Google-Owned Meka Robotics Work To Advance Human-Robot Interaction
redOrbit Staff & Wire Reports – Your Universe Online
Co-founded in 2006 by Aaron Edsinger and Jeff Weber, Meka was an early creator of “compliant” humanoid robots that now work safely alongside humans in everyday environments from factories to research labs.
Meka’s sophisticated robotics hardware includes human-sized heads, arms, hands, torsos and full-body systems with advanced control innovations such as torque control and measurements at each joint. And all of Meka’s robots run off Meka M3 and Robot Operating System software, which allows for real-time communication.
But the company’s biggest success to date is likely its M1 Mobile Manipulator – a $340,000 robotic humanoid that incorporates all of Meka’s hardware. Designed to lift and carry objects, the M1’s arms move seamlessly and are equipped with strong grippers and an advanced control system that allows the arms to slow down upon human touch. A customizable head with a Kinect 3-D camera, along with other digital cameras, is included for detecting objects. The unit’s base is an omnidirectional platform with a mechanical lift that allows the torso to move vertically.
The platform is in use by dozens of researchers today for advanced robotics research in labs throughout the world.
“These are hardware platforms for research labs to develop algorithms for mobile manipulation, social robotics, and human-robot interaction,” said Edsinger, who was Meka’s chief executive officer, in an interview with Rob Matheson of MIT’s News Office.
Google’s other recent acquisitions include MIT spinout Boston Dynamics, a military robot maker, and Redwood Robotics, a joint venture between Meka and the robotics firms Willow Garage and SRI International.
Co-founded by Edsinger, Redwood Robotics focused specifically on refining Meka’s robot arms, but has greater aims of bringing manufacturing back stateside.
“Designing arms is part of the story, but the bigger product solution is to fulfill that vision,” said Edsinger, now a robotics director at Google.
With Google’s acquisitions, Edsinger believes that robotics innovation is on the rise.
“My hope is that we’re going to see as much energy and effort pooled into robotics startups in the next 10 years as we’ve seen in social media in the last 10,” he said.
Although the technology behind Meka’s robots was considered novel just a few years ago, what distinguished the company from a burgeoning robotics landscape “was designing robots on human scale that had a focus on aesthetic packaging,” Edsinger noted.
This is perhaps best showcased in Meka’s S2 Humanoid Heads, whose expressive eyes and emotive ears were used to build “sociable” robots in collaboration with researchers across the nation.
Simon, a robot co-developed by Meka and researchers at the Georgia Institute of Technology, includes a Meka humanoid head with 13 degrees of freedom (DOF), including independently moving eyes and eyelids, movable ears, and a five-DOF neck that replicates a human’s range of motion. It also conveys nonverbal cues through lifelike head motions, eye contact, and blinking.
Simon is similar to the red-haired “Dreamer,” a head incorporated onto a robot co-developed by Meka and the University of Texas at Austin, which had seven DOF with ears that curl and bend to display emotions such as confusion and understanding. Its eyes come equipped with cameras that track movements, while its head tracks and moves in the same direction of the eyes.
Edsinger said the goal of the aesthetic designs for M1, Simon, Dreamer and the other Meka robots is to help make people feel “affinity and trust” toward robots.
Meka’s robots are also inspired from the co-founders’ time as artists, when Edsinger (who holds a bachelor’s degree in computer science from Stanford University) and Weber (a trained industrial designer) were visual artists building anthropomorphic robotic sculptures for participation in theatrical performances.
“As artists we valued aesthetics and design, and human interaction, and how these robotic systems relate to people,” Edsinger said.
“That’s the mindset we came into MIT with and learned the chops of engineering.”
In MIT’s Human Robotics Group, the duo built the Domo robot – which had 29 active DOF, sensors, Series Elastic Actuators (SEA) – integrated arms, four digital cameras and other features that allowed it to work safely alongside humans.
After graduating, and while serving as a postdoc student, Edsinger said he had an unflinching desire to launch a robotics company where he “could get out in the world and have an impact.”
Without a formal business plan, Edsinger and Weber moved to San Francisco, taking with them the knowledge they gained building Domo to found Meka.
After securing a few quick sales and contracts from researchers, Meka completed its first commercial robotic arm in about nine months. From there, the company sold parts – an arm, a hand, a head, a torso, a base – and ultimately began working with the Defense Advanced Research Projects Agency (DARPA) building underwater humanoid robots, exoskeletons, and prosthetics, among other things.
“We took an incremental bootstrapping approach,” Edsinger said. “Every sale would finance the next iteration of engineering the robot. We stayed very diligent, trying to ensure that every little step forward could scale into a bigger opportunity.”
Soon, they built the entire M1 Mobile Manipulator, “which allowed for a higher sales price,” Edsinger said.
This incremental approach is something Edsinger said he learned from the business classes he took at MIT. Another critical lesson was the importance of surrounding himself with people better than him at different aspects of technology and business.
“In robotics it’s particularly important,” he said, “because it’s so multidisciplinary you can’t possibly cover all the bases. That’s one bit of advice I’ve taken to heart over the years.”
Returning back to Meka’s founding, Edsinger said the company was initially launched to bring advanced robots to computer science labs.
“At the time,” he says, “these labs could spend years building robotic systems to test robotic algorithms, but the robots were ultimately unreliable.”
Over time, the company went from a highly self-fulfilling project to something that just happened to get big.
“Really, we just enjoyed the hard engineering and design and wanted to build cool stuff. This was a fun way to do it.”