Publications

Miscellaneous

2022

HDDL 2.1: Towards Defining an HTN Formalism with Time

Pellier, D., Fiorino, H., Grand, M., Albore, A., and Bailon-Ruiz, R.

2022

[Abs] [PDF] [URL] [DOI]

Real world applications of planning, like in industry and robotics, require modelling rich and diverse scenarios. Their resolution usually requires coordinated and concurrent action executions. In several cases, such planning problems are naturally decomposed in a hierarchical way and expressed by a Hierarchical Task Network (HTN) formalism. The PDDL language used to specify planning domains has evolved to cover the different planning paradigms. However, formulating real and complex scenarios where numerical and temporal constraints concur in defining a solution is still a challenge. Our proposition aims at filling the gap between existing planning languages and operational needs. To do so, we propose to extend HDDL taking inspiration from PDDL 2.1 and ANML to express temporal and numerical expressions. This paper opens discussions on the semantics and the syntax needed to extend HDDL, and illustrate these needs with the modelling of an Earth Observing Satellite planning problem.

Journal Articles

2022

Real-time wildfire monitoring with a fleet of UAVs

Bailon-Ruiz, Rafael, Bit-Monnot, Arthur, and Lacroix, Simon

Robotics and Autonomous Systems, vol. 152, pp. 104071, Jun, 2022

[Abs] [PDF] [URL] [DOI]

This paper introduces a wildfire monitoring system based on a fleet of Unmanned Aerial Vehicles (UAVs) to provide firefighters with precise and up-to-date information about a propagating wildfire, so that they can devise efficient suppression actions. We present an approach to plan trajectories for a fleet of fixed-wing UAVs to observe a wildfire evolving over time by tailoring the Variable Neighborhood Search metaheuristic to the problem characteristics. Realistic models of the terrain, of the fire propagation process, and of the UAVs are exploited, together with a model of the wind, to predict wildfire spread and plan accordingly the UAVs motions. Algorithms and models are integrated within a software architecture allowing tests with real and simulated UAVs flying over synthetic wildfires. Results of a mixed-reality test campaign show the ability of the proposed system to effectively map wildfire propagation.

Conference Articles

2022

A Hierarchical Deliberative Architecture Framework based on Goal Decomposition

Lesire, Charles, Bailon-Ruiz, Rafael, Barbier, Magali, and Grand, Christophe

In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. , pp. 9865-9870, Oct, 2022

[Abs] [PDF] [DOI]

Performing a complex autonomous mission with a multi-robot system requires to integrate several deliberative approaches to perform task allocation, optimization, and execution control. Implementing such a deliberative architecture is a complex task: it requires the developer to master the decision algorithms themselves (e.g., automated planning models), to have a good knowledge of the involved robotic platforms, and to think about how these elements will be assembled as a system architecture. We propose a framework to help designing such deliberative architectures. The framework relies on the concept of a hierarchical structure of actors, each actor managing goals with specific planning or optimization approaches, and delegating sub-goals to other actors.

2020

Wildfire remote sensing with UAVs: A review from the autonomy point of view

Bailon-Ruiz, Rafael, and Lacroix, Simon

In 2020 International Conference on Unmanned Aircraft Systems (ICUAS), vol. , pp. 412-420, Sep, 2020

[Abs] [PDF] [DOI]

This article analyses the state of the art on wildfire remote sensing using UAVs, an application context that has now gained significant interest. It reviews a selection of relevant publications, and proposes a classification scheme to synthesize them from an autonomy perspective. Three metrics are introduced: situation awareness, decisional ability, and collaboration ability. A discussion about the current state and the outlook of UAV systems for wildfire observation concludes the paper.

2018

A Local Search Approach to Observation Planning with Multiple UAVs

Bit-Monnot, Arthur, Bailon-Ruiz, Rafael, and Lacroix, Simon

In International Conference on Automated Planning and Scheduling (ICAPS), pp. 9p., Jun, 2018

[Abs] [PDF] [URL]

Observation planning for Unmanned Aerial Vehicles (UAVs) is a challenging task as it requires planning trajectories over a large continuous space and with motion models that can not be directly encoded into current planners. Furthermore, realistic problems often require complex objective functions that complicate problem decomposition. In this paper, we propose a local search approach to plan the trajectories of a fleet of UAVs on an observation mission. The strength of the approach lies in its loose coupling with domain specific requirements such as the UAV model or the objective function that are both used as black boxes. Furthermore, the Variable Neighborhood Search (VNS) procedure considered facilitates the adaptation of the algorithm to specific requirements through the addition of new neighborhoods. We demonstrate the feasibility and convenience of the method on a large joint observation task in which a fleet of fixed-wing UAVs maps wildfires over areas of a hundred square kilometers. The approach allows generating plans over tens of minutes for a handful of UAVs in matter of seconds, even when considering very short primitive maneuvers.
Planning to Monitor Wildfires with a Fleet of UAVs

Bailon-Ruiz, Rafael, Lacroix, Simon, and Bit-Monnot, Arthur

In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. , pp. 4729-4734, Oct, 2018

[Abs] [PDF] [URL] [DOI]

