At the end of a winding back hallway on the first floor of Atanasoff Hall, an unassuming, locked door leads to a space filled with cutting-edge possibilities: the ISU computer science robotics lab.
The lab is currently home to two highly advanced legged humanoid robots. One stands about the height of an average adult while the other is roughly as tall as a typical 10-year-old. A quadruped robot with dog-like attributes sits obediently nearby.
This is where Bowen Weng, roboticist and assistant professor of computer science at Iowa State University, and a group of graduate student researchers are working to safely advance the physical capabilities of robots.
“As humans, we often take our physical intelligence for granted because it becomes so automatic when we’re still young,” Weng says. “But the truth is, it’s remarkable.”
Human coordination and motor skills develop throughout early childhood, and it doesn’t take long for these abilities — also known as physical intelligence — to become second nature for most people, including deceptively complex actions such as walking, grasping objects, and navigating our way across a room.
“Once humans master a skill, the physical intelligence needed to perform that skill becomes a background process, and our minds are freed up to focus on other tasks,” Weng says.
Humanoid robots are designed with a body shape that resembles the human form and are built to interact with human environments and tools, setting them apart from other robots. However, tasks that are largely intuitive in humans are notoriously difficult to replicate in machines.
“Humanoid robots struggle with physical intelligence because it requires adapting to unpredictable environments, integrating sensory feedback in real time, and mastering complex motor skills,” Weng says.
In the lab, Weng and team use computer software and hand-held controllers to take the humanoid robots through commands to stand up from a lying position, sit down, walk, turn around, wave their arms, and shake hands. Their research is focused on enhancing test algorithms for specific capabilities that can one day be used for humanoid robots and support their safe interaction with humans.
“Mobile robots that feature limbed structures — particularly legs — are becoming increasingly relevant because of how versatile and adaptable they can be across many different environments and applications,” Weng says.
Legged robotic systems have shown significant promise in a variety of areas, he adds, from assisting with repetitive assembly and heavy lifting in manufacturing to providing enhanced mobility solutions in health care, navigating rubble during dangerous search and rescue missions, and entering hazardous environments that are unsafe for humans.
Zaid Mahboob, a doctoral student in computer science who is working with Weng, says the goal is to create collaboration, not competition, between humans and humanoid robots.
“We want to help improve the precision, accuracy, and speed of the robots so they can safely and effectively collaborate with humans,” Mahboob says.
Yuija Chen, a doctoral student in computer science, says the opportunity to conduct research using real robots was an important part of her decision to come to Iowa State.
“Most of the robotics labs are just interested in simulation and that kind of thing, but in [the Iowa State] lab, we are conducting real experiments using real robots to get real data,” Chen says.
Weng says humanoid robots still face hurdles to widespread adoption, including high development and unit costs, infrastructure gaps and limited use cases, and social and ethical challenges. These barriers make ongoing research to improve the safety and efficacy of robots even more important.
“The bottom line is, you have to be able to trust it,” Weng says, “and the path to proving the trustworthiness of humanoid robots is through human-led research.”
