stub Autonomous Robot Finds and Opens Doors While Recharging Itself - Unite.AI
Connect with us

Robotics

Autonomous Robot Finds and Opens Doors While Recharging Itself

Published

 on

A team of engineering students at the University of Cincinnati are building an autonomous robot that can open its own doors and find the nearest electrical wall outlet, which enables it to recharge without human assistance.

The new study was published in the journal IEEE Access

Doors – A Robot’s Kryptonite

One of the biggest obstacles for robots is doors. 

Ou Ma is an aerospace engineering professor at the University of Cincinnati. 

“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,” Ma said.

The team was able to overcome this problem in three-dimensional digital simulations, and it is a major step forward for helper robots. These robots can include those that vacuum and disinfect office buildings, airports, and hospitals. They make up a large part of the $27 billion robotics industry. 

Yufeng Sun is the study’s lead author and a UC College of Engineering and Applied Science doctoral student. 

According to Sun, some researchers have worked around this problem by scanning an entire room to create a 3D digital model, which enables a robot to locate a door. However, this is a time-consuming solution that is only applicable to the room being scanned. 

There are many challenges to developing an autonomous robot to open a door itself. First, they come in different colors and sizes, and they have different handles that could be lower or higher. Robots are also required to know how much force to use to open doors to overcome resistance. Since many public doors are self-closing, a robot can lose its grip and be required to start over.

An Autonomous Robot for Self-Closing Door Opening

Using Machine Learning

Through the use of machine learning, the UC students enabled the robot to “teach” itself how to open a door through trial and error. This means the robot corrects its mistakes as it goes, and simulations help it prepare for the actual task.

“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.” 

Sun and UC master’s student Sam King are now converting the successful 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 said.

Another challenge is that digital simulations are usually only 60% to 70% successful in the initial real-world applications, so Sun plans to spend at least a year perfecting the new autonomous robotics system. 

Alex McFarland is a tech writer who covers the latest developments in artificial intelligence. He has worked with AI startups and publications across the globe.