Digital Image Processing
Evolving Vision-Based Flying Robots
BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series)
Expansion segmentation for visual collision detection and estimation
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Inertial aided SIFT for time to collision estimation
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A modified model for the Lobula Giant Movement Detector and its FPGA implementation
Computer Vision and Image Understanding
Work directions and new results in electronic travel aids for blind and visually impaired people
WSEAS TRANSACTIONS on SYSTEMS
Elaborated motion detector based on Hassenstein-Reichardt correlator model
ICS'10 Proceedings of the 14th WSEAS international conference on Systems: part of the 14th WSEAS CSCC multiconference - Volume I
Work directions and new results in electronic travel aids for blind and visually impaired people
ICS'10 Proceedings of the 14th WSEAS international conference on Systems: part of the 14th WSEAS CSCC multiconference - Volume I
A bio-inspired obstacle avoidance system concept for visually impaired people
Proceedings of the 15th WSEAS international conference on Systems
Hi-index | 0.00 |
The most versatile and robust flying machines are still those produced by nature through evolution. The solutions to the 6 DOF control problem faced by these machines are implemented in extremely small neuronal structures comprising thousands of neurons. Hence, the biological principles of flight control are not only very effective but also efficient in terms of their implementation. An important question is to what extent these principles can be generalized to man-made flying platforms. Here, this question is investigated in relation to the computational and behavioral principles of the opto-motor system of the fly and locust. The aim is to provide a control infrastructure based only on biologically plausible and realistic neuronal models of the insect opto-motor system. It is shown that relying solely on vision, biologically constrained neuronal models of the fly visual system suffice for course stabilization and altitude control of a blimp-based UAV. Moreover, the system is augmented with a collision avoidance model based on the Lobula Giant Movement Detector neuron of the Locust. It is shown that the biologically constrained course stabilization model is highly robust and that the combined model is able to perform autonomous indoor flight.