Engineering students from the U.S. are building a robot that can open doors and find the nearest electric wall outlet to recharge, all without help from humans.
The robot, courtesy of students out of the University of Cincinnati, is learning how to bypass that teeny tiny block in robot domination: doors.
“Robots can do many things, but if you want one to open a door by itself and go through the doorway, that’s a tremendous challenge,” said Ou Ma, an aerospace engineering professor at UC.
As detailed in a study, students from UC’s Intelligent Robotics and Autonomous Systems Laboratory have solved the door-opening problem through 3D simulations.
They’re now building an autonomous robot that not only can open its own doors but also can find the nearest electric wall outlet to recharge without human assistance. This might seem simple, but it’s a pretty big deal – robot ‘independence’ represents a huge leap forward for helper robots that vacuum and disinfect office buildings, airports and hospitals, as some examples.
UC College of Engineering and Applied Science doctoral student Yufeng Sun, the study’s lead author, said some researchers have addressed the problem by scanning an entire room to create a 3D digital model so the robot can locate a door. But that is a time-consuming custom solution that works only for the specific room that is scanned.
There’s also the added issue that doors come in different colours and sizes with different handles installed at different heights. Heck, even us humans often ‘push’ instead of ‘pull’ doors, and we have cognition.
Some engineers have mounted an arm with multiple joints on robots to grasp a knob or door handle to tackle the whole doors issue (something Spot is doing), but Ma said these can be super expensive (like, tens of thousands of dollars expensive).
The UC students solved the problem by designing an appendage on a simple motorised lift the robot can raise and lower to reach a door handle. A small arm at the base holds the door open while the robot pivots around it and carries on with its duties in the next room.
They’re using machine learning to get the robot to “teach” itself how to open doors, essentially through trial and error.
“The robot needs sufficient data or ‘experiences’ to help train it,” Sun said. “This is a big challenge for other robotic applications using AI-based approaches for accomplishing real-world tasks.”
This can be time-consuming initially, but the robot corrects its mistakes as it goes. Simulations help the robot prepare for the actual task, Sun said.
Next up is converting the successful simulation study into a real robot, to take autonomous robots to a whole new level of independence. Yikes.