Refereed Journal Articles

1. Gattaux, G., Diallo, H., Serres, J. R., Wystrach, A., & Ruffier, F. (2026). Antflie: Frugal Visual Teach and Repeat on Narrow FoV Micro-Drones. IEEE Robotics and Automation Letters, 11(4), 4617–4624. https://ieeexplore.ieee.org/document/11408827

   PDF DOI BIB Abstract

   @article{gattaux2026antflie,
     author = {Gattaux, Gabriel and Diallo, Hamidou and Serres, Julien R. and Wystrach, Antoine and Ruffier, Franck},
     title = {Antflie: Frugal Visual Teach and Repeat on Narrow FoV Micro-Drones},
     journal = {IEEE Robotics and Automation Letters},
     year = {2026},
     volume = {11},
     number = {4},
     pages = {4617--4624},
     doi = {10.1109/LRA.2026.3667486},
     url = {https://ieeexplore.ieee.org/document/11408827},
     file = {antflie_ral_2026.pdf}
   }
   

   We present an insect-inspired visual teach-and-repeat framework demonstrated on Antflie, a 33-gram micro aerial vehicle equipped with an ultra-low-resolution 24 × 24 px camera and a narrow 87° field of view. During a one-shot teach flight, Antflie stores compact lateralized visual memories in a Mushroom Body neural network below 4 kB, then repeats the route and lands at home using visual familiarity through direct sensorimotor coupling. Simulations and indoor experiments show accurate route repetition with low computational cost, supporting frugal bio-inspired vision-only navigation for size-, weight-, power-, and cost-constrained micro aerial vehicles.

2. Gattaux, G. G., Wystrach, A., Serres, J. R., & Ruffier, F. (2025). Route-centric ant-inspired memories enable panoramic route-following in a car-like robot. Nature Communications, 16, 8328.

   PDF DOI BIB Abstract

   @article{gattaux2025route,
     author = {Gattaux, Gabriel G. and Wystrach, Antoine and Serres, Julien R. and Ruffier, Franck},
     title = {Route-centric ant-inspired memories enable panoramic route-following in a car-like robot},
     journal = {Nature Communications},
     year = {2025},
     volume = {16},
     pages = {8328},
     doi = {10.1038/s41467-025-62327-3},
     file = {antcar_ncoms_2025.pdf}
   }
   

   Solitary foraging ants excel at route following using minimal neural resources, Robots don’t. Recent biological studies proposed lateralized, nest-centric memories to explain ants’ direct visual homing but did not address how ants follow curved visual routes away from their nest. We present a biologically inspired neuromorphic model for one-shot panoramic route learning and continuous route following, implemented on a compact car-like robot, Antcar. We demonstrate that route-centric lateralized memories, inspired by the insect mushroom body, enable Antcar to achieve bi-directional route-following, with motivation-driven recognition of route extremities and familiarity-based velocity control. With rigorous Lyapunov-based stability analysis and an empirical memory scalability evaluation, the model was tested over 1.6 km across 113 challenging real-world trials. The system achieves less than 25 cm median lateral error using minimal resources (800-pixel input, 300 MB RAM, 500 mW power, and 18.75 kB memory per 50 m route), offering insights into insect cognition and advancing autonomous robotics under strict resource constraints.

Refereed Conference Proceedings

1. Gattaux, G., Serres, J. R., & Ruffier, F. (2026). Visual Homing in Outdoor Robots Using Mushroom Body Circuits and Learning Walks. In J. Rodríguez & others (Eds.), Biomimetic and Biohybrid Systems (pp. 456–468). Springer Nature Switzerland.

   PDF DOI BIB Abstract

   @inproceedings{gattaux2026visualhoming,
     author = {Gattaux, Gabriel and Serres, Julien R. and Ruffier, Franck},
     title = {Visual Homing in Outdoor Robots Using Mushroom Body Circuits and Learning Walks},
     booktitle = {Biomimetic and Biohybrid Systems},
     editor = {Rodr{\'i}guez, Jim{\'e}nez and others},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     year = {2026},
     pages = {456--468},
     isbn = {978-3-032-07448-5},
     doi = {10.1007/978-3-032-07448-5_38},
     file = {antcar_living_2026.pdf}
   }
   

