Robots are a lot of potential to help people with reduced mobility, including models that could help disabled people to train. It is a particularly challenging task that requires dexterity, safety and speed. Now scientists with MIT CSAIL have developed an algorithm that establishes a balance by allowing harmless influences, instead of not allowing any influences as before.
Humans are wired to adapt and adapt to other humans, but robots have to learn all of this from scratch. For example, it is relatively easy for a person to help someone else get dressed because we instinctively know where to keep the garment, how people can bend their arms, how the fabric reacts, and more. However, robots must be programmed with all this information.
In the past, algorithms prevented robots from making any impact on humans in the interest of security. However, this can lead to something called a “robot freeze” problem, where the robot basically stops moving and cannot perform the task it set.
To overcome this problem, the MIT CSAIL team led by PhD student Shen Liom has developed an algorithm that redefines robotic motion safety by enabling “safe strikes” on top of collision avoidance. This allows the robot to establish harmless contact with the human in order to accomplish its task, as long as its impact on the human is low.
“Developing algorithms to prevent physical damage without unnecessarily affecting task efficiency is a crucial challenge,” Li said. “By allowing robots to exert a harmless influence on humans, our method can find effective robot trajectories to dress a human with a safety guarantee.”
For a simple dressing task, the system worked even if the person was doing other activities like checking the phone, as shown in the video above. It does this by combining multiple models for different situations, instead of relying on a single model as before. “This multifaceted approach combines set theory, human-conscious security constraints, human motion prediction, and feedback control for safe human-robot interaction,” said Zackory Erickson of Carnegie Mellon University.
Research is still at an early stage, but ideas could be used in areas other than just dressing. “This research could be applied to a wide range of assisted robotics scenarios, towards the ultimate goal of enabling robots to provide safer physical assistance to people with disabilities,” Erickson said.
All products recommended by Engadget are selected by our editorial team, regardless of our parent company. Some of our stories include associated links. If you purchase something through one of these links, we may earn an associated commission.