There have been massive improvements in autonomous driving, and other related capabilities in the automotive industry in recent years. Driven by the pioneers in the industry, full market adoption of these technologies is approaching quickly. Deep learning is a major enabler in the space of autonomous driving systems and is used for various tasks including the detection of other vehicles, classification of traffic signs and obstacle recognition. For machine drivers to become safer than human drivers however, there is still some way to go. Experts agree nonetheless that deep learning will take this hurdle in the coming years.
Robust autonomous driving systems
In partnerships with leading German Automotives and OEMs, Merantix is working on level 4+ autonomous by going simulation-first. We are using smart augmentation algorithms and create simulated datasets to train and especially test neural network. That way we make autonomous driving systems robust and explainable. In addition, we have developed a testing system that can visualize the characteristics of a trained neural network and highlight regions as well as objects in a real or simulated dataset, that trigger decisions and quantify their impact.
Find below one of our developments, that we have open-sourced for the research community:
Number of Papers
published in top-tier journals and conferences on visualizing neural networks.
of automakers do not have a hacking countermeasure strategy in place.
faster growth rate of the connected car market vs. the total car market.
Your data and knowledge,
Schedule an appointment