Nnaisense has announced the launch of EvoTorch. The artificial intelligence startup is providing industry with an evolutionary algorithm (EA) package in the “first open-source platform of its kind”. Based in Lugano, Nnaisense was formed in 2014 in order to build large-scale neural network solutions for industrial process inspection, modeling and control.
EvoTorch provides a package with powerful EAs, which when combined with machine learning (ML) can solve complex operational challenges “in a fraction of the time, at lower costs and greater scale”, as was reported in a press release. “The goal of EvoTorch is to create an open-source ML community and facilitate the adoption of EAs within the field of automation,” said Rupesh Srivastava, Director of Software Infrastructure at Nnaisense. It does so by “providing researchers and engineers with the tools to scale up their designs easily and quickly”.
In a pioneering project with Audi, these tools were applied to the automotive manufacturer’s autonomous parking system. This highlighted how much time could be saved by parallelizing evolutionary algorithms to achieve operational goals for industry, as Jan Koutnik, Co-founder & Director of Intelligent Automation, explained: “using this technique, we condensed 180 years’ worth of simulated driving time into 24 hours”.