作者: Stéphane Doncieux , Mohamed Hamdaoui
DOI: 10.1007/978-3-642-18272-3_6
关键词: Flapping 、 Evolutionary algorithm 、 Context (language use) 、 Relation (database) 、 Control theory 、 Multi-objective optimization 、 Kinematics 、 Computer science 、 Robotics 、 Control engineering 、 Artificial intelligence
摘要: Evolutionary Algorithms are now mature optimization tools, especially in a multi-objective context. This ability is used here to help explore, analyse and, on this basis, propose controller for complex robotics system: flapping wings aircraft. A performed find the best parameters of sinusoidal kinematics. Multi-objective algorithms generate set trade-off solutions instead single solution. The feedback then potentially more informative context relative one objective setup: can be analyzed characterize studied system. Such an approach applied study simulated wing speed-energy relation empirically evaluated and analysis relations between kinematics speed has led, further step, synthesis open-loop allowing change during flight.