How Do You Teach a Robot About Risk?

George Di Nardo, President of Larus Technologies, is the Honorary Chair of the 2013 IEEE Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA 2013) taking place July 15-17 in Milan, Italy. Among the highlights of CIVEMSA 2013 will be a variety of presentations by international thought leaders in the field of computational intelligence related to real-world applications such as assisted living, oil well profiling and body condition assessment.

George Di Nardo will be presenting an article, recently published by Larus Technologies and entitled “A Proactive Risk-Aware Robotic Sensor Network for Critical Infrastructure Protection”, presenting the results of its current research efforts in risk management for mission-critical applications. This paper is an excellent example of the work Larus has undertaken in the area of proactive risk management for Critical Infrastructure Protection. Using computational intelligence techniques, the risk management framework analyzes risk features that are extracted from a remote robotic sensor network. The latter continually monitors and updates various aspects of the environment and, in response to node failures and possible security breaches, the remaining nodes will topologically self-organize to maximize the perimeter coverage while minimizing the cost of doing so. This framework can be applied to the safe-guarding of national defence assets, transportation and energy assets, strategic public buildings, offshore infrastructure and large public events just to name a few examples.

Why is this exciting? Well, this is the first time a robotic sensor network applied to a Critical Infrastructure Protection scenario is self-organized in response to a risk analysis conducted on every sensor node on the basis of multiple risk features.

Scroll to Top