photo of takashi tanaka in drone lab

Takashi Tanaka, an assistant professor in the Department of Aerospace Engineering and Engineering Mechanics at The University of Texas at Austin, received an Air Force Office of Scientific Research (AFOSR) Young Investigator Award for research that will provide new tools and insights used in path planning for autonomous decision-making systems such as ground robots and multi-drone platforms.

As part of the Air Force’s Young Investigator Research Program, the AFOSR awarded approximately $17.8 million in grants to 40 scientists and engineers who submitted winning research proposals in 2019. The program’s objective “is to foster creative basic research in science and engineering, enhance early career development of outstanding young investigators, and increase opportunities for the young investigators to recognize the Air Force mission and the related challenges in science and engineering.”

Tanaka was selected for his proposal titled “Information-Geometric Path Planning: Perception-based Motion Planning Algorithms for Highly Autonomous Systems” for which he and his research group will introduce the concept of information-geometric path planning (IGPP) and develop its theoretical algorithmic foundations.

Currently, it is challenging for robots to find “simple” solutions when it comes to path planning due to the lack of a standardized mathematical framework for “simplicity” planning. Because of this limitation, these types of operations are often controlled by humans instead of robots, which greatly restricts the autonomous capability of safety-critical missions.

Tanaka’s proposal aims to meet this challenge by developing a new mathematical framework and algorithms based on the concept of rational inattention, which was originally introduced in the economics literature. Roughly speaking, the proposed mathematical framework will allow robots to select a “simple” path plan by minimizing the expected perception cost to execute the plan.

Researchers will begin by developing a mathematical foundation for IGPP, followed by creating new algorithms using this foundation. Once the new algorithms have been developed, they will be tested using ground robots to demonstrate simultaneous perception and motion planning and drones to demonstrate coordinated path planning.

The results of this project could revolutionize current path planning methods and would be applicable to a broad range of autonomous decision-making scenarios such as Mars rover path planning and should also help researchers gain a better understanding of the difference between human and robot path planning.

Tanaka joined the department as an assistant professor in 2017. His research interests include systems and control theory, networked and multi-agent systems and information theory control. He specializes in stochastic and non-stochastic optimal control, robust control, distributed and networked control, optimization, and game theory. He is an affiliated member of the Oden Institute. Tanaka also received a DARPA Young Faculty Award to develop a new theoretic framework for predictive vision modeling. Learn more about Tanaka’s work on his research website.