Realtime Robotics, a Boston, Mass.-based startup focusing on speeding up the time a robot takes to make decisions, has secured $2 million in seed funding. Key investors in the seed round include SPARX Group Ltd., Scrum Ventures, and Toyota AI Ventures, a venture capital subsidiary of Toyota Research Institute (TRI). Realtime, founded in March 2016…
Realtime Robotics, a Boston, Mass.-based startup focusing on speeding up the time a robot takes to make decisions, has secured $2 million in seed funding. Key investors in the seed round include SPARX Group Ltd., Scrum Ventures, and Toyota AI Ventures, a venture capital subsidiary of Toyota Research Institute (TRI).
Realtime, founded in March 2016 by Duke University professors Dan Sorin and George Konidaris, has developed a motion planning processor that it claims enables robots to perform complex motion planning tasks up to 10,000 times faster than their predecessors, while using significantly less power. The company sees industrial robots and autonomous vehicles as two primary markets.
From Realtime’s website: “Realtime’s processor can plan in less than a millisecond, overcoming the primary obstacle preventing robots and autonomous vehicles from achieving their potential. Realtime’s processor will enable robots with sophisticated arms to generate collision-free motion in unstructured and dynamic environments in real time, making them useful for tasks well beyond the precise, rigid, and repetitive industrial tasks where they are currently employed.”
James Kuffner, chief technology officer of TRI, wrote a blog explaining the investment in Realtime. He equated the development of Realtime’s processor to the improvements in storage and memory technology that advanced computer graphics.
State-of-the-art algorithms for motion planning in high dimensions typically involve online sampling-based tree search, such as RRT-Connect [4]. Back in 2002, an algorithm was proposed by Leven and Hutchinson based on using large memory buffers to store precomputed mappings between environment-free space and robot configurations [5]. Unfortunately, at that time, computing systems did not have sufficient memory nor computing resources to efficiently store large enough mappings to solve interesting problems of real-world complexity.
Fast forward fifteen years, Realtime Robotics has developed a practical implementation of a variant of this technique in specialized hardware?-?exploiting recent advances in memory and computing hardware. The result is the potential to deliver incredibly efficient, real-time motion planning for complex, real-world applications. Existing modern processors typically consume 200-300 Watts of power, taking anywhere from hundreds of milliseconds to tens of seconds to compute a safe motion plan. With Realtime Robotics’ technology, that same planning decision can often be made in less than a millisecond, using less than 10 watts of power, with a six degrees of freedom robotic arm.
“We’re currently working with major multinational customers to create highly adaptable robotic systems for application to new classes of industrial tasks, many times larger than the existing robotics market,” said Realtime Robotics CEO Peter Howard. “In addition, we’re excited about the role that Realtime’s technology can play in improving the safety of emerging autonomous driving platforms, even in complex urban driving environments.”
Realtime said it is hiring roboticists and software engineers to join its founding team.
