌ Montbéliard, December 19, 2025.‌​‌
• Shan He, Thèse de​​ l'Université de Technologie de​​​‌ Compiègne, Decembre 16, 2025.‌
• Smail Ait Bouhsain, LAAS,‌​‌ INSA Toulouse, April 2025​​ (President of the jury).​​​‌
• Marc-Antoine Maheux, Univ. Sherbrooke,‌ Canada, March 25, 2025.‌​‌

Olivier Simonin examined the​​ following PhD

• Antonio Marino,​​​‌ Université de Rennes, December‌ 4, 2025 (President of‌​‌ the Jury).
• Maxime Bernard,​​ Université de Rennes, Apris​​​‌ 30, 2025.

11.2.3 Educational‌ and pedagogical activities

Multidisciplinary‌​‌ Teaching:

• The Physics of​​ Shapes, from Nature to​​​‌ the Hand: Baudouin Saintyves,‌ art and science, 36h,‌​‌ School of the Art​​ Institute of Chicago, USA.​​​‌

Teaching in Masters:

• Olivier‌ Simonin is in charge‌​‌ of the Robotics topic​​ in the new international​​​‌ Master of AI "MINDS",‌ at INSA Lyon, since‌​‌ Sept. 2025. He teaches​​ a 16-hour course on​​​‌ introduction to robotics., and‌ a 16-hour course on‌​‌ multi-robot cooperation in M2.​​ Alessandro Renzaglia is also​​​‌ teaching 4-hour in M1,‌ on multi-robot coverage and‌​‌ exploration.
• Alessandro Renzaglia is​​ teaching, each year, at​​​‌ INPG Ense3 Grenoble, Master‌ MARS: AI and Autonomous‌​‌ Systems, 12h.
• Anne Spalanzani​​ is teaching, each year,​​​‌ at INPG Ense3 Grenoble,‌ Master MARS: Autonomous Robot‌​‌ Navigation 6h.
• M2R MoSIG:​​ A. Martinelli, Autonomous Robotics,​​​‌ 12h, ENSIMAG

Olivier Simonin's‌ teachings at INSA Lyon‌​‌ (engineering school), each year:​​

• INSA Lyon 5th year​​​‌ - Robotics option (20‌ students): AI for Robotics‌​‌ (plannning, RL, bio-inspiration), Multi-Robot​​ Systems, Robotics Projects, 80h,​​​‌ Resp., Telecom Dept.
• INSA‌ Lyon 4th year :‌​‌ Artificial Intelligence (Intro AI,​​ Metaheuristics), 10h (90 students),​​​‌ Telecom Dept.
• INSA Lyon‌ 3rd year : Algorithmics,‌​‌ 50h (90 students), L3,​​ Resp., Telecom Dept.

Alessandro​​​‌ Renzaglia's teachings at INSA‌ Lyon:

• INSA Lyon 5th‌​‌ year / Master -​​ Robotics option: Multi-Robot Systems,​​​‌ 4h, Telecom Dept.
• INSA‌ Lyon 3rd year /‌​‌ Lic.: supervision of research​​ initiation projects (groups of​​​‌ 5 students) along one‌ semester, 15h, Telecom Dept.‌​‌

Jacques Saraydaryan's teachings at​​​‌ the CPE Lyon (engineering​ school), SN Dept.:

• CPE​‌ Lyon 5th year :​​ Autonomous Robot Navigation 32h,​​​‌ Particle Filter 12h.
• CPE​ Lyon 4-5th year :​‌ Software Architecture, 156h.
• CPE​​ Lyon 4-5th year :​​​‌ Introduction to Cyber Security,​ 25h.
• CPE Lyon 4-5th​‌ year : Software development​​ and big data projects​​​‌ (supervision), 88h.
• CPE Lyon​ 4-5th year : Software​‌ Design and Big Data,​​ Resp.

Fabrice Jumel's teachings​​​‌ at the CPE Lyon​ (engineering school), SN Dept.,​‌ each year:

• CPE Lyon​​ 4-5th year : Robotic​​​‌ vision, cognitive science, HRI,​ deep learning, robotic platforms,​‌ Kalman Filter, 250h /​​ 288h.

11.3.1​​​‌ Specific official responsibilities in​ science outreach structures

• Shapes​‌ of emergence, Founder​​ and co-director of art​​​‌ and science performance project​ Shapes of Emergence (With​‌ Severine Atis, CNRS).

11.3.2​​ Productions (articles, videos, podcasts,​​​‌ serious games, ...)

