Engineers in the US are developing a robot that can open doors and can find the nearest electric wall outlet to recharge without human help.
To tackle this, students in UC’s Intelligent Robotics and Autonomous Systems Laboratory have solved this complex problem in three-dimensional (3D) digital simulations and are building an autonomous robot to demonstrate this.
According to its developers, this simple advance in independence represents a huge leap forward for helper robots that vacuum and disinfect office buildings, airports, and hospitals. Helper robots are part of a $27bn (£20bn) robotics industry, which includes manufacturing and automation.
UC College of Engineering and Applied Science doctoral student Yufeng Sun 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 this is a time-consuming custom solution that works only for the particular room that is scanned.
According to Sun, developing an autonomous robot to open a door for itself poses several challenges.
Since UC students are using machine learning, the robot has to ‘teach’ itself how to open a door, through trial and error. 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.
Sun and UC master’s student Sam King are currently converting Sun’s simulation study into a real robot. “The challenge is how to transfer this learned control policy from simulation to reality, often referred to as a ‘Sim2Real’ problem,” Sun explained.
According to Sun, digital simulations typically are only 60 to 70 per cent successful in initial real-world simulations. He expects to spend a year or more bridging the gap to perfect his new autonomous robotic system.