Our robots are fully autonomous with intuitive interfaces to define and customize behaviors. Users monitor each robot’s progress in a purely supervisory role, as opposed to remote operation with real-time or frequent intervention.
SMART ROBOTS THAT LEARN FROM AND WORK WITH HUMANS
In our research and development of artificial intelligence solutions for robotic systems, we adhere to three core principles that define our focus on machine intelligence and embodied AI.
SUPERVISE INSTEAD OF OPERATE
Let AI out of simulators into the physical world:
The ultimate goal of AI and reinforcement learning is to train real agents to operate in today's world. OffWorld is applying years of research and patented technology to rugged hardware that can handle even the most extreme environments.
We get that offscreen environments are more complex, so we've planned for them:
At some point, the fidelity of even the best simulations becomes inadequate to prepare any robot for the real world. We can only simulate the known unknowns, which leaves unknown unknowns unexplored. We work with real systems in real environments to prepare for as many as possible.
Imprint human intelligence in robots:
Learning industrial operations is challenging for both robots and human workers alike. Humans don’t try to learn the job by trial and error, and we think robots shouldn’t either. Our approach and methodology allow human teachers to guide our robots and assist them during the learning process.
We replace hard-coded procedures with learned behaviors:
Normally, it takes a team of engineers to describe the desired industrial operation in code, and this expensive effort produces a single-purpose procedure that is inflexible to changes in the environment. Learning behaviors from human teachers saves time, engineering costs and can be modified at any time to meet new requirements and adapt to a changing environment.
LEARNING FROM HUMANS
WE IDENTIFY THE PARTS OF THE ROBOTIC PIPELINE THAT BENEFIT MOST FROM AI
Replace complex and outdated heuristics:
We break down robotic operations into subroutines and identify the ones that benefit most from artificial intelligence and imprinted human learning. We focus on the outdated and inflexible subroutines first, making sure our artificial intelligence solutions have an immediate and noticeable impact.
Blend new AI with what's tried and true:
We build on top of well-optimized existing solutions. We acknowledge that over the years, robots have discovered pioneering solutions to problems and inefficiencies. We integrate modern AI methods with well-proven and established algorithms.
Open the possibilities for what a robotic workforce is capable of:
By expanding the proficiencies of our industrial robotic workforce, we expand the range of tasks that robots can tackle and open up new applications in mining, construction, and other industries.
Elevate robotic autonomy to a whole new level:
Solutions that are based on AI are by design more adaptable and robust to changes in the environment, unknown situations, and unforeseen challenges. A higher level of autonomy and reduced human involvement opens up the possibility of deploying a robotic workforce in extreme and remote environments on any surface.