• Society​ for Art and Technology​‌ (SAT), Dome movie​​ Water Organoids, distributed in​​​‌ Dome theter by SAT.​ As part of the​‌ 2025 dome residency program.​​ Montreal, Canada. (Last projection:​​​‌ between Nov 8 and​ Dec 12, 2025).​‌

11.3.3 Participation in Live​​ events

• « Fête de​​​‌ la science », CITI​ Lab. Chroma, INSA &​‌ Inria Lyon, O. Simonin,​​ T. Balaguer (Phd student),​​​‌ H. Diallo, N. Valle.​ Swarm of UAVs demos.​‌
• “Pint of Sciences” O.​​ Simonin & F. Jumel,​​​‌ "L'aube des robots sociaux​ : entre espoirs et​‌ défis", May 20, Lyon,​​ Repère(s).
• Pop'Sciences, N. Valle​​​‌ "Danse avec les drones",​ Belleville-en-Beaujolais festival popsciences universite-lyon​‌
• Society for Art and​​ Technology, World premier​​​‌ immersive performance venue and​ research center, with dome​‌ and 3d sound facility.​​ As part of the​​​‌ 2025 dome residency program.​ Montreal, Canada. (Oct. 14,​‌ 15, 16, 17, 18,​​ 2025).
• Lafayette Electronic​​​‌ Arts Festival, Performance​ “Water Organoids", Lafayette, Colorado,​‌ USA. (May 30, 2025)​​.

11.3.4 Others science​​​‌ outreach relevant activities

• «​ Inauguration of the I-Factory​‌ - Robotics demos »,​​ A. Betaille, D. Rambeau,​​​‌ N. Valle, O. Simonin,​ Demos of an autonomous​‌ Crazyflie UAV fleet flight​​ and presentation of the​​​‌ semi-humanoid Mirokaï (one day,​ November 13, 2025, open​‌ to all)

International journals

• 11‌ articleD.David Brown‌​‌, J.Jacques Saraydaryan​​, B.Benoit Renault​​​‌ and O.Olivier Simonin‌. NAMOSIM: a Robot‌​‌ Motion Planner for Navigation​​ Among Movable Obstacles.​​​‌Journal of Open Source‌ Software10113September‌​‌ 2025, 8816HAL​​DOIback to text​​​‌back to text
• 12‌ articleI.Iñaki Echeverría-Huarte‌​‌, A.Antonin Roge​​, O.Olivier Simonin​​​‌ and A.Alexandre Nicolas‌. Near-future projections in‌​‌ continuous agent-based models for​​ crowd dynamics: mathematical structures​​​‌ in use and their‌ implications.Journal of‌​‌ Statistical Mechanics: Theory and​​ ExperimentMarch 2025,​​​‌ 033403HALDOI
• 13‌ articleA.Agostino Martinelli‌​‌. Local identifiability of​​ nonlinear ODE models with​​​‌ time-varying parameters: The general‌ algebraic condition.IEEE‌​‌ Transactions on Automatic Control​​October 2025, 1-16​​​‌HALDOIback to‌ text
• 14 articleX.‌​‌Xiao Peng, F.​​François Schwarzentruber, O.​​​‌Olivier Simonin and C.‌Christine Solnon. Spanning-tree‌​‌ based coverage for a​​ tethered robot.IEEE​​​‌ Robotics and Automation Letters‌January 2025, 1-8‌​‌In press. HAL

