Jan 23, 2019

Why AV sensors need simulations of their own

Illustration: Rebecca Zisser/Axios

Simulation has been critical to speeding up AV development, especially for motion planning and control algorithms. But in these simulations, vehicles are either not perceiving the simulated world at all or perceiving only scenarios that have been previously encountered on the road.

Why it matters: Using these approaches, vast amounts of on-road data will need to be gathered in order to reach the edges of a perception module's capabilities. An additional layer of simulation for AV sensors and perception systems could use synthetic data to accelerate the development of AVs.

Background: AV simulations test different modules of the self-driving software using map data and information about obstacles on the road.

  • In re-simulations, saved data from on-road drives can be fed back through the software. AV engineers can develop test scenarios to benchmark software performance and then compare the results after making updates.

What's needed: Simulating sensor models as well could help in several areas.

  • Optimizing sensor placement on vehicles. Being able to position and visualize the output from sensors is easier and faster using software than real hardware.
  • Creating data sets to train for rare situations. Simulations can model any imaginable scenario, however unlikely.
  • Feeding perception algorithms with synthetic sensor data. This allows engineers to continuously create new scenarios and test their algorithms, rather than waiting for new on-road data.

The catch: Sensor simulation for perception algorithms is difficult because each sensor type (lidar, radar, camera, infrared) has different levels of complexity.

  • In an ideal case, a real hardware sensor’s information could be reproduced using purely software. This requires modeling the underlying physics of each sensor and carefully constructing the 3D environment in which the synthetic sensors “operate.”
  • Synthetic data could then be passed to perception algorithms in a form that they can’t differentiate from real data.

These simulation platforms have to be capable of creating and rendering large photorealistic environments in real time.

  • Sensor tasks add to the load: Properly simulating radar or lidar can require casting millions of synthetic rays per second.

The bottom line: Sensor simulation for perception is still a new process, but could fill an important gap in the development cycle of AV software.

Chris Gundling is a senior software engineer at Applied Intuition, an AV simulation software company.

Go deeper

America's rundown roads add to farmers' struggles

Illustration: Sarah Grillo/Axios

American farmers are struggling to safely use the roads that cut through their fields; decades of neglect and lack of funding have made the routes dangerous.

The big picture: President Trump has long promised to invest billions in rural infrastructure, and his latest proposal would allocate $1 trillion for such projects. Rural America, where many of Trump's supporters live, would see a large chunk of that money.

South Korea and Italy see spikes in coronavirus cases

Data: The Center for Systems Science and Engineering at Johns Hopkins, the CDC, and China's Health Ministry. Note: China numbers are for the mainland only and U.S. numbers include repatriated citizens.

The novel coronavirus continues to spread to more nations, and the U.S. reports a doubling of its confirmed cases to 34 — while noting those are mostly due to repatriated citizens, emphasizing there's no "community spread" yet in the U.S. South Korea's confirmed cases jumped from 204 on Friday to 433 on Saturday, while Italy's case count rose from 3 to 62 as of Saturday.

The big picture: COVID-19 has now killed at least 2,362 people and infected more than 77,000 others, mostly in mainland China. New countries to announce infections recently include Israel, Lebanon and Iran.

Go deeperArrowUpdated 4 hours ago - Health

Centrist Democrats beseech 2020 candidates: "Stand up to Bernie" or Trump wins

Bernie Sanders rallies in Las Vegas, Nevada on Feb. 21. Photo: Mario Tama/Getty Images

Center-left think tank Third Way urgently called on the Democratic front-runners of the 2020 presidential election to challenge Sen. Bernie Sanders on the South Carolina debate stage on Feb. 25, in a memo provided to Axios' Mike Allen on Saturday.

What they're saying: "At the Las Vegas debate ... you declined to really challenge Senator Sanders. If you repeat this strategy at the South Carolina debate this week, you could hand the nomination to Sanders, likely dooming the Democratic Party — and the nation — to Trump and sweeping down-ballot Republican victories in November."