Researchers at Michigan State University in East Lansing are developing robots made with softer materials in an effort to help the robots navigate their surroundings more safely and effectively and building trust between robots and the humans they assist.
“We’re developing robots not to replace humans, but to assist humans,” says Zhaojian Li, an assistant professor in the Department of Mechanical Engineering, who is working on the project supported by a $1.5 million grant from the National Science Foundation. “We think about it as the robot is your partner. If you don’t trust your partner, you won’t work well with it.”
Li envisions a world where people work side-by-side with robots in a variety of settings, including apple orchards, operating rooms, and assisted living facilities. His team is working toward this future with its Soft Mult-Arm Robot, or SMART.
“We want our robots to understand their environment and understand the humans they’re working with,” Li says. “We want to enable robots and humans to interact and communicate without talking to each other. You want that all to be automatic.”
Li has been working with the U.S. Department of Agriculture for about 18 months to create an apple-picking prototype. It’s a rigid machine that uses a tube-like appendage and suction to pick apples.
The next generate of robots will have several softer arms that can grip independently of each other. The team plans to start with four limbs per robot, and each robot will be able to travel through tight spots in an orchard without harming trees or apples due to their softer construction.
“We want materials that can be soft enough to not hurt an apple, but that can still be stiff enough to hold onto the apple. We want to have tunable stiffness,” says Xiaobo Tan, who recently helped create soft humanoid hands for robots. “It’s not easy.” Tan is co-investigator on the grant and an adjunct professor of mechanical engineering.
The team plans to validate its robots with apple picking, but other applications for strong, soft arms include helping caregivers lift residents who have fallen in assisted living facilities. This will require training a robot to understand what a human intends to do and assist with the task as well as promote trust among the people working with robots.
Cameras, sensors, and programming will help machines anticipate how to help. Building trust on the human side will require a better understanding of the psychology of working with robots.