The SLAMcore solution is easy and cost effective for developers to implement. They can download and integrate our SDK with just a few clicks and be up and running in a matter of minutes. Working closely with our engineers, developers quickly identify how and why SLAM estimations are failing and integrate solutions that benefit from data from hundreds of previous edge-cases. This consistent frame of reference allows them to leverage and contribute to a global body of data on how robots locate and map in real-world situations. The more data added the more detailed and precise this shared map and understanding becomes.
This creates a virtuous cycle that benefits all participants. The more data collected, processed and used in this consistent framework; the better all SLAM calculations become. Robot operations improve allowing them to be used more widely and collect more data and experience more edge-cases. As data granularity and scale increases, and more edge-case solutions are found, algorithms can be tweaked to make better ‘judgement calls.’ The human mind employs many tricks of perception built on its own experience. That’s how we know that a small cow, for example, is probably further away than a larger cow. Building a common data set and language of visual perception will allow robots and autonomous machines to start to use some of these shortcuts to position, map and understand the world around them.
Crucially, just as the human brain ‘pays attention’ to a small subset of vital inputs to correctly calculate our position in space, SLAMcore's algorithms can focus on fewer data points, and use less processing and memory to create highly accurate SLAM estimations. Robots and autonomous machines using SLAMcore will be able to mimic the tricks of perception that humans and animals use naturally to make fast, accurate decisions based on limited data.
Constantly updated, shared maps have immediate and obvious applications for wide scale deployments. Fleets of robots can contribute to shared maps so that every change is noticed and passed to all those affected. Robots will learn from their peers’ experiences. Using vision, full-colour 3D maps can be shared with humans so that both they and the robots have a commonly agreed map that accurately interprets and can be verified with the world around them.
The accuracy, currency and robustness of these maps, constantly updated as every robot surveys a scene, will be the foundation of a real-time digital twin of the physical world. This will have huge benefits for those managing facilities, locations or properties providing not only real-time data on the exact state of the physical world, but the opportunity to test and simulate actions before implementing them. The universal language of spatial intelligence created by SLAMcore will not only unleash a wave of robotic innovation and deployment but could deliver significant benefits across sectors. Imagine the value and the utility of a hyper-accurate, real-time digital twin of the physical world, automatically updated and shared as every robot or autonomous device passed through.
The story of the Tower of Babel was a warning to humankind not to overreach and aspire to reach the heavens. Yet today, the opportunity exists for robots to deliver widespread, lasting and valuable contributions to the betterment of humankind. We should not be afraid of this, nor should we seek to limit the potential for robots to take on tasks that are dangerous, difficult, unrewarding or even impossible for humans to undertake. So the parallels with that story fall short. We do want robots to cooperate, to share and benefit from a common language with which to describe the physical environment around them. We want robots to cooperate with each other and to work alongside humans to find solutions to some of the world’s most pressing challenges. We want, and many would argue, need robots to help build a better world.
Robots can help solve climate change, pandemic and disaster response, care for the elderly and disabled as well as providing more cost effective and efficient ways to deliver the economics of abundance. But they can only do this if enough robots can be made and deployed cost effectively enough to move from the domain of the wealthy and privileged to become part of everyday life. This is the mission that drives us: to make quality spatial intelligence accessible to all. We do this because every autonomous machine needs to understand where it is in physical space - if we can help them do this using consistent language of shared spatial intelligence we can democratize access to robust, accurate and fast SLAM that will stimulate the growth of the whole robotics market.
By creating a new language of spatial intelligence, SLAMcore has built the foundations of a multitude of new services and applications that leverage automated understanding of physical environments to solve countless issues. Not only does this unlock broad and deep opportunities for our algorithms, but creates the necessary building blocks for an explosion in the use of robots to solve countless pressing problems and help build a better world.