62 / 2025-04-15 10:48:21
Overcoming Detection and Monitoring Challenges of Rail-Mounted Robots in Commercial Broiler Systems
broiler,Precision livestock farming,robot,welfare,rail-mounted
摘要待审
Tanner Thornton / University of Tennessee Knoxville
Shawn Hawkins / University of Tennessee Knoxville
Yang Zhao / University of Tennessee Knoxville
Robert Burns / University of Tennessee Knoxville
Tom Tabler / University of Tennessee Knoxville
Precision Livestock Farming (PLF) systems utilizing rail-mounted robots offer promising solutions for environmental monitoring and mortality detection in commercial poultry production. However, challenges remain regarding sensor accuracy and computer vision reliability. This study examined how sensor height placement and camera occlusion influence data accuracy and detection efficacy of the SCOUT® rail-mounted robotic system deployed in a commercial broiler house (16.5 × 152 m, Bradley County, Tennessee, USA). Environmental data (temperature and relative humidity) collected at robot sensor height (1.7 m) significantly differed from measurements at bird-level height (0.4 m), with lower temperatures (-1.4°C) and higher relative humidity (+10.6%) recorded at bird-level. Mortality detection accuracy was assessed by comparing robot-reported mortalities with manual counts over two production cycles, revealing an overall detection rate of 31%. Staged mortality tests clarified the impact of occlusion, revealing significantly higher detection rates beneath the rail when mortalities were isolated within enclosures (57%) compared to outside (19%; p < 0.001). Detection rates were substantially lower near feed and water lines and house sidewalls due to obstruction from infrastructure and live birds, yet still significantly higher within enclosures (p = 0.042 and p = 0.022, respectively). Additionally, camera field of view limitations (approximate 1 m effective range) and poor performance in low-light conditions further reduced system reliability. This research identifies specific limitations in current PLF robotic designs and proposes technological refinements in sensor positioning and vision systems to improve monitoring accuracy and bird welfare management in commercial houses.





 
重要日期
  • 会议日期

    10月20日

    2025

    10月23日

    2025

  • 04月15日 2025

    摘要截稿日期

  • 05月01日 2025

    摘要录用通知日期

  • 06月30日 2025

    初稿截稿日期

  • 08月