SEMFIRE (Safety, Exploration and Maintenance of Forests with the Integration of Ecological Robotics) proposes the development of a support robotic system to reduce fuel accumulation (e.g., forest debris), thus assisting in landscaping maintenance tasks. This is an application domain with an unquestionable beneficial impact at the economic, social and environmental level, as the proposed project will contribute by significantly reducing wildfire hazard potential.

SEMFIRE addresses several disciplines to succeed in fire prevention by benefiting from disruptive technologies and novel ecological robotic approaches. Focus will be placed in the development of a multi-robot system, combined with pervasive local positioning, multi-robot navigation and coordination in forests, and an innovative artificial perception architecture.

SEMFIRE is a project of the Central Portugal Region cofunded by the program Portugal 2020, under the reference

CENTRO-01-0247-FEDER-032691

Europe has been affected by an alarming number of wildfires every year, ravaging nearly half a million hectares of forestry areas and resulting in an unacceptable amount of human losses. The year 2017 was one of the worst ever recorded, with devastating wildfires raging across the globe. Bearing these shocking facts in mind, this position paper aims to lay the foundations of crucial new upcoming research in the field of forestry robotics by presenting an overview of the SEMFIRE project. SEMFIRE proposes the development of a robotic system designed to reduce the accumulation of combustible material in forests, thus assisting in landscaping maintenance tasks for wildfire prevention. This paper describes the multi-robot system envisaged by SEMFIRE, combined with pervasive local positioning, multi-robot navigation and coordination in forests, and an innovative artificial perception architecture.

Couceiro, M. S., Portugal, D., Ferreira, J. F., & Rocha, R. P. SEMFIRE: towards a new generation of forestry maintenance multi-robot systems, in 2019 IEEE. In SICE International Symposium on System Integration (SII)(IEEE, Paris, 2019) (pp. 270-276).

Martins, G. S., Ferreira, J. F., Portugal, D., & Couceiro, M. S. (2019). MoDSeM: modular framework for distributed semantic mapping. Poster Papers, 12.

Martins, G. S., Ferreira, J. F., Portugal, D., & Couceiro, M. S. (2019, July). MoDSeM: towards semantic mapping with distributed robots. In Annual Conference Towards Autonomous Robotic Systems (pp. 131-142). Springer, Cham.

Portugal, D., Ferreira, J. F., & Couceiro, M. S. (2020, September). Requirements specification and integration architecture for perception in a cooperative team of forestry robots. In Annual Conference Towards Autonomous Robotic Systems (pp. 329-344). Springer, Cham.

Nasir, A. K., Araújo, A. G., & Couceiro, M. S. (2020, October). Localization and navigation assessment of a heavy-duty field robot. In Proceedings of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020), Workshop on Perception, Planning and Mobility in Forestry Robotics (WPPMFR 2020) (pp. 25-29).

Andrada, M. E., De Castro Cardoso Ferreira, J., Portugal, D., & Couceiro, M. (2020). Testing different CNN architectures for semantic segmentation for landscaping with forestry robotics.

Lourenço, D., De Castro Cardoso Ferreira, J., & Portugal, D. (2020). 3D local planning for a forestry UGV based on terrain gradient and mechanical effort.

Portugal, D., Andrada, M. E., Araújo, A. G., Couceiro, M. S., & Ferreira, J. F. (2021). Ros integration of an instrumented bobcat t190 for the semfire project. In Robot Operating System (ROS) (pp. 87-119). Springer, Cham.

Andrada, M. E., Ferreira, J. F., Portugal, D., & Couceiro, M. S. (2022, January). Integration of an Artificial Perception System for Identification of Live Flammable Material in Forestry Robotics. In 2022 IEEE/SICE International Symposium on System Integration (SII) (pp. 103-108). IEEE.

Karfakis, P. T., Couceiro, M. S., Portugal, D., & Antunes, C. H. (2022, March). A Comparative Study of Mobile Robot Positioning Using 5G NR. In ICRA 2022 Workshop in Innovation in Forestry Robotics: Research and Industry Adoption.

Bittner, D., Ferreira, J. F., Andrada, M. E., Bird, J. J., & Portugal, D. (2022, March). Generating Synthetic Multispectral Images for Semantic Segmentation in Forestry Applications. In ICRA 2022 Workshop in Innovation in Forestry Robotics: Research and Industry Adoption.

Andrada, M. E., Ferreira, J. F., Kantor, G., Portugal, D., & Antunes, C. H. (2022, March). Model Pruning in Depth Completion CNNs for Forestry Robotics with Simulated Annealing. In ICRA 2022 Workshop in Innovation in Forestry Robotics: Research and Industry Adoption.

Invited Talks:

Ferreira, J. F. (2019). “Forestry 4.0” – Going Beyond Smart Agriculture. Invited Talk. Smart Industry Workshop, Nottingham Trent University, United Kingdom.

Requirements of System and Scenarios of Use

Functional and Technical Specification

Artificial Perception System and Robotic Decision-Making – Artificial Perception Base System

Multi-Robot Exploration, Patrolling and Localization System

Initial Deployment of Scouts under Connectivity Constraints

Plan of dissemination and disclosure enlarged from results

Contents multimedia for disclosure of prototype

Contents multimedia for disclosure of prototype