Publication | Closed Access
360‐degree visual detection and target tracking on an autonomous surface vehicle
64
Citations
16
References
2010
Year
Caracas/savant SystemBehavior AutonomyEngineeringField RoboticsAutonomous SystemsAutonomous Surface VehicleImage AnalysisIntelligent Autonomous SystemsAutonomous VehiclesRov ObservationSystems EngineeringObject TrackingIntegrated SystemMachine VisionUnderwater RoboticsAutonomous Underwater VehiclesMoving Object TrackingUnderwater RobotAutonomous NavigationComputer VisionVisual DetectionUnderwater VehicleAerospace EngineeringSurface RoboticsRoboticsTracking SystemMarine Surveillance
The Jet Propulsion Laboratory’s CARACaS system integrates sensing, planning, and autonomous behavior for maritime missions. The paper describes the perception and planning systems of an autonomous sea surface vehicle designed to detect and track other vessels at medium to long ranges and determine if they are adversarial, focusing on the SAVAnT system that processes omnidirectional camera images to identify and probabilistically track objects even when they exit the sensor range. The system operates in two patrol scenarios: a harbor patrol that scans for vessels near a fixed asset on each pass, and a circular patrol that intercepts approaching vessels around a fixed asset, using the SAVAnT perception module to process omnidirectional camera data and track objects probabilistically. The integrated CARACaS/SAVAnT system was implemented on U.S. Navy experimental ASVs and demonstrated in on‑water field trials.
Abstract This paper describes perception and planning systems of an autonomous sea surface vehicle (ASV) whose goal is to detect and track other vessels at medium to long ranges and execute responses to determine whether the vessel is adversarial. The Jet Propulsion Laboratory (JPL) has developed a tightly integrated system called CARACaS (Control Architecture for Robotic Agent Command and Sensing) that blends the sensing, planning, and behavior autonomy necessary for such missions. Two patrol scenarios are addressed here: one in which the ASV patrols a large harbor region and checks for vessels near a fixed asset on each pass and one in which the ASV circles a fixed asset and intercepts approaching vessels. This paper focuses on the ASV's central perception and situation awareness system, dubbed Surface Autonomous Visual Analysis and Tracking (SAVAnT), which receives images from an omnidirectional camera head, identifies objects of interest in these images, and probabilistically tracks the objects' presence over time, even as they may exist outside of the vehicle's sensor range. The integrated CARACaS/SAVAnT system has been implemented on U.S. Navy experimental ASVs and tested in on‐water field demonstrations. © 2010 Wiley Periodicals, Inc.
| Year | Citations | |
|---|---|---|
Page 1
Page 1