Navigation of autonomous Unmanned Aerial Vehicles (UAVs) in unknown, obstacle-cluttered environments requires motion planning under limited sensing and strict safety constraints. Although learning-based navigation approaches have demonstrated promising performance, many rely on purely reactive obstacle avoidance or indirect reward shaping (e.g., end-to-end learning or deep-learning based sensor encoding), without explicitly incorporating predictive collision information into the learning process. This work introduces a conceptual framework for learning collision-aware UAV navigation over a predicted motion horizon.
Zallaghi, MJ, Convens, B, Merckaert, K, Munteanu, A & Vanderborght, B 2026, Learning UAV Navigation with Collision-Aware Predicted-Motion Embedding. in G Bianchin, M Cao, R Sepulchre, B De Schutter, D Dochain, J Goncalves, M Heemels, J Hendrickx, B Jayawardhana, R Jungers, K Keesman, M Kinnaert, H Nijmeijer, T Oomen, H Stigter, S Weiland, J Winkin, N van de Wouw & H J. Zwart (eds), 45th Benelux Meeting on Systems and Control., TueA11-3, 45th Benelux Meeting on Systems and Control, pp. 79-79, 45th Benelux Meeting on Systems and Control, Lommel, Belgium, 24/03/26. <https://beneluxmeeting.be/2026/uploads/boa2026.pdf>
Zallaghi, M. J., Convens, B., Merckaert, K., Munteanu, A., & Vanderborght, B. (2026). Learning UAV Navigation with Collision-Aware Predicted-Motion Embedding. In G. Bianchin, M. Cao, R. Sepulchre, B. De Schutter, D. Dochain, J. Goncalves, M. Heemels, J. Hendrickx, B. Jayawardhana, R. Jungers, K. Keesman, M. Kinnaert, H. Nijmeijer, T. Oomen, H. Stigter, S. Weiland, J. Winkin, N. van de Wouw, & H. J. Zwart (Eds.), 45th Benelux Meeting on Systems and Control (pp. 79-79). Article TueA11-3 45th Benelux Meeting on Systems and Control. https://beneluxmeeting.be/2026/uploads/boa2026.pdf
@inbook{85c24f80a3ed4aee9bee0369c1292f29,
title = "Learning UAV Navigation with Collision-Aware Predicted-Motion Embedding",
abstract = "Navigation of autonomous Unmanned Aerial Vehicles (UAVs) in unknown, obstacle-cluttered environments requires motion planning under limited sensing and strict safety constraints. Although learning-based navigation approaches have demonstrated promising performance, many rely on purely reactive obstacle avoidance or indirect reward shaping (e.g., end-to-end learning or deep-learning based sensor encoding), without explicitly incorporating predictive collision information into the learning process. This work introduces a conceptual framework for learning collision-aware UAV navigation over a predicted motion horizon.",
keywords = "Learning-based Planning and Control, Autonomous UAV Navigation",
author = "Zallaghi, \{Mohammad Javad\} and Bryan Convens and Kelly Merckaert and Adrian Munteanu and Bram Vanderborght",
year = "2026",
month = mar,
day = "24",
language = "English",
pages = "79--79",
editor = "Gianluca Bianchin and Ming Cao and Rodolphe Sepulchre and \{De Schutter\}, Bart and Dennis Dochain and Jorge Goncalves and Maurice Heemels and Julien Hendrickx and Bayu Jayawardhana and Rapha{\"e}l Jungers and Karel Keesman and Michel Kinnaert and Henk Nijmeijer and Tom Oomen and Hans Stigter and Siep Weiland and Joseph Winkin and \{van de Wouw\}, Nathan and \{J. Zwart\}, Hans",
booktitle = "45th Benelux Meeting on Systems and Control",
publisher = "45th Benelux Meeting on Systems and Control",
note = "45th Benelux Meeting on Systems and Control ; Conference date: 24-03-2026 Through 26-03-2026",
url = "https://www.beneluxmeeting.nl/2026/",
}