Bio-inspired Robots: Learning from Nature
The fundamental motivation behind the development of bio-inspired multi-robot teams is the ability of living organisms to successfully cope and provide good solutions to almost all robotic related problems. Navigation, material handling and sensors, machine learning are only some of the research areas benefited from examining and adopting methodologies, techniques or mimicking behaviors proved sustainable and successful for animals and humans.
The talk will follow the bio-inspired paradigm of hunting mammals in land (wolves) and the sea (dolphins), intending to make this knowledge applicable to the coordination problem of heterogeneous robotic teams. The objective will be to present, define and discuss the required level of inference capabilities needed for robotic navigation and coordination purposes. Emphasis will be given on the fact that humans and animals decide and conclude about unknown features of their world under constraints of limited time, knowledge, and computational capacity. And despite their ”bounded rationality” (or cognitive limitations) tend to built and use domain specific heuristics that allow for fast problem solving (and task specific successful behaviors). Robots and agents may be benefited from this fact.