Towards the Autonomous Evolution of Robotics Ecosystems
Event details
Robot design is traditionally the domain of humans – engineers, physicists, and increasingly AI experts. However, if the robot is intended to operate in a completely unknown environment (for example planetary exploration) then it is very difficult for human designers. Evolutionary computing is a well-known technology that has been applied in various aspects of robotics for many years, for example to design controllers or body-plans. When coupled with advances in materials and printing technologies that allow rapid prototyping, it offers a potential solution to the issue raised above. However, it also brings new challenges. The additional constraints introduced by the need for example to manufacture robots autonomously, to explore rich morphological search-spaces and develop novel forms of control require some re-thinking of “standard" approaches in evolutionary computing and some novel approaches to engineering. In this talk I will discuss some of these challenges and propose some methods to address them, that have mainly been developed in the context of the collaborative ARE project.