International​​ peer-reviewed conferences

• 15 inproceedings​​​‌T.Théotime Balaguer,‌ O.Olivier Simonin,‌​‌ I.Isabelle Guérin-Lassous and​​​‌ I.Isabelle Fantoni.​ DANCERS: A Physics and​‌ Network Co-Simulator for Communicating​​ Multi-Robot Systems.SIMPAR​​​‌ 2025 - IEEE International​ Conference on Simulation, Modeling,​‌ and Programming for Autonomous​​ RobotsPalermo, ItalyIEEE​​​‌2025, 1-6HAL​back to textback​‌ to textback to​​ textback to text​​​‌
• 16 inproceedingsT.Théotime​ Balaguer, O.Olivier​‌ Simonin, I.Isabelle​​ Guérin-Lassous and I.Isabelle​​​‌ Fantoni. UAV Chain​ Network Creation in Cluttered​‌ Environment with Flocking Rules​​ and Routing Data.​​​‌IROS 2025 - IEEE/RSJ​ International Conference on Intelligent​‌ Robots and Systems (IROS)​​Hangzhou, China2025HAL​​​‌back to textback​ to textback to​‌ text
• 17 inproceedingsG.​​Guillermo Benito-Calvino, A.​​​‌Ahmed Boubrima, H.​Hervé Rivano, A.​‌Alessandro Renzaglia and Z.​​Zhambyl Shaikhanov. Poster:​​​‌ Joint RF-Gas Sensing for​ Victim Localization using UAV​‌ Networks.Mobisys25 -​​ 23rd ACM International Conference​​​‌ on Mobile Systems, Applications,​ and ServicesAnaheim, United​‌ States2025, 1-3​​HALDOI
• 18 inproceedings​​​‌K.Kaushik Bhowmik,​ A.Anne Spalanzani and​‌ P.Philippe Martinet.​​ CG-Net: Urban Trajectory Forecasting​​​‌ with Bipartite Graphs for​ Agents, Scene Context and​‌ Candidate Centerlines.IROS​​ 2025 - IEEE/RSJ International​​​‌ Conference on Intelligent Robots​ and SystemsHangzhou, China​‌2025, 1-7HAL​​back to textback​​​‌ to text
• 19 inproceedings​M.Mathis Fleuriel,​‌ E.Elena Vanneaux,​​ D.David Filliat and​​​‌ O.Olivier Simonin.​ Exploring Underground Environments by​‌ Deploying and Reconfiguring a​​ Chain of Visually Connected​​​‌ UAVs.ECMR 2025​ - European Conference on​‌ Mobile RobotsPadoue, Italy​​2025, 1-7HAL​​​‌back to text
• 20​ inproceedingsJ.-B.Jean-Baptiste Horel​‌, P.Philippe Ledent​​, R.Radu Mateescu​​​‌, W.Wendelin Serwe​ and A.Aline Uwimbabazi​‌. Assessing Test Scenarios​​ for Autonomous Driving Using​​​‌ Probabilistic Model Checking.​Lecture Notes in Computer​‌ ScienceICTSS 2025 -​​ 37th IFIP WG 6.1​​​‌ International Conference on Testing​ Software and Systems16107​‌Lecture Notes in Computer​​ ScienceLimassol, CyprusSpringer​​​‌ Nature SwitzerlandSeptember 2026​, 273-289HALDOI​‌
• 21 inproceedingsB.Benjamin​​ Sportich, A.Alessandro​​​‌ Renzaglia and S.Sara​ Bernardini. Energy-based Adaptive​‌ Coverage Path Planning with​​ Multiple Robots.International​​​‌ conference on Intelligent Autonomous​ SystemsIAS 2025 -​‌ 19th International conference on​​ Intelligent Autonomous SystemsGenova,​​​‌ Italy2025, 1-15​HAL

National peer-reviewed Conferences​‌

• 22 inproceedingsM.Mathis​​ Fleuriel, E.Elena​​​‌ Vanneaux, D.David​ Filliat and O.Olivier​‌ Simonin. Exploration d'environnements​​ souterrains par déploiement et​​​‌ réorganisation d'une chaîne de​ drones.JFSMA 2025​‌ - Journées Francophones des​​ Système Multi-AgentsDijon, France​​​‌July 2025HAL
• 23​ inproceedingsC.Chanattan Sok​‌ and O.Olivier Simonin​​. Simulation et résolution​​​‌ de conflits spatiaux entre​ piétons fondée sur la​‌ théorie du choix social​​.JFSMADijon, France​​​‌CépaduèsJune 2025HAL​
• 24 inproceedingsS.Stéphane​‌ d'Alu, H.Hervé​​ Rivano and O.Olivier​​​‌ Simonin. Estimation de​ distances distribuée FTM-BC par​‌ UWB sur systèmes embarqués​​.CORES 2025 -​​ 10èmes Rencontres Francophones sur​​​‌ la Conception de Protocoles,‌ l'Evaluation de Performances et‌​‌ l'Expérimentation des Réseaux de​​ CommunicationCORES 2025 -​​​‌ 10èmes Rencontres Francophones sur‌ la Conception de Protocoles,‌​‌ l'Evaluation de Performances et​​ l'Expérimentation des Réseaux de​​​‌ CommunicationSaint Valery-sur-Somme, France‌2025, 1-4HAL‌​‌

Doctoral dissertations and habilitation​​ theses

• 25 thesisR.​​​‌Rabbia Asghar. Uncertainty-Aware‌ Motion Prediction with Dynamic‌​‌ Occupancy Grid Maps.​​Inria Grenoble Rhône-Alpes, Université​​​‌ de GrenobleJuly 2025‌HALback to text‌​‌
• 26 thesisT.Théotime​​ Balaguer. Cooperative UAV​​​‌ Fleet based on Wireless‌ Communication, a Flocking Perspective‌​‌.INSA Lyon -​​ Ecole doctorale d’Informatique et​​​‌ Mathématique de LyonNovember‌ 2025HALback to‌​‌ textback to text​​back to text

Reports​​​‌ & preprints

• 27 misc‌B.Benjamin Sportich,‌​‌ K.Kenza Boubakri,​​ O.Olivier Simonin and​​​‌ A.Alessandro Renzaglia.‌ Quality-guided UAV Surface Exploration‌​‌ for 3D Reconstruction.​​2025HALback to​​​‌ text