Existing cleaning robots clean in a simple linear back and forth “ox-plow” pattern. However, in complex buildings like shopping malls, real cleaning professionals clean in more complex curvilinear patterns that conform to the contours of their surroundings. The new Cyberworks path planner uses the latest advances in AI to analyze the contours of a complex building to generate highly efficient human-like cleaning patterns as shown in the example below which was generated by Cyberworks’ AI Navigation Path Planning Engine. This marks a dramatic breakthrough in efficiency for existing floor scrubbers in the field. Additionally, unlike conventional robotic systems, Cyberworks new self-driving solution works in feature-sparse, feature-repetitive and very large-scale environments – something that has been impossible for competitive self-driving systems.
Cyberworks has developed the first realistic 3D Virtual Reality Simulator for cleaning robots. This allows Cyberworks to achieve extraordinary levels of robustness by testing their navigation systems in hundreds of real-world environments using real sensory data without leaving the lab. The Sim uses data from real buildings (generated by walkthroughs using an inexpensive RGBD sensor) and using the actual mechanics and kinematics of real floor scrubbers (which allows Cyberworks to duplicate the slippage, turning radius, etc of those machines). The Cyberworks Sim runs custom versions of its core autonomous navigation software adapted to the specific kinematics of each simulated scrubber. Cyberworks’ clients can see their equipment operating in the buildings of their choice in full 3D Virtual Reality just as they would in the real world.
There are over 4.4 million power wheelchairs in the USA alone and 3 million professional floor scrubbers. In total there are an estimated tens of millions of target vehicles which Cyberworks aims to automate through sales and installation of add-on navigation systems for existing equipment in the field as well as to OEMs for new equipment sales.
In 1984, Cyberworks demonstrated the world’s first autonomous robot, one that could navigate and work in unknown areas – without any apriori teaching or map learning: The world’s first fully autonomous robot.
In the late 1980’s, Cyberworks also deployed, across Europe and in Japan, the world’s first commercial industrial autonomous cleaning robot.
In 1991, Cyberworks developed the world’s first robotically-assisted electric scooter for the disabled.
In the late 80s and 90s, Cyberworks published some of the earliest peer-reviewed scientific papers on autonomous vehicles, in leading international journals.
Today we work with global OEMs to provide next-generation, low-cost add-on autonomous navigation modules for their existing and future products.
We also fund research partnerships with several top tier universities to ensure we remain on the leading edge of autonomous vehicle technology.
Credits2 : In Cooperation with our Valued Partners at the University of Waterloo and NSERC