Aquatic drones can run into challenges in extreme circumstances.
Lantao Liu, an assistant professor of intelligent systems engineering at the Luddy School of Informatics, Computing, and Engineering, has been awarded a grant from the National Science Foundation to study the interrelationship between model symmetries and various performances of decision-theoretic planning, which can directly affect the accuracy and efficiency of autonomous robots’ basic motion and coordination.
The project, “Exploiting Symmetries of Decision-Theoretic Planning for Autonomous Vehicles,” will enhance the resilience to extreme disturbances in unstructured environments for autonomous vehicles. Improving the autonomy and intelligence of the vehicles will expand the capabilities of mobile robot platforms that perform challenging outdoor missions such as environmental monitoring and surveillance; search and rescue; and other tasks.
“Many field robots, such as drones and underwater robots, need to commit tasks in harsh natural environments which can cause significant disturbances including those from strong air or water flows,” Liu said. “In the presence of strong disturbances, the robot motion outcome can become extremely uncertain. Without an effective way to deal with the uncertainty, robots can easily drift from planned navigation paths, causing unwanted or even catastrophic behaviors.”
The project aims at making breakthroughs in artificial intelligence planning theories that directly affect the basic motion and coordination capabilities of autonomous robots.
“An important focus of this research is to gain a deeper understanding of the interrelationship between mathematical ‘symmetries’ and various performance characteristics in modeling robot decision making,” Liu said. “This research is based on the intuition that autonomous systems acting in real-world environments follow physics laws, and many systems studied in physics show some form of symmetry. Model symmetries in planning, decision making, and multi-agent coordination domains can be immensely beneficial for designing efficient solving mechanisms to tackle problems with large computational and communication complexities.”
The $450,000 grant will support graduate students who are working on aerial and underwater drones, and the newly constructed Vehicle Autonomy and Intelligence Lab at the Luddy School will provide the space for recently developed algorithms to be tested.
“Autonomous vehicles are an expanding frontier in technology, and they’re going to play a critical role in so many areas going forward,” said Dennis Groth, interim dean of the Luddy School. “The research being conducted at VAIL is giving our school a leadership role in this key area, and this support from the NSF is important to furthering our understanding of how we can get the most out of aerial and underwater drones.”