Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Active Sensing for Search and Tracking: A Review

Luca Varotto, Angelo Cenedese, Andrea Cavallaro

TL;DR

The main elements of APE are defined to systematically classify and critically discuss the state of the art in this domain and a reference framework is proposed as a formalism to classify APE-related solutions.

Abstract

Active Position Estimation (APE) is the task of localizing one or more targets using one or more sensing platforms. APE is a key task for search and rescue missions, wildlife monitoring, source term estimation, and collaborative mobile robotics. Success in APE depends on the level of cooperation of the sensing platforms, their number, their degrees of freedom and the quality of the information gathered. APE control laws enable active sensing by satisfying either pure-exploitative or pure-explorative criteria. The former minimizes the uncertainty on position estimation; whereas the latter drives the platform closer to its task completion. In this paper, we define the main elements of APE to systematically classify and critically discuss the state of the art in this domain. We also propose a reference framework as a formalism to classify APE-related solutions. Overall, this survey explores the principal challenges and envisages the main research directions in the field of autonomous perception systems for localization tasks. It is also beneficial to promote the development of robust active sensing methods for search and tracking applications.

Active Sensing for Search and Tracking: A Review

TL;DR

The main elements of APE are defined to systematically classify and critically discuss the state of the art in this domain and a reference framework is proposed as a formalism to classify APE-related solutions.

Abstract

Active Position Estimation (APE) is the task of localizing one or more targets using one or more sensing platforms. APE is a key task for search and rescue missions, wildlife monitoring, source term estimation, and collaborative mobile robotics. Success in APE depends on the level of cooperation of the sensing platforms, their number, their degrees of freedom and the quality of the information gathered. APE control laws enable active sensing by satisfying either pure-exploitative or pure-explorative criteria. The former minimizes the uncertainty on position estimation; whereas the latter drives the platform closer to its task completion. In this paper, we define the main elements of APE to systematically classify and critically discuss the state of the art in this domain. We also propose a reference framework as a formalism to classify APE-related solutions. Overall, this survey explores the principal challenges and envisages the main research directions in the field of autonomous perception systems for localization tasks. It is also beneficial to promote the development of robust active sensing methods for search and tracking applications.
Paper Structure (43 sections, 40 equations, 3 figures, 5 tables)

This paper contains 43 sections, 40 equations, 3 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Active Position Estimation
  3. The targets
  4. The sensing platforms
  5. Active Search and Probabilistic Target Search
  6. Active Localization and Tracking
  7. Search and Tracking
  8. The sensing units
  9. The observation model
  10. Probabilistic map
  11. Perceiving passive targets
  12. Perceiving active targets
  13. Discussion
  14. Multi-Sensor APE
  15. Uni-modal and multi-modal MS-APE
  16. ...and 28 more sections

Figures (3)

  • Figure 1: Generic APE scheme: different targets properties require different APE algorithms and, therefore, sensing platforms with specific requirements (Sec. \ref{['sec:APE']}). Perception modules (Sec. \ref{['sec:sensing']}), on-board data management and multi-agent coordination (Sec. \ref{['sec:info_fusion']}), and platform control (Sec. \ref{['sec:dynamics']}-\ref{['subsec:criteria']}) are the most important aspects to be considered in the design of any APE mission.
  • Figure 2: POD of a visual sensor furukawa2012autonomous: the camera can not detect any object outside the FoV, while the detection capabilities are maximized at the center of the sensing domain. An object is unlikely to be recognized when too far or too close to the camera, due to scale and resolution issues.
  • Figure 3: MS-APE classification according to the number of platforms and the sensors heterogeneity.