NEWSLETTER
© TIER IV, INC.
Nov 07, 2024BLOG6. Autoware in a virtual world
In the previous installment, we explored the openness of Autoware, emphasizing its freely available source code. Now, we turn our attention to the simulation tools that play a crucial role in the development of autonomous driving technology.
TIER IV tests autonomous vehicles in various locations across Japan. However, developing autonomous driving in real-world conditions presents several challenges, such as the vast number of scenarios to cover, the unpredictability of specific situations, reproducibility issues, and safety concerns.
As with traditional vehicle development, preliminary validations are conducted on test courses. However, real road environments differ significantly from controlled test courses due to elements like traffic, parked vehicles, pedestrians and bicycles, as well as static objects like signage and trees. Recreating these complex scenarios on a test course is nearly impossible.
This is where computer simulations become indispensable. By creating virtual road environments, Autoware can be tested in a range of simulated settings.
There are three types of simulation methods, each designed to meet different testing needs and applications. The first is the Planning Simulator, which verifies that Autoware’s planning function generates accurate routes and navigates correctly. However, it operates under the assumption that sensor recognition and self-localization are working properly: it cannot test these functions.
The second is the Replay Simulator, which uses sensor data collected from road tests and inputs it into Autoware to reproduce driving scenarios. By using actual road data, it verifies how Autoware interprets real environments, making it ideal for testing recognition and localization functions. However, it is limited to the scenarios recorded by the test vehicle and isn’t suitable for testing planning or control functions.
Both simulators have their unique strengths and limitations, and they are often used together. Despite this, real-world testing remains necessary to ensure the entire autonomous driving system functions correctly, as some issues only surface during on-road trials.
AWSIM simulator
To overcome these challenges, TIER IV developed AWSIM, an open-source digital twin simulator capable of recreating real-world environments. The tool allows for advanced simulation testing of the entire Autoware system.
Historically, such simulations required extremely expensive hardware and software, limiting their accessibility. However, recent advancements have made these simulations available to a broader audience. Now, anyone with access to high-performance computers can perform realistic autonomous driving simulations.
TIER IV’s commitment to advancing both autonomous driving and the simulators that support it ensures that this groundbreaking technology is within reach for developers everywhere.
The next installment looks at the evolving safety measures necessary for autonomous vehicles, examining how they differ from those of traditional automobiles.
Toshihide Ando | TIER IV Fellow
Toshihide joined TIER IV in 2019, where he has served in roles including vice president of technology before assuming his current position as fellow. Previous experience includes software development and R&D at a major Japanese automotive parts manufacturer.
TIER IV is always on the lookout for passionate individuals to join our journey. If you share our vision of making autonomous driving accessible to all, get in touch.
Visit our careers page to view all job openings.
If you’re uncertain about which roles align best with your experience, or if the current job openings don’t quite match your preferences, register your interest here. We’ll get in touch if a role that matches your experience becomes available, and schedule an informal interview.
Media contact
pr@tier4.jp
Business inquiries
sales@tier4.jp
Social Media
X (Japan/Global) | LinkedIn | Facebook | Instagram | YouTube
More