Task 010 - Self-flying Drones and Visual Analytics

Abstract:

Traditional approaches for active mapping focus on building geometric maps. For most real-world applications, however, actionable information is related to semantically meaningful objects in the environment. We propose an approach to the active metric-semantic mapping problem that enables multiple heterogeneous robots to collaboratively build a map of the environment. The robots actively explore to minimize the uncertainties in both semantic (object classification) and geometric (object modeling) information. We represent the environment using informative but sparse object models, each consisting of a basic shape and a semantic class label, and characterize uncertainties empirically using a large amount of real-world data. Given a prior map, we use this model to select actions for each robot to minimize uncertainties. The performance of our algorithm is demonstrated through multi-robot experiments in diverse real-world environments. The proposed framework is applicable to a wide range of real-world problems, such as precision agriculture, infrastructure inspection, and asset mapping in factories.

 

Bio:

Xu Liu is a Ph.D. student in Mechanical Engineering and Applied Mechanics at the GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA. He is advised by Dr. Vijay Kumar. His research focuses on developing long-range autonomous UAV navigation and multi-robot semantic mapping systems for large-scale, unstructured, cluttered, GPS-denied 3-D environments, and applying them to solve real-world problems such as precision agriculture and infrastructure inspection. Xu Liu received an M.S.E. degree in Robotics from the University of Pennsylvania, Philadelphia, PA, USA, in 2019. Contact him at liuxu@seas.upenn.edu.