Evolving State Machines as Robot Controllers

Automated generation of robot controllers using an Evolutionary Algorithm(EA) has received increasing attention in the last years as it has the potentialfor a reduction in the development time of a robot. Often these EAs generateNeural Networks (NNs) as robot controllers. Using a NN for automaticallygenerating robot controllers has two important...

Design of a magnetic coupling for reducing maintenance in long-term-autonomous bio-inspired underwater vehicles

Bio-inspired underwater vehicles are highly researched as a means for low-invasive monitoring. As a result, the performance of these vehicles has improved greatly. Research has thus far been directed towards the performances of the swimming motion. In order for the development of these bio-inspired underwater vehicles to continue, the increased...

Lunar Zebro - Software Design Of The Locomotion Sub-System With The Dezyne Model Driven Development Tool

The TU Delft ZEs-Benige RObot (Zebro) project is presented with the opportunity to bring the Zebro concept to the surface of our moon. To maximise the probability of success, the Locomotion Sub-System (LSS) software of Lunar Zebro is developed using a novel model-driven design tool called Dezyne. Dezyne uses a proprietary language to describe...

Design of the locomotion subsystem for the Lunar Zebro: A design and implementation to ensure that Zebro can thrive on the moon

This report covers the development of the Locomotion system for the Lunar Zebro that is responsible for the positioning control of the six legs and the operating of the solar panel. It covers the initial problem analysis, requirement discovery, conceptual design, part identification for implementation, implementation and the first tests, their...