UC Berkeley is teaching robots to ride Hovershoes
Wheeled platforms are more efficient across flat, continuous terrainsBy Shawn Knight
Through the looking glass: The ideal solution, it would seem, would be retractable wheels that come out when the robot is on flat surfaces and tuck away when obstacles like stairs are met where legs would be more efficient.
If you thought the capabilities of bipedal robots from companies like Boston Dynamics were terrifying, just wait until you get a load of what the Hybrid Robotics lab at UC Berkeley is up to.
The team of researchers has created a framework for autonomous bipedal robotic locomotion using a wheeled platform - in other words, a robot that can use InMotion Hovershoes. The framework includes a computer vision system, a path planner and a feedback control system.
The researchers note that while using legs is efficient when traveling over rough and discrete terrain, wheeled locomotion is more efficient when traveling over flat, continuous terrain.
As you'll see in the video above, lots of work went into training the robot on how to properly navigate uneven terrain, deal with obstacles and lean into corners. A patient lift was even used as a mobile fall arrest system but didn't support the robot in any way.
Found is a TechSpot feature where we share clever, funny or otherwise interesting stuff from around the web.