While robots can quickly perform recurrent tasks such as the installation of parts, one person cope better with complex actions that require flexibility and accuracy. However, human unpredictability can create risky situations in which standard robot algorithms do not always cope. The new development solves this problem.
Researchers from the University of Colorado used the approaches of game theory to create algorithms that help robots to choose optimal actions under uncertainty conditions. Algorithms take into account the possibility of human errors and help the robot to minimize potential damage while performing their tasks.
The approach is based on the concept of iştir reflection on regret ”. The robot evaluates and tries to avoid which actions can lead to negative consequences for a person or task itself. Thus, the robot not only completes the job, but also safe for others.
For example, on a car line, if a robot makes a mistake during assembly, it can adjust a person’s actions or move the part to a safe place to complete the task. Like a chess player, the robot puts a few steps forward to a person’s possible actions to prevent dangerous situations.
The aim of algorithms is not to fully predict the behavior of a person, but to create a system in which people’s safety is a priority. The robot should adapt to a person, not the opposite. This approach allows the use of robots with people with any skill levels from newcomers to experts.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