   Ants achieve robust visual homing with minimal sensory input and only a few learning walks, inspiring biomimetic solutions for autonomous navigation. While Mushroom Body (MB) models have been used in robotic route following, they have not yet been applied to visual homing. We present the first real-world implementation of a lateralized MB architecture for visual homing onboard a compact autonomous car-like robot. We test whether the sign of the angular path integration (PI) signal can categorize panoramic views, acquired during learning walks and encoded in the MB, into “goal on the left” and “goal on the right” memory banks, enabling robust homing in natural outdoor settings. We validate this approach through four incremental experiments: (1) simulation showing attractor-like nest dynamics; (2) real-world homing after decoupled learning walks, producing nest search behavior; (3) homing after random walks using noisy PI emulated with GPS-RTK; and (4) precise stopping-at-the-goal behavior enabled by a fifth MB Output Neuron (MBON) encoding goal-views to control velocity. This mimics the accurate homing behavior of ants and functionally resembles waypoint-based position control in robotics, despite relying solely on visual input. Operating at 8 Hz on a Raspberry Pi 4 with 32 
    32 pixel views and a memory footprint under 9 kB, our system offers a biologically grounded, resource-efficient solution for autonomous visual homing.

2. Gattaux, G., Wystrach, A., Ruffier, F., & Serres, J. (2025). Enhancing Ant-Inspired Visual Compass with Focused Visual Scan in a Compact Robot. 2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS), 1–5.

   PDF DOI BIB Abstract

   @inproceedings{gattaux2025enhancing,
     author = {Gattaux, Gabriel and Wystrach, Antoine and Ruffier, Franck and Serres, Julien},
     title = {Enhancing Ant-Inspired Visual Compass with Focused Visual Scan in a Compact Robot},
     booktitle = {2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)},
     year = {2025},
     pages = {1-5},
     volume = {},
     number = {},
     doi = {10.1109/AICAS64808.2025.11173128},
     issn = {2834-9857},
     file = {antcar_aicas_2025.pdf}
   }
   

   As the demand for autonomous robots grows, from self-driving cars to factory automation, so does the need for resource-efficient navigation algorithms. This challenge has inspired the development of sparse neural networks for visual navigation, drawing particularly from bio-inspired, ant-based neuromorphic artificial intelligence algorithms. Recent approaches leverage the neural architecture of the mushroom body in ants to learn and follow routes by recognizing familiar visual patterns. However, such models have not yet been implemented in closed-loop, resource-constrained robotic systems with satisfying performance. In this work, we present a mushroom body-inspired model embedded in the Antcar, a compact, car-like robot that processes panoramic images at low resolution. Our experiments reveal that reducing the scanning range and resolution improves visual compass performance for robot’s route-following. These findings highlight the trade-off between increased refresh rates and the benefits of selective perception, paving the way for more efficient real-time decision-making in resource-constrained systems.

Patents

1. Gattaux, G., Ruffier, F., Serres, J. R., & Wystrach, A. (2026). Method for heading estimation using vision. Patent draft in preparation.

   @patent{gattaux2026patent,
     author = {Gattaux, Gabriel and Ruffier, Franck and Serres, Julien R. and Wystrach, Antoine},
     title = {Method for heading estimation using vision},
     year = {2026},
     note = {Patent draft in preparation}
   }
   

2. Gattaux, G., Ruffier, F., Serres, J. R., & Wystrach, A. (2025). Method for guiding to a destination. French patent granted; international patent application pending.

   @patent{gattaux2025patent,
     author = {Gattaux, Gabriel and Ruffier, Franck and Serres, Julien R. and Wystrach, Antoine},
     title = {Method for guiding to a destination},
     year = {2025},
     number = {FR3151085A1; WO2025012244A1},
     note = {French patent granted; international patent application pending}
   }
   

Preprints

1. Gattaux, G., Vimbert, R., Wystrach, A., Serres, J. R., & Ruffier, F. (2023). Antcar: Simple Route Following Task with Ants-Inspired Vision and Neural Model. HAL: hal-04060451.

   PDF arXiv BIB Abstract

   @unpublished{gattaux2023antcar,
     author = {Gattaux, Gabriel and Vimbert, Roxane and Wystrach, Antoine and Serres, Julien R. and Ruffier, Franck},
     title = {Antcar: Simple Route Following Task with Ants-Inspired Vision and Neural Model},
     note = {HAL: hal-04060451},
     year = {2023},
     doi = {hal-04060451v1},
     file = {antcar_preprint_2023.pdf}
   }
   

   The goal of this project is to develop a new method of route following for mobile robots in GNSS-denied environments like urban canyons or forests. Inspired by ants’ navigation strategies, we propose a lightweight visual memory model based on panoramic snapshots and familiarity discrimination. This method enables robust route following using only low-resolution visual input and a compact neural architecture, making it suitable for embedded robotic applications.