eduzhai > Applied Sciences > Engineering >

LAVAPilot Lightweight UAV Trajectory Planner with Situational Awareness for Embedded Autonomy to Track and Locate Radio-tags

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 8 pages

Abstract: Tracking and locating radio-tagged wildlife is a labor-intensive andtime-consuming task necessary in wildlife conservation. In this article, wefocus on the problem of achieving embedded autonomy for a resource-limitedaerial robot for the task capable of avoiding undesirable disturbances towildlife. We employ a lightweight sensor system capable of simultaneous (noisy)measurements of radio signal strength information from multiple tags forestimating object locations. We formulate a new lightweight task-basedtrajectory planning method-LAVAPilot-with a greedy evaluation strategy and avoid functional formulation to achieve situational awareness to maintain a safedistance from objects of interest. Conceptually, we embed our intuition ofmoving closer to reduce the uncertainty of measurements into LAVAPilot insteadof employing a computationally intensive information gain based planningstrategy. We employ LAVAPilot and the sensor to build a lightweight aerialrobot platform with fully embedded autonomy for jointly tracking and planningto track and locate multiple VHF radio collar tags used by conservationbiologists. Using extensive Monte Carlo simulation-based experiments,implementations on a single board compute module, and field experiments usingan aerial robot platform with multiple VHF radio collar tags, we evaluate ourjoint planning and tracking algorithms. Further, we compare our method withother information-based planning methods with and without situational awarenessto demonstrate the effectiveness of our robot executing LAVAPilot. Ourexperiments demonstrate that LAVAPilot significantly reduces (by 98.5 ) thecomputational cost of planning to enable real-time planning decisions whilstachieving similar localization accuracy of objects compared to information gainbased planning methods, albeit taking a slightly longer time to complete amission.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...