MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) researchers have developed a new algorithm to help a robot find efficient motion plans to ensure physical safety of its human counterpart. Whether it be putting a jacket on a human or another garment, this could potentially prove to be a powerful tool in expanding assistance for those with disabilities or limited mobility. Read more for a video and additional information.
If this does become a commercially viable installation, a robot shipped to a person at home could be pre-programmed with a very narrow, “default” model of how one could interact with it during an assisted dressing task. The algorithm would then determine the uncertainty in the human model and then refine its algorithm rather than have just a single, default model where it only understands one potential reaction.
- Robotic arm Wired controlled can rotate, grab objects, and even move them!
- This stem robot has an extensive range of motion through all pivot points.
- Five motors power five joints for optimal control, movement, and fun!
Developing algorithms to prevent physical harm without unnecessarily impacting the task efficiency is a critical challenge. By allowing robots to make non-harmful impact with humans, our method can find efficient robot trajectories to dress the human with a safety guarantee,” said Shen Li, MIT PhD student and a lead author on a new paper about the research.