Robo-Taxi Startup Voyage to Make its Autonomous Safety Systems Open Source
【Summary】Silicon Valley startup Voyage, which recently launched a pilot autonomous ride-hailing service in two retirement communities in California and Florida, is taken a proactive, safety first approach. Starting today, the company announced today it is opening its safety requirements, test scenarios, metrics, tools, and source code that it has developed for its own autonomous taxis.
After a self-driving Uber vehicle fatality struck a pedestrian last month in Arizona, the nascent autonomous driving companies paused to reevaluate the hardware and software used to control self-driving cars—in order to prevent another incident like the one in Arizona from happening again.
Silicon Valley startup Voyage, which recently launched a pilot autonomous ride-hailing service in two retirement communities in California and Florida, is taken a proactive, safety first approach. Starting today, the company announced today it is opening its safety requirements, test scenarios, metrics, tools, and source code that it has developed for its own autonomous taxis.
The initial release, which Voyage calls ‘Open Autonomous Safety' (OAS), will reside in a GitHub repository containing documents and source code—available to any interested parties to utilize as needed.
OAS is a fully open-source library of Voyage's internal safety procedures, materials, and test code designed to supplement existing safety programs at autonomous vehicle startups across the world.
The OAS consist of four primary parts. The first is ‘scenario testing'. These important scenarios represent fundamental questions, such as how should an autonomous vehicle behave when it reaches a crosswalk and a pedestrian approaches from the right?
The OAS also includes other key areas including, functional safety, autonomy assessment and a complete testing toolkit. Voyage plans to add fault-injection testing in the future, to evaluate how a self-driving car reacts in the event of a hardware or software failure.
These scenarios, and many more, provide a rubric for assessing the practical capabilities of a self-driving vehicle while on the road in a suburban environment. The scenarios also introduce a qualitative dimension to Voyage's safety program.
"We don't just ask if one of our vehicles can complete a scenario, but also how well it performs." Voyage wrote in their blog post.
Voyage is not the first company working on self-driving technology to open its platform to developers. China's Baidu announced last year its Apollo platform, which consists of an entire suite of self-driving tools, including simulation and HD mapping technology open to any interested parties. Baidu's open source Apollo platform is looking to become the Android of self-driving cars.
This alpha release of OAS is designed to grow extensively in the coming months now that it's open to other developers. Voyage's aim is to cement its OAS as a foundational safety resource for the entire self-driving car industry.
Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.
Ford is Testing a New Robotic Charging Station to Assist Drivers of EVs With Disabilities
Ford Raises the Prices of the F-150 Lightning Electric Pickup Due to Rising Raw Material Costs
The BMW 7-Series to Feature HD Live Maps From HERE Technologies for Hands-Free Highway Driving in North America at Speeds up to 80 MPH
AutoX to Use the 'Eyeonic Vision Sensor' from California-based SiLC Technologies for its Robotaxi Fleet in China
LG Develops ‘Invisible’ Speaker Sound Technology That Could Revolutionize In-Vehicle Audio
Researchers at South Korea’s Chung-Ang University Develop a ‘Meta-Reinforcement’ Machine Learning Algorithm for Traffic Lights to Improve Vehicle Throughput
Zeekr’s New 009 Electric Passenger Van is the World’s First EV to Feature CATL’s Advanced ‘Qilin’ Battery With a Range of 510 Miles
Redwood Materials is Building an Electric Vehicle Battery Recycling Facility in South Carolina
- Tesla’s Battery Supplier Panasonic is Working on New EV Battery Technology That Can Boost Range by 20%
- LG Chem is Investing $3.2 Billion to Build a Cathode Manufacturing Facility for Electric Vehicle Batteries in Tennessee
- Volvo’s Electric Vehicle Brand Polestar Reports $1 Billion in Revenue in the First Half of 2022, Adds 6 New Global Markets
- The Polestar 5 Sedan Will Have Dual Electric Motors With 884 HP
- The Tesla Model Y and Model 3 Take the 1st and 2nd Place Spots in the Annual Cars.com ‘American-Made Index’
- J.D. Power Study Finds That EVs Are More Problematic Than ICE Cars
- Tesla Rival XPeng and Alibaba Cloud Set Up China’s Largest Cloud-Based Computing Center to Train Machine Learning Models for Autonomous Driving
- Lucid Launches New Performance Brand ‘Sapphire’ with a 1,200 Horsepower, Tri-Motor Version of the Lucid Air Sedan
- Apple Reveals the Next-Gen Version of CarPlay, Which Takes Over a Vehicle’s Entire Dashboard and Screens
- Ford Motor Co is Recalling 2.9 Million Vehicle That Could ‘Roll Away’ After the Transmission is Shifted Into Park