Modular robotics and autonomy platform advances
Perrone Robotics, Inc. (PRI) announced advances that include a new patent toward the commercial development and deployment of its modular autonomy and robotics software platform—a common platform for companies at any stage to quickly design and build a range of robotic products and applications. The company was awarded a continuation of its earlier U.S. patent (9,195,233) that addresses the ability of its MAX platform to handle a wide range of autonomous vehicles including robots, carts, shuttles, automobiles, trucks, aircraft, and watercraft.
The new patent, U.S. patent no. 9,833,901, expands on the original patent covering Perrone Robotics’ technology and makes it easier to develop and deploy reliable and capable robotics solutions with minimal programming. The original patent was filed in February 2006.
Additionally, PRI is collaborating with Professor Robert Hecht-Nielsen of the University of California, San Diego’s (UCSD) Vertebrate Movement Laboratory (VML) and its research team on advanced machine learning methods for autonomous vehicle perception and control. The new collaboration project is based on a method for perception and machine learning for autonomous vehicles and will combine Hecht-Nielsen’s work on artificial neural networks (ANN), confabulation theory, and vertebrate movement mathematics with PRI’s applied experience in autonomous vehicles and robots.
“The market for autonomous driving technologies has become unduly frothy even though those solutions offer isolated or highly constrained applicability,” said Paul Perrone, Founder and CEO of Perrone Robotics, Inc. “Our platform addresses the market opportunity and demand for the general mobility of things, and is the only common platform for developing and deploying autonomous vehicles, ranging from a vacuum cleaner to a car to mining or farming equipment.
“The new expanded patent is a direct result of 14+ years of research and development in autonomous mobility and robotics. Our MAX technology represents a unique and modular platform that accelerates the development, production, testing, and certification of reliable, safe, and high-performance autonomous and robotics solutions across all types of moving things,” he continued.
To demonstrate the scalability of its platform, PRI says it is conducting extensive research and development, testing its platform on various hardware from multi-core central processing units (CPUs), graphics processing units (GPUs), and field-programmable gate arrays (FPGAs) down to something as simple and inexpensive as a Raspberry Pi.
The ability to run complex solutions across a range of hardware illustrates not only the efficiency of the code, but also the value of the platform’s ability to allow OEMs to layer on, or subtract, advanced processing as needed. Developers do not have to be locked into high-powered, energy-consuming systems, but instead can apply as many or as few autonomous components as needed. This approach illustrates PRI’s contrarian model of optimally layering on adaptive processing rather than starting with solutions that consume many resources and require complex training and execution models.