Towards long-lived robot genes

Robot projects are often evolutionary dead ends, with the software and hardware they produce disappearing without trace afterwards. Common causes include dependencies on uncommon or obsolete devices or libraries, and dispersion of an already small group of users. In humanoid robotics, a small field with an avid appetite for novel devices, we experience a great deal of "churn" of this nature. In this paper, we explore how best to connect our software with the mainstream, so that it can be more stable and long-lasting, without compromising our ability to constantly change our sensors, actuators, processors, and networks. We also look at how to encourage the propagation and evolution of hardware designs, so that we can start to build up a "gene-pool" of material to draw upon for new projects. We advance on two fronts, software and hardware. Building on our robot software architecture YARP [11], we focus on how to organize communication between sensors, processors, and...

• Type: Journal
• Year: 2008
• Where: RAS
• Authors: Paul M. Fitzpatrick, Giorgio Metta, Lorenzo Natale
• Keywords: Humanoid Robotics, Loose Coupling, RAS 2008, Software