StandPI enables the efficient usage of
Crowdsourcing Delivery for the loading industry. Therefore, internal and
external system parameters will be continuously monitored and these real-time
data will be further processed by a machine learning algorithm. By the means of
this algorithm, the matching of the loader’s product supply and the dynamically
available transportation capacities concerning Crowdsourcing Delivery will be
optimized. Eventually, in contrast to the nowadays commonly used sequentially
controlling and optimization of the transportation and inner logistics systems,
the aim of this research project is a self-learning controlling, which acts at
the interface of this system, concerning a cross-system optimization. Hence,
consistent exploitation of the remaining capacities of vehicles en route will
significantly contribute to economical, ecological and social sustainability
concerning physical distribution.
The usage of private
cars to deliver goods need new coordination and routing protocols, which could
have an impact on PI Network Services. The coordination of different networks
is foreseen but was not visible from the current results of Stand PI.
Collaboration between
different networks contributes to Generation 0.