Open-source digital twin-oriented autonomous driving simulator

Open-source digital twin-oriented autonomous driving simulator

New Products |
By Rich Pell

Open source autonomous driving startup TIER IV has announced the open-source release of a digital twin-oriented autonomous driving simulator designed to efficiently develop safe autonomous driving systems. To realize the evaluation and verification of the autonomous driving software, Scene Simulator for Autoware – AWSIM – is designed to achieve real-world driving and traffic environment simulation by building a virtual world based on 3D model maps and pairing them with sensor data models in combination with realistic physical models.

Over the coming months, says the company, the automatic generation of synthetic training data for machine learning will significantly reduce the cost of training and validation of object detection and environmental recognition.

“The mission of TIER IV is to co-create value, disruptively, through intelligent vehicles,” says Shinpei Kato, Founder and CTO of TIER IV. “To achieve this goal in the right way, we share the vision ‘The Art of Open Source – Reimagine Intelligent Vehicles’, establishing a sound ecosystem that enables as many organizations and individuals as possible to be part of our mission. This ensures the technology is not dominated by particular players but open to everyone. The digital twin-oriented autonomous driving simulator which we just announced today is one of such products that will realize our vision through open source and fulfill our responsibility in the market.”

The company’s Web.Auto is a cloud-native and edge-intensive DevOps platform for autonomous driving simulation, CI/CD data pipeline, data management, operations management, and remote monitoring. Until today, says the company, the focus of autonomous driving software validation has been on scenario-based driving and traffic environment simulation, and real-world event reproduction tests with driving logs. The newly announced end-to-end simulation adds to the existing modes of testing, enabling efficient validation according to each target objective and achieving even safer autonomous driving.

Web.Auto is powered by Amazon Web Services (AWS), the world’s most comprehensive and widely adopted cloud platform. In addition, the autonomous driving simulator uses the technology from Unity, the world’s leading provider of real-time 3D platforms.


If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles