Deep Learning for Exploration and Recovery of Uncharted and Dynamic Targets from UAV-like Vision

William Andrew, Colin Greatwood, Tilo Burghardt

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

2 Citations (Scopus)
387 Downloads (Pure)

Abstract

This paper discusses deep learning for solving static and dynamic search and recovery tasks – such as the retrieval of all instances of actively moving targets – based on partial-view Unmanned Aerial Vehicle (UAV)-like sensing. In particular, we demonstrate that abstracted tactic and strategic explorational agency can be implemented effectively via a single deep network that optimises in unity: the mapping of sensory inputs and positional history towards navigational actions. We propose a dual-stream classification paradigm that integrates one Convolutional Neural Network (CNN) for sensory processing with a second one for interpreting an evolving long-term map memory. In order to learn effective search behaviours given agent location and agent-centric sensory inputs, we train this design against 400k+ optimal navigational decision samples from each set of static and dynamic evolutions for different multi-target behaviour classes. We quantify recovery performance across an extensive range of scenarios; including probabilistic placement and dynamics, as well as fully random target walks and herd-inspired behaviours. Detailed results comparisons show that our design can outperform naïve, independent stream and off-the-shelf DRQN solutions. We conclude that the proposed dual-stream architecture can provide a unified, rationally motivated and effective architecture for solving online search tasks in dynamic, multi-target environments. With this paper we publish 3 3 Source code available at: https://data.bris.ac.uk/data and https://github.com/CWOA/GTRF key source code and associated models.
Original languageEnglish
Title of host publication2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1124-1131
Number of pages8
ISBN (Electronic)9781538680940
ISBN (Print)9781538680957
DOIs
Publication statusPublished - Jan 2019

Publication series

Name
ISSN (Print)2153-0858

Keywords

  • Navigation
  • robot sensing systems
  • task analysis
  • history
  • visualisation
  • vehicle dynamics
  • Reinforcement Learning

Fingerprint Dive into the research topics of 'Deep Learning for Exploration and Recovery of Uncharted and Dynamic Targets from UAV-like Vision'. Together they form a unique fingerprint.

  • Student Theses

    Visual Biometric Processes for Collective Identification of Individual Friesian Cattle

    Author: Andrew, W., 7 May 2019

    Supervisor: Burghardt, T. (Supervisor), Greatwood, C. (Supervisor) & Richards, A. (Supervisor)

    Student thesis: Doctoral ThesisDoctor of Philosophy (PhD)

    File

    Cite this

    Andrew, W., Greatwood, C., & Burghardt, T. (2019). Deep Learning for Exploration and Recovery of Uncharted and Dynamic Targets from UAV-like Vision. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018) (pp. 1124-1131). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IROS.2018.8593751