Occlusion-Aware Ground Target Tracking by a Dubins Vehicle using Visibility Volumes
Collin Hague, Artur Wolek

TL;DR
This paper introduces a method for UAV ground target tracking in urban environments using visibility volumes to account for occlusions, with a control strategy to maintain a standoff orbit around the target.
Contribution
It develops a visibility volume framework and a feasible control approach for Dubins UAVs to track ground targets despite occlusions in complex environments.
Findings
The proposed method effectively maintains target tracking in occluded urban settings.
Numerical simulations and flight tests validate the approach's practicality.
The approach ensures the UAV follows a feasible, time-varying standoff orbit.
Abstract
This paper considers the problem of tracking a point of interest (POI) moving along a known trajectory on the ground with an uncrewed aerial vehicle (UAV) modeled as a Dubins vehicle using a line-of-sight (LOS) sensor through an urban environment that may occlude the POI. A visibility volume (VV) encodes a time-varying, three-dimensional representation of the sensing constraints for a particular POI position. A constant-altitude, translating, and radially time-varying circular standoff orbit is then inscribed within the dynamically changing VV centered at the POI position. The time-varying VV is approximated by placing static VVs along the POI's trajectory using an adaptive metric that restricts the volume change of consecutive VVs to below a specified rate. The time-varying circular standoff orbit is proven to be feasible for a Dubins vehicle and approximated with a piecewise set of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSpacecraft Dynamics and Control · Distributed Control Multi-Agent Systems · Guidance and Control Systems
MethodsSparse Evolutionary Training
