Bipedal robot that can haul 40-pound packages aims for last mile

Agility Robotics has developed its robot models to be able to pick up packages and is working with Ford

Agility's new robot, Digit [Credit: Agility Robotics]

The new bipedal robot, named Digit, is equipped with two arms and a suite of sensors. Agility Robotics said in a release that the robot’s arms are able to move in four degrees-of-freedom (4-DOF) meaning it can pick up and stack boxes up and stack boxes weighing up to 40 lb (18 kg) and can catch itself during a fall.

Two multi-core CPUs alongside the systems sensors allow the robot to address traditionally difficult traversal challenges, such as stair climbing, and to plan out where it needs to step.

The company claims that within five minutes users can get the robot out of the box and get it working but given that it is still in testing this seems like a bold claim.

Agility Robotics is partnering with Ford, which envisions the robots as being a potential solution for how to get packages from autonomous vehicles to customers homes, completely taking humans out of the equation for most deliveries.

Agility will announce Digit pricing mid-year, with deliveries beginning Q1 2020.

“For us,” said Dr. Jonathan Hurst, CTO and co-founder of Agility, “arms are simultaneously a tool for moving through the world - think getting up after a fall, waving your arms for balance, or pushing open a door - while also being useful for manipulating or carrying objects.” These new capabilities are important when moving through complex, human-oriented environments, for tasks such as curb-to-doorstep delivery.

Out-of-the-box, Digit will be up and walking within five minutes, even for users who are not legged locomotion control researchers. “We developed Digit for the much larger audience of users who wish to explore broader applications that are enabled through legged mobility, rather than focusing only on the mobility itself’” said Dr. Damion Shelton, CEO and co-founder of Agility.

 

 

comments powered by Disqus