Team develops versatile knee exoskeletons for safer lifting

A set of knee exoskeletons, built with commercially available knee braces and drone motors at the University of Michigan, has been shown to help counteract fatigue in lifting and carrying tasks. They helped users maintain a better lifting posture even when tired, a key factor in defending against on-the-job injuries, say the researchers of a new paper published in the journal Science Robotics.

“Rather than directly bracing the back and giving up on proper lifting form, we strengthen the legs to maintain it,” said Robert Gregg, U-M professor of robotics and corresponding author of the study. “This differs from what’s more commonly done in industry.”

Already, workers who lift regularly, such as in construction and manufacturing, may use back braces. Back exoskeletons, which use springs or motors to help with lifting, are an emerging technology. But devices supporting the back assume unsafe lifting, or stooping, and back exoskeletons tend to be cumbersome devices that must be deactivated to allow motions that aren’t part of the lifting task, Gregg said.

The Michigan team says their knee exoskeletons are the first to support the quadriceps muscles instead, which provide the bulk of the force in safe squat lifting, as a less intrusive way to help protect workers from back injuries. Study participants tested them out with lifting and carrying tasks using a 20-pound kettlebell.

The tasks included lifting the weight off the ground and setting it down again, and lifting and carrying the weight on flat ground, up and down an incline, and up and down stairs. The study found that after becoming fatigued, the participants kept better posture with the help of the exoskeleton, and they also lifted faster—just 1% slower than their pre-fatigued paces, versus 44% slower without the aid of the exoskeletons.

“This is especially important when a worker has to keep up with a conveyor belt. Usually, when a worker is fatigued, they’ll keep up with that rate, but with a compromised posture. They’ll bend their back more, and that’s when injuries are most likely,” said Nikhil Divekar, a postdoctoral research fellow in robotics at U-M and first author of the study.

The participants felt the benefit, too—they mainly said they were quite or very satisfied, with the exception of walking on level ground, with which they were more or less satisfied. This tracks with the small amount of assistance required by the quadriceps during this relatively easy task; Gregg described it as just enough support to counteract the weight of the exoskeleton.

One of the keys to making the exoskeleton so wearable is the motors and the way that they are geared, which enables users to swing their knees freely for a natural gait. The other is the software, which predicts what kind of assistance the user needs by measuring the angle of the knee joint, the orientations of the thigh and lower leg, and the force picked up by a sensor in the user’s shoe.

With these three measurements from both legs, it’s possible to work out what motion the user is trying to make, and how much assistance to give. These measurements were taken 150 times per second, enabling the exoskeletons to move seamlessly between activities.

This approach is in contrast to many exoskeleton controllers, which follow predefined patterns for a limited set of tasks. Switching tasks can be a problem for these controllers, and they may need a full second to figure out what the user is trying to do, Gregg said.

“If your exo is trying to walk upstairs, and you’re trying to walk downstairs, that could be a problem, right?” he said.

The new controller also pairs a physics model with machine learning, which prevents the exoskeleton from making unexpected moves if the user begins behaving differently than any activity included in the controller’s training data.

The lab prototypes cost about $4,000 per pair, so Gregg anticipates that if the exoskeletons were produced at scale, they might cost about $2,000 per pair.

The 10 study participants, five women and five men, did all the tasks on two different days, one day fresh and the other fatigued. To induce fatigue, each participant performed a series of squat lifts with the kettlebell until they couldn’t continue without a long break between repetitions. All participants had experience with proper squat lifting techniques.

The team has applied for patent protection with the assistance of U-M Innovation Partnerships and is seeking partners to bring the technology to market.

A set of knee exoskeletons, built with commercially available knee braces and drone motors at the University of Michigan, has been shown to help counteract fatigue in lifting and carrying tasks. They helped users maintain a better lifting posture even when tired, a key factor in defending against on-the-job injuries, say the researchers of a new paper published in the journal Science Robotics.

“Rather than directly bracing the back and giving up on proper lifting form, we strengthen the legs to maintain it,” said Robert Gregg, U-M professor of robotics and corresponding author of the study. “This differs from what’s more commonly done in industry.”

Already, workers who lift regularly, such as in construction and manufacturing, may use back braces. Back exoskeletons, which use springs or motors to help with lifting, are an emerging technology. But devices supporting the back assume unsafe lifting, or stooping, and back exoskeletons tend to be cumbersome devices that must be deactivated to allow motions that aren’t part of the lifting task, Gregg said.

The Michigan team says their knee exoskeletons are the first to support the quadriceps muscles instead, which provide the bulk of the force in safe squat lifting, as a less intrusive way to help protect workers from back injuries. Study participants tested them out with lifting and carrying tasks using a 20-pound kettlebell.

The tasks included lifting the weight off the ground and setting it down again, and lifting and carrying the weight on flat ground, up and down an incline, and up and down stairs. The study found that after becoming fatigued, the participants kept better posture with the help of the exoskeleton, and they also lifted faster—just 1% slower than their pre-fatigued paces, versus 44% slower without the aid of the exoskeletons.

“This is especially important when a worker has to keep up with a conveyor belt. Usually, when a worker is fatigued, they’ll keep up with that rate, but with a compromised posture. They’ll bend their back more, and that’s when injuries are most likely,” said Nikhil Divekar, a postdoctoral research fellow in robotics at U-M and first author of the study.

The participants felt the benefit, too—they mainly said they were quite or very satisfied, with the exception of walking on level ground, with which they were more or less satisfied. This tracks with the small amount of assistance required by the quadriceps during this relatively easy task; Gregg described it as just enough support to counteract the weight of the exoskeleton.

One of the keys to making the exoskeleton so wearable is the motors and the way that they are geared, which enables users to swing their knees freely for a natural gait. The other is the software, which predicts what kind of assistance the user needs by measuring the angle of the knee joint, the orientations of the thigh and lower leg, and the force picked up by a sensor in the user’s shoe.

With these three measurements from both legs, it’s possible to work out what motion the user is trying to make, and how much assistance to give. These measurements were taken 150 times per second, enabling the exoskeletons to move seamlessly between activities.

This approach is in contrast to many exoskeleton controllers, which follow predefined patterns for a limited set of tasks. Switching tasks can be a problem for these controllers, and they may need a full second to figure out what the user is trying to do, Gregg said.

“If your exo is trying to walk upstairs, and you’re trying to walk downstairs, that could be a problem, right?” he said.

The new controller also pairs a physics model with machine learning, which prevents the exoskeleton from making unexpected moves if the user begins behaving differently than any activity included in the controller’s training data.

The lab prototypes cost about $4,000 per pair, so Gregg anticipates that if the exoskeletons were produced at scale, they might cost about $2,000 per pair.

The 10 study participants, five women and five men, did all the tasks on two different days, one day fresh and the other fatigued. To induce fatigue, each participant performed a series of squat lifts with the kettlebell until they couldn’t continue without a long break between repetitions. All participants had experience with proper squat lifting techniques.

The team has applied for patent protection with the assistance of U-M Innovation Partnerships and is seeking partners to bring the technology to market.