Sarcos Defense has won contracts from both the US Navy and US Air Force for development of its GUARDIAN technology, the company announced in early October.
The Office of Naval Research has selected the company to develop a remote-controlled variant of the upper body of the GUARDIAN wearable exoskeleton robot. This will be adapted for attachment to a number of mobile bases to address maintenance and logistics requirements, providing strength, dexterity, precision, and versatility at human scale, enabling the robot to perform difficult tasks in dangerous environments while keeping the operator safe and out of harm’s way.
“The Navy is very focused on improving readiness rates,” said Steve McKee, Lead for the Naval Enterprise Sustainment Technologies Team (NESTT). “A key factor in achieving this objective is the deployment of new technologies that improve the turnaround time for maintenance activities, while also increasing the safety and effectiveness of our workforce. [GUARDIAN] addresses a significant gap that the Navy has identified.”
“Similar to our teleoperated GUARDIAN GT robot for heavy, dexterous work, but designed at human scale, the GUARDIAN DX robot can be teleoperated to perform intricate tasks that require human-like dexterity,” added Ben Wolff, Chairman and CEO of parent company, Sarcos Robotics. “Examples of such tasks include the use of portable sensors for non-destructive structural testing and inspections, the use of portable power tools for grinding, cutting and welding at height, as well as lifting and manipulating heavy components weighing up to 200lbs. Because the GUARDIAN DX robot is kinematically equivalent to the upper body of humans, operators are able to manage [it] intuitively at typical human speeds by relying on their reflexes, instincts, and judgment to perform complex tasks in unstructured, often hazardous environments that historically have only been able to be completed by people directly.”
The US Air Force contract calls for development of an artificial intelligence (AI) system that would enable robotic platforms to learn how to perform tasks with human-like movement through positive reinforcement and imitation machine learning (ML) technologies, known as Cybernetic Training for Autonomous Robots (CYTAR). This system furthers Sarcos’ vision of robotic systems that augment rather than replace humans by reducing the system operator’s cognitive load for basic tasks, yet still relying on human intelligence, judgement, instincts, and reflexes to manage more complex tasks.
The platform will be based on the upper body of the GUARDIAN XO wearable exoskeleton robot. Unlike many of today’s AI platforms that are characterised by a trial and error approach, Sarcos’ AI system enables human operators to teach robotic systems to perform tasks correctly the first time. Sarcos’ approach will significantly accelerate the speed and reduce the cost of deploying robotic systems that can perform meaningful work in unstructured environments.
“This is a unique opportunity to leverage a robotic system that is kinematically equivalent to the human body to lay the foundation for teaching robots how to move and accomplish tasks in the real world, the same way humans do,” said Denis Garagić, Chief Scientist, Advanced Systems and AI at Sarcos Robotics. “This success-based teaching will speed up the learning process of AI-enhanced perception, reasoning, and decision-making techniques currently being implemented across Sarcos’ platforms. Implementation of such an AI-based system will enable autonomous situational awareness, which can radically reduce the cognitive load on the operator while dramatically increasing precision as it augments human performance.”