We present an approach to plan trajectories for a fleet of fixed-wing UAVs to observe a wildfire evolving over time. Realistic models of the terrain, of the fire propagation process, and of the UAVs are exploited, together with a model of the wind. The approach tailors a generic Variable Neighborhood Search method to these models and associated constraints. Simulation results show ability to plan observation trajectories for a small fleet of UAVs, and to update the plans when new information on the fire are incorporated in the fire model.
FIRE-RS: Integrating land sensors, cubesat communications, unmanned aerial vehicles and a situation assessment software for wildland fire characterization and mapping

Pérez-Lissi, Franco, Aguado-Agelet, Fernando, Vázquez, Antón, Yañez, Pablo, Izquierdo, Pablo, Lacroix, Simon, Bailon-Ruiz, Rafael, Tasso, Joao, Guerra, Andre, and Costa, Maria

In 69th International Astronautical Congress, Oct, 2018

[Abs] [PDF] [URL]

The Wildland Fire Remote Sensing (FIRE-RS) project, developed within the European Interreg SUDOE Programme, implements an innovative system for prevention, detection and mapping of natural disasters, centred on wildland fires. This objective is achieved through the synergy of four technologies: forest based infrared land sensors for fire in-situ detection, CubeSat spacecraft for early warnings and communications coverage, UAVs for high-accuracy fire mapping and real time data acquisition, and a situation assessment tool for performing efficient risk assessments and coordination strategies, both during and after the wildland fire emergency. The infrared land sensors are responsible for the early detection and initial analysis of the extension and location of the fire spots. These devices will generate alert messages to be broadcasted to the microsatellite and to the UAVs. The spacecraft (LUME-1) will receive the alert message, and will relay it to the ground facilities, using the on-board SDR communications payload. The Payload Operations Centre is in charge of the live distribution of the alert messages to the Data Distribution and Control Centre, whose main goal is to implement actuation protocols based on the alert messages received from the satellite. It will forward the specific actuation guidelines to the UAVs Control Centres located within the specific emergency zone, where the alert message was originated. The UAVs will fly over the emergency area to perform a more detailed mapping and characterization of the zone. They will use on-board optic payloads, wind sensors and a SDR communication system to gather detailed data. The data will be integrated within a Situation Assessment software suite, providing centralized access to relevant information for the emergency departments to apply decision-making protocols.

2017

System simulation of a fleet of drones to probe cumulus clouds

Bailon-Ruiz, Rafael, Reymann, Christophe, Lacroix, Simon, Hattenberger, Gautier, Marina, Hector, and Lamraoui, Fayçal

In International Conference on Unmanned Aircraft Systems (ICUAS), pp. 8p., Jun, 2017

[Abs] [PDF] [URL] [DOI]

Simulation plays an essential role in the development of complex systems. This paper reports on the development of a simulation infrastructure for a fleet of UAVs conceived to probe clouds, using an adaptive sampling scheme that calls for cloud mapping and trajectory planning. The mission is presented, the global approach to solve it and the ensemble of required processes are sketched. An overall simulation architecture is then depicted, and the details of its development using the Robot Operating System (ROS) are presented.

Theses

2020

Design of a wildfire monitoring system using fleets of Unmanned Aerial Vehicles

Bailon-Ruiz, Rafael

PhD thesis, INSA de Toulouse, Sep, 2020

[Abs] [PDF] [URL]

Wildfires, also known as forest or wildland fires, are uncontrolled vegetation fires occurring in rural areas that cause tremendous damage to the society, harming environment, property and people. The firefighting endeavor is a dull, dirty and dangerous job and as such, can greatly benefit from automation to reduce human exposure to hazards. Aerial remote sensing is a common technique to obtain precise information about a wildfire state so fire response teams can prepare countermeasures. This task, when performed with manned aerial vehicles, expose operators to high risks that can be eliminated by the use of autonomous vehicles. This thesis introduces a wildfire monitoring system based on fleets of unmanned aerial vehicles (UAVs) to provide firefighters with timely updated information about a wildland fire. We present an approach to plan trajectories for a fleet of fixed-wing UAVs to observe a wildfire evolving over time. Realistic models of the terrain, of the fire propagation process, and of the UAVs are exploited, together with a model of the wind, to predict wildfire spread and plan UAV motion. The approach tailors a generic Variable Neighborhood Search method to these models and the associated constraints. The execution of the planned monitoring mission provides wildfire maps that are transmitted to the fire response team and exploited by the planning algorithm to plan new observation trajectories. Algorithms and models are integrated within a software architecture allowing for execution under scenarios with different levels of realism, with real and simulated UAVs flying over a real or synthetic wildfire. Mixed-reality simulation results show the ability to plan observation trajectories for a small fleet of UAVs, and to update the plans when new information on the fire are incorporated in the fire model.

2016

Deployment of a simulation software architecture for a fleet of UAVs

Bailon-Ruiz, Rafael

Master's thesis, Université Grenoble-Alpes, Jun, 2016

[Abs] [PDF]

SkyScanner is a project whose mission is to guide a fleet of Unmanned Aerial Vehicles (UAVs) to actively gather data in low-altitude cumulus clouds with the aim of mapping atmospheric variables. This report presents the work done for the SkyScanner project at LAAS-CNRS to design and implement a simulation software architecture for a fleet of UAVs. The new software package, based on the Robot Operating System (ROS) framework, integrates the in-house mapping and path planning algorithms with realistic simulators: Paparazzi open-source autopilot, FlightGear flight simulator and MesoNH atmospheric model. Then, the whole simulation loop is tested in order to identify potential weaknesess. Finally, some guidance and navigation enhancements are proposed in order to improve system performance.