How does a robot decide the best navigation approach when there are multiple paths and stops? A team of researchers developed a way to determine the optimal solution to move from point A to point B and published their results in the August 2021 Issue, IEEE/CAA Journal of Automatica Sinica.
The team believes that this is the first time that a highly flexible, computationally efficient, accurate solution with the proof of optimality is presented for general optimal control problems, according to the paper’s first author Hossein Mirinejad, assistant professor in the College of Aeronautics and Engineering at Kent State University, USA.
Researchers combined two existing approaches to enable the algorithmic approach to find the direct path in control problems. The method, dubbed RBF-Galerkin, is named for the two contributing methods.
To test the method, researchers told the robot to move across a flat space containing three circles without crossing into the circles. They used three approaches to see how they might change the robot’s trajectory and found that their RBF-Galerkin method was the most cost and time efficient in three different attempts.
The researchers plan to develop an automated strategy to fine-tune the process and also to improve the overall performance of their approach by working to minimize potential errors in the initial estimations.
Original Release: Eureka Alert