Modular Evolution of Artificial Potential Fields for Coordinated Aerial Navigation

https://doi.org/10.58571/CNCA.AMCA.2025.069

Resumen: Artificial Potential Fields (APFs) are commonly used to control multi-agent systems such as drone swarms, enabling behaviors like trajectory tracking, coordination, and collision avoidance. However, APFs are typically hand-crafted and require extensive tuning, limiting their adaptability. To address this, we propose an evolutionary strategy based on Genetic Programming (GP) to automatically synthesize vector-valued controllers that replace traditional APF components for attraction, synchronization, and repulsion. Controllers are evolved in a 3D quadrotor simulation with realistic dynamics and evaluated on position and velocity errors during coordinated trajectory tracking. Results show that the evolved controllers match or outperform classical APFs, enabling emergent coordination without manual design. This demonstrates the potential of evolutionary synthesis for scalable, adaptive multi-agent control.

¿Cómo citar?

Cetina-Denis, J., Cruz-Hernández, C., Chan-Ley, M., Arellano-Delgado, A. & Murillo-Escobar, M. (2025). Modular Evolution of Artificial Potential Fields for Coordinated Aerial Navigation. Memorias del Congreso Nacional de Control Automático 2025, pp. 403-408. https://doi.org/10.58571/CNCA.AMCA.2025.069

Palabras clave

Autonomous Mobile Robots, UAVs, Evolutionary Algorithms, Decentralized Control, Trajectory Tracking and Path Following.

• (2017). Linear vs nonlinear mpc for trajectory tracking applied to rotary wing micro aerial vehicles. IFAC-PapersOnLine, 50(1), 3463–3469. doi: https://doi.org/10.1016/j.ifacol.2017.08.849. 20th IFAC World Congress.
• Arnold, R.D., Yamaguchi, H., and Tanaka, T. (2018). Search and rescue with autonomous flying robots through behavior-based cooperative intelligence. Journal of International Humanitarian Action, 3(1), 1–18.
• Besada, E., de la Torre, L., de la Cruz, J., and Andres-Toro, B. (2010). Evolutionary trajectory planner for multiple uavs in realistic scenarios. Robotics, IEEE Transactions on, 26, 619 – 634. doi: 10.1109/TRO.2010.2048610.
• Bouček, Z., Flidr, M., and Straka, O. (2024). Trajectory tracking for uavs: An interpolating control approach. arXiv preprint arXiv:2407.01095.
• Brameier, M. and Banzhaf, W. (2007). Linear Genetic Programming. Springer.
• Debie, E., Kasmarik, K., and Garratt, M. (2023). Swarm robotics: A survey from a multi-tasking perspective. ACM Comput. Surv., 56(2). doi:10.1145/3611652. URL https://doi.org/10.1145/3611652.
• Fujimori, A., Kubota, H., Shibata, N., and Tezuka, Y. (2014). Leader-follower formation control with obstacle avoidance using sonar-equipped mobile robots. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 228, 303– 315. doi:10.1177/0959651813517682.
• Handayani, A., Nurmaini, S., and Yani, I. (2015). Brief review on formation control of swarm robot. doi: 10.11591/eecsi.2.804.
• Horvath, D., Gazda, J., Šlapak, E., Maksymyuk, T., and Dohler, M. (2021). Evolutionary coverage optimization for a self-organizing uav-based wireless communication system. IEEE Access, 9, 145066–145082.
• Huang, Y., Tang, J., and Lao, S. (2019). Uav group formation collision avoidance method based on second-order consensus algorithm and improved artificial potential field. Symmetry, 11(9). doi:10.3390/sym11091162. URL https://www.mdpi.com/2073-8994/11/9/1162.
• Jones, S., Studley, M., Hauert, S., and Winfield, A. (2018). Evolving behaviour trees for swarm robotics. In Distributed autonomous robotic systems: The 13th international symposium, 487–501. Springer.
• Khatib, O. (1986). Real-time obstacle avoidance for manipulators and mobile robots. The international journal of robotics research, 5(1), 90–98.
• Klančar, G., Zdešar, A., and Krishnan, M. (2022). Robot navigation based on potential field and gradient obtained by bilinear interpolation and a grid-based search. Sensors, 22(9). doi:10.3390/s22093295. URL https://www.mdpi.com/1424-8220/22/9/3295.
• Koza, J.R. (1994). Genetic programming as a means for programming computers by natural selection. Statistics and computing, 4, 87–112.
• li Su, J. and Wang, H. (2021). An improved adaptive differential evolution algorithm for single unmanned aerial vehicle multitasking. Defence Technology, 17(6), 1967– 1975. doi:https://doi.org/10.1016/j.dt.2021.07.008.
• Mellinger, D. and Kumar, V. (2011). Minimum snap trajectory generation and control for quadrotors. In 2011 IEEE International Conference on Robotics and Automation, 2520–2525. doi:10.1109/ICRA.2011.5980409.
• Meza-Sanchez, M., Clemente, E., Rodriguez-Linan, M., and Olague, G. (2019). Synthetic-analytic behavior-based control framework: Constraining velocity in tracking for nonholonomic wheeled mobile robots. Information Sciences, 501, 436–459. doi:
  https://doi.org/10.1016/j.ins.2019.06.025.
• Neupane, A. and Goodrich, M.A. (2019). Learning swarm behaviors using grammatical evolution and behavior trees. In IJCAI, 513–520.
• Nikolos, I.K., Zografos, E.S., and Brintaki, A.N. (2007). Uav path planning using evolutionary algorithms. In Innovations in intelligent machines-1, 77–111. Springer.
• Olfati-Saber, R. (2006). Flocking for multi-agent dynamic systems: Algorithms and theory. IEEE Transactions on Automatic Control, 51(3), 401–420.
• Qin, H., Shao, S., Wang, T., Yu, X., Jiang, Y., and Cao, Z. (2023). Review of autonomous path planning algorithms for mobile robots. Drones, 7(3), 211.
• en, W. and Beard, R.W. (2005). Consensus seeking in multiagent systems under dynamically changing interaction topologies. IEEE Transactions on Automatic Control, 50(5), 655–661.
• Rezk, N.M., Alkabani, Y., Bedour, H., and Hammad, S. (2015). Swarm robotics obstacle avoidance: A progressive minimal criteria novelty search-based approach. In Progress in Artificial Intelligence: 17th Portuguese Conference on Artificial Intelligence, EPIA 2015, Coimbra, Portugal, September 8-11, 2015. Proceedings 17, 493– 498. Springer.
• Rossi, F., Bandyopadhyay, S., Wolf, M., and Pavone, M. (2018). Review of multi-agent algorithms for collective behavior: a structural taxonomy. arXiv preprint arXiv:1803.05464.
• Selvam, P.K., Raja, G., Rajagopal, V., Dev, K., and Knorr, S. (2021). Collision-free path planning for uavs using efficient artificial potential field algorithm. In 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 1–5. IEEE.
• Sfeir, J., Saad, M., and Saliah-Hassane, H. (2011). An improved artificial potential field approach to real-time mobile robot path planning in an unknown environment. In 2011 IEEE International Symposium on Robotic and Sensors Environments (ROSE), 208–213.
• Sperati, V., Trianni, V., and Nolfi, S. (2008). Evolving coordinated group behaviours through maximisation of mean mutual information. Swarm Intelligence, 2, 73–95.
• Zhao, Z. et al. (2023). Enhanced trajectory tracking for quadrotors: disturbance observer-based control. PeerJ Computer Science, 9, e1861.