Adaptive Multi-Sensor Fusion Based Object Tracking for Autonomous Urban Air Mobility Operations
Authors:
- Thomas LombaertsTLThomas Lombaerts
- Gordon KellerGKGordon Keller
- Vahram StepanyanVSVahram Stepanyan
- Vanessa V. AubuchonVAVanessa V. Aubuchon
- Kelley E. HashemiKHKelley E. Hashemi
- R. J. ShivelyRSR. J. Shively
- Jacob M. WishartJWJacob M. Wishart
- Chester DolphCDChester Dolph
- Evan KawamuraEKEvan Kawamura
- 3 January 2022
- conference paper
- Published by American Institute of Aeronautics and Astronautics (AIAA)
Abstract
View Video Presentation: https://doi.org/10.2514/6.2022-0362.vid Autonomous operations are a crucial aspect in the context of Urban Air Mobility and other emerging aviation markets. In order to enable this autonomy, systems must be able to build independently an accurate and detailed understanding of the own vehicle state as well as the surrounding environment, this includes detecting and avoiding moving objects in the sky, which can be cooperative (aircraft, UAM vehicles, etc.) as well as noncooperative (smaller drones, birds, ...). This paper focuses on the object tracking part that relies on adaptive multi-sensor fusion, taking into account specific properties and limitations of different sensor types. Results show the impact of dropouts of individual sensors on the accuracy of the tracking results for this adaptive sensor fusion approach.Keywords
This publication has 9 references indexed in Scilit:
- Survey of Capabilities and Gaps in External Perception Sensors for Autonomous Urban Air Mobility Applications2021
- 3D object tracking in driving environment: A short review and a benchmark dataset2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Microsoft COCO: Common Objects in Context2014
- Autonomous driving in urban environments: Boss and the Urban ChallengeJournal of Field Robotics, 2008
- Model Based Vehicle Tracking for Autonomous Driving in Urban Environments2008
- Visual Tracking of a Maneuvering TargetJournal of Guidance, Control, and Dynamics, 2008
- Airborne Multisensor Tracking for Autonomous Collision Avoidance2006
- Multiple hypothesis tracking for multiple target trackingIEEE Aerospace and Electronic Systems Magazine, 2004