Zenuity, a joint venture between Volvo Cars and Veoneer, announced that it is working with CERN to improve self-driving cars' decision-making, thus enhancing safety.
The challenge in developing these vehicles lies in interpreting the vast data generated during normal driving, such as identifying other vehicles and pedestrians. CERN, known for its Large Hadron Collider, generates vast amounts of data that requires quick decision-making, which it achieves through Field-Programmable GATE Arrays (FPGAs).
Use of autonomous driving software
For the past three years, researchers have collaborated with Volvo's subsidiary Zenseact on computer vision for autonomous driving software. The aim was to enhance decision-making in autonomous cars using LHC's Deep Learning algorithms. The research showed potential for improvement in running the algorithms faster and more efficiently on resource-constrained on-device hardware. According to Christoffer Petersson, research lead at Zenseact; machine learning can drive faster decision-making in autonomous vehicles.
The CEO of Zenuity, Dennis Nobelius, emphasized the significance of the partnership between the European Organization for Nuclear Research (CERN), known for its work in high-energy particle collisions, and the joint venture between Volvo Cars and Veoneer, which is dedicated to eliminating traffic collisions. Despite the excitement surrounding the potential of autonomous vehicles, the industry still faces safety concerns that need to be addressed.
Cern uses FPGAs, a hardware system capable of executing complex decision-making algorithms in microseconds, for fast machine learning in autonomous driving and particle physics experiments.
The partnership highlights the importance of collaboration and cooperation in science and technology. The collaboration between Zenuity and CERN will focus on utilizing Field-Programmable Gate Arrays (FPGAs) for advanced machine-learning applications in both the autonomous driving sector and particle physics experiments. FPGAs will provide the necessary speed and decision-making capabilities for these complex applications.
Safety concerns with self-driving cars
Autonomous vehicles can revolutionize transportation and make our roads safer, but safety concerns continue to be a major issue. This is highlighted by the tragic incident in 2018 where an Uber autonomous vehicle struck and killed a pedestrian in Tempe, Arizona. The incident drew attention to the complex and challenging problem of ensuring the safety of autonomous vehicles in all driving scenarios.
In 2019, the CEO of Arm Holdings, Simon Segars, commented on the state of the self-driving car industry, stating that it would take some time for the technology to become mainstream. He noted that anticipating a car's actions under all possible circumstances is a daunting task, and it may still be some time before fully autonomous vehicles become widely adopted.
However, Segars also stated that early, limited autonomous vehicle services could emerge in the future. This could give people a taste of what self-driving cars can do, but complete mainstream adoption of the technology is likely still some time away. Despite the challenges, the potential benefits of autonomous vehicles are too great to ignore. The industry is working to overcome these safety concerns and make self-driving cars a reality.
