The Secret Sauce of Autonomous Cars

Intelligent vehicles are complex distributed systems. An autonomous car combines vision, radar, lidar, proximity sensors, GPS, mapping, navigation, planning, and control. These components must combine into a reliable, safe, secure system that can analyze complex environments in real time and react to chaotic environments. Autonomy is thus a supreme technical challenge. An autonomous car is more a robot on wheels than it is a car. Automotive vendors suddenly face a very new challenge. Of course, the challenge isn’t completely new; autonomy has a rich technology heritage in other industries, including aviation drones, space robotics, and underwater vehicles. Autonomous cars can leverage this base, but streets and highways are much faster, more chaotic environments. Human cargo raises the stakes for reliability and safety. Passenger vehicles are already very complex systems. Thus, cars take the autonomy challenge to a new level. They need industrial-class reliability, true real-time response, and powerful system integration. So, what’s the secret sauce? System components interact through data flow. Complex systems, therefore, operate by controlling that dataflow exactly as needed by each component. This technology is called datacentric connectivity. It today runs intelligent robots and reliable power and medical systems. Data-centric connectivity was originally developed for autonomous systems. Unlike messaging technologies, it directly controls data interactions. It removes all of the complexity of managing data communications from components. It excels at highly reliable, complex system integration. It is fully standardized, proven in hundreds of industrial systems, and already controlling many autonomous planes, robots, submarines . . . and cars. Data Centricity History in Autonomy Data-centric communications originated in autonomous robotic systems. Researchers building autonomous air and space vehicles at the Stanford Aerospace Robotics Laboratory developed the core technology. In 2004, the technology was codified in a standard called the Data Distribution Service (DDS). Since then, DDS expanded into thousands of applications in defense, medical, power, mining, communications, and transportation. Today, DDS is everywhere there is autonomy. It integrates the world’s most advanced drones, NASA planetary rovers, unmanned military ground vehicles, and autonomous surface and underwater robots. RTI was the architectural lead for the US ground station design; DDS now forms the core connectivity for essentially all ground stations. An RTI-based nationwide system called Ground-Based Sense and Avoid (GBSAA) will soon allow drones in US National Air Space. And, as this paper outlines, DDS is a key component in the exciting emergence of autonomous cars and trucks. WHITEPAPER Stan Schneider, CEO, Real-Time Innovations, Inc.