A Human-in-the-Loop Evaluation of ACAS Xu

被引:3
|
作者
Rorie, R. Conrad [1 ]
Smith, Casey [1 ]
Sadler, Garrett [2 ]
Monk, Kevin J. [1 ]
Tyson, Terence L. [1 ]
Keeler, Jillian [1 ]
机构
[1] NASA, Ames Res Ctr, Human Syst Div, Moffett Field, CA 94035 USA
[2] San Jose State Univ, Human Syst Div, Moffett Field, CA USA
关键词
unmanned aircraft systems; detect and avoid; collision avoidance;
D O I
10.1109/dasc50938.2020.9256618
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
Detect and avoid (DAA) systems provide unmanned aircraft systems (UAS) with an alternative means of compliance with the see-and-avoid requirements associated with operations in the National Airspace System (NAS). Previous studies have examined the efficacy of different DAA alerting and guidance structures and formats. Prior research has also investigated the integration of DAA information with the alerting and guidance generated by the Traffic Alert and Collision Avoidance System (TCAS II). The next-generation replacement for TCAS II - the Airborne Collision Avoidance System X (ACAS X) - includes a variant to be used by UAS (ACAS Xu) that will provide both DAA and Collision Avoidance (CA) guidance. The alerting and guidance issued by ACAS Xu differs from previous DAA and CA systems, a result of new capabilities that were not available to earlier systems. Differences include the removal of warning-level DAA alerting and guidance, as well as the issuance of new types of CA guidance, referred to as Resolution Advisories (RAs). Whereas TCAS II only issues vertical RAs, ACAS Xu adds horizontal and blended (i.e., simultaneous vertical and horizontal) RAs. The current study assessed pilots' ability to respond to and comply with the DAA and RA alerting and guidance generated by ACAS Xu in a human-in-the-loop simulation. Sixteen active UAS pilots participated in the study and were tasked with responding to scripted DAA and RA traffic conflicts. Results showed that pilots were effective at making timely maneuvers against DAA threats. The proportion of losses of DAA well clear against noncooperative intruders was found to be significantly higher than the proportion of losses against cooperative intruders, a result of the limited declaration range of the simulated onboard RADAR. Results also demonstrated that pilots could consistently meet the five second response time requirement for initial RAs. Rapid responses to RAs had the corresponding effect of minimizing the severity of losses of DAA well clear. While pilots complied with initial RAs at a high rate, compliance dropped substantially when the target heading was updated during a horizontal RA. Pilot performance with ACAS Xu will be presented alongside results from prior DAA research.
引用
下载
收藏
页数:10
相关论文
共 50 条
  • [21] Human-in-the-Loop Schema Induction
    Zhang, Tianyi
    Than, Isaac
    Hou, Zhaoyi
    Ren, Jiaxuan
    Zhou, Liyang
    Xu, Hainiu
    Zhang, Li
    Martin, Lara J.
    Dror, Rotem
    Li, Sha
    Ji, Hang
    Palmer, Martha
    Brown, Susan
    Suchocki, Reece
    Callison-Burch, Chris
    PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-DEMO 2023, VOL 3, 2023, : 1 - 10
  • [22] Human-in-the-Loop Interpretability Prior
    Lage, Isaac
    Ross, Andrew Slavin
    Kim, Been
    Gershman, Samuel J.
    Doshi-Velez, Finale
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [23] Human-in-the-loop Outlier Detection
    Chai, Chengliang
    Cao, Lei
    Li, Guoliang
    Li, Jian
    Luo, Yuyu
    Madden, Samuel
    SIGMOD'20: PROCEEDINGS OF THE 2020 ACM SIGMOD INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2020, : 19 - 33
  • [24] Human-In-The-Loop Evaluation of Human-Machine Interface for Power Plant Operators
    Lee, Seunghyun Tina
    Kim, So Young
    Gilmore, David
    2017 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2017, : 34 - 39
  • [25] The human-in-the-loop: an evaluation of pathologists' interaction with artificial intelligence in clinical practice
    Boden, Anna C. S.
    Molin, Jesper
    Garvin, Stina
    West, Rebecca A.
    Lundstrom, Claes
    Treanor, Darren
    HISTOPATHOLOGY, 2021, 79 (02) : 210 - 218
  • [26] Human-in-the-loop evaluation of a vehicle stability controller using a vehicle simulator
    Chung, T
    Kim, J
    Yi, K
    INTERNATIONAL JOURNAL OF AUTOMOTIVE TECHNOLOGY, 2004, 5 (02) : 109 - 114
  • [27] Evaluation of a Multi-agent "Human-in-the-loop" Game Design System
    Kruse, Jan
    Connor, Andy M.
    Marks, Stefan
    ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, 2022, 12 (03)
  • [28] Tower Information Display System (TIDS): Human-in-the-loop simulation and evaluation
    Hannon, Daniel J.
    Lee, Jonathan T.
    Sheridan, Thomas B.
    Donohoe, Caroline
    2008 INTEGRATED COMMUNICATIONS, NAVIGATION AND SURVEILLANCE CONFERENCE, 2008, : 203 - 211
  • [29] HUMAN-IN-THE-LOOP EVALUATION OF REMOTE MANIPULATOR SYSTEM ACTIVE DAMPING AUGMENTATION
    DEMEO, ME
    GILBERT, MG
    SCOTT, MA
    LEPANTO, JA
    BAINS, EM
    JENSEN, MC
    JOURNAL OF GUIDANCE CONTROL AND DYNAMICS, 1995, 18 (04) : 689 - 695
  • [30] A human-in-the-loop deep learning paradigm for synergic visual evaluation in children
    Zhang, Kai
    Li, Xiaoyan
    He, Lin
    Guo, Chong
    Yang, Yahan
    Dong, Zhou
    Yang, Haoqing
    Zhu, Yi
    Chen, Chuan
    Zhou, Xiaojing
    Li, Wangting
    Liu, Zhenzhen
    Wu, Xiaohang
    Liu, Xiyang
    Lin, Haotian
    NEURAL NETWORKS, 2020, 122 : 163 - 173