Robots can learn from their mistakes in real-time

Robots and other artificial intelligences can already learn from their mistakes, but they typically have to pause what they're doing to process what happened. They might not have to take a break in the future, though. Researchers have patented a technique, Integral Reinforcement Learning, that has devices continuously refining their actions based on each previous decision. If a machine doesn't already know the optimal way to handle a task, it can keep walking through the scenario (whether by predicting the outcome or actually trying) until it gets things right.

The approach could be useful for just about any computing task where constant optimization is important, such as autopilot systems or your car's emission controls. However, it might be most useful in robotics. Many robots don't adapt well to unexpected conditions -- this technology could help them improvise and otherwise make the best of a bad situation. No matter where the invention ends up, it's safe to say that autonomous devices will be both smarter and more efficient while they're at work.

[Image credit: University of Texas at Arlington]