Search and Pursuit with Unmanned Aerial Vehicles in Road Networks
Abstract
Across many rescue, surveillance, and scientific applications, there exists a broad need to perform wide-area reconnaissance and terrain surveys for which unmanned aerial vehicles (UAVs) are increasingly popular. This thesis considers the task of using one or more UAVs to locate an object of interest, provide continuous viewing, and rapidly re-acquire tracking should it be lost for any reason. For both the common class of small field-launched UAVs as well as larger UAVs, this is a difficult task due to a small available sensor field of view, uncertain estimates of UAV pose, and limited maneuverability relative to the scale of the environment, requiring constant processing of observations and recomputation of flight paths or sensor aiming to best find the object or keep it in view. Existing strategies for accomplishing this provide poor estimates of the object's location and rely on grossly heuristic or computationally intensive trajectory generation for both pursuit and search. This thesis proposes careful representation of observation uncertainty and exploitation of environmental structure -- with a particular focus on road networks typical of urban-like areas -- as a means to simplify and better model the problem. For the case of actively tracked objects, greatly improved location estimates are demonstrated through filter representations designed for high-uncertainty observations, and improved pursuit performance is achieved by modeling terrain-constrained space reduction in object location and motion. Objects having no or only a roughly known prior location require an initial search, for which both classical Bayesian probabilistic search and novel road network coverage strategies are considered. Finally, this is extended to search and local recapture of evasive adversaries in road networks through novel mappings of pursuit-evasion tactics that are well-studied in abstract or ground-based domains, but have yet to see use in aerial applications.
Document Details
- Document Type
- Technical Report
- Publication Date
- Nov 01, 2013
- Accession Number
- ADA595133
Entities
People
- Michael Dille
Organizations
- Carnegie Mellon University