While exoskeletons have proved incredibly useful in recent years by enabling people with disabilities to move around more easily, they still have some drawbacks. A research team at the University of Waterloo in Canada is looking to address these issues by integrating smart cameras and AI into the technology.

If you’re not familiar with these devices, exoskeletons are essentially wearable robots that can help amplify the user’s capabilities. One of the main limitations of this science fiction-like tech is that it typically requires the wearer to manually switch between different modes when it comes to performing more complicated tasks than walking, such as climbing stairs, or passing over obstacles.

“That can be inconvenient and cognitively demanding,” says Brokoslaw Laschowski, the lead researcher of the study. “Every time you want to perform a new locomotor activity, you have to stop, take out your smartphone and select the desired mode.”

To make things easier, Laschowski and his colleagues started equipping exoskeleton users with wireless video cameras, the output of which could be analyzed with AI-based software. By analyzing the camera footage in real-time, the software was able to identify stairs that have to be climbed as well as other obstacles.

The research team now plans to work on fully integrating the software into the exoskeleton so it helps move the user accordingly without them having to tell it to do so. “Our control approach wouldn’t necessarily require human thought,” explains Laschowski. “Similar to autonomous cars that drive themselves, we’re designing autonomous exoskeletons that walk for themselves.”