A Battery Model for Learning Energy Optimized Flight Paths in UAV Simulation*

Gründer A, Bayer J, Kalenberg M, Benz J, Becker S, Franke J, Reitelshöfer S (2025)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2025

Publisher: Institute of Electrical and Electronics Engineers Inc.

Conference Proceedings Title: 2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings

Event location: Padua, ITA

ISBN: 9798331527051

DOI: 10.1109/ECMR65884.2025.11163369

Abstract

In the field of robotics, recent improvements of simulators have significantly narrowed the sim-to-real gap, enabling effective pre-training of agents in simulation environments. Especially Reinforcement Learning (RL) approaches now facilitate not only common tasks - such as robotic navigation in simulation - but also exhibit superior real-world performance compared to conventional methods. However, the optimization of less apparent components, such as energy consumption in Unmanned Aerial Vehicles (UAVs), remains largely unexplored. Existing simulators do not model the energy consumption of robots accurately. This limits the capability of including energy-efficient behavior in simulation-based RL training. However, especially for UAVs, more specific for Drones, including the battery state and energy consumptiong for energy-efficient behavior and flight maneuvers is important for increasing the maximum flight time.In this paper, we introduce a method for modeling the energy consumption of a hexacopter. Our approach is integrated with the open-source simulator Gazebo and the PX4-Autopilot, providing a robust foundation for training RL agents that consider energy optimization.

Authors with CRIS profile

How to cite

APA:

Gründer, A., Bayer, J., Kalenberg, M., Benz, J., Becker, S., Franke, J., & Reitelshöfer, S. (2025). A Battery Model for Learning Energy Optimized Flight Paths in UAV Simulation*. In Antonios Gasteratos, Nicola Bellotto, Stefano Tortora (Eds.), 2025 European Conference on Mobile Robots, ECMR 2025 - Proceedings. Padua, ITA: Institute of Electrical and Electronics Engineers Inc..

MLA:

Gründer, Andreas, et al. "A Battery Model for Learning Energy Optimized Flight Paths in UAV Simulation*." Proceedings of the 12th European Conference on Mobile Robots, ECMR 2025, Padua, ITA Ed. Antonios Gasteratos, Nicola Bellotto, Stefano Tortora, Institute of Electrical and Electronics Engineers Inc., 2025.

BibTeX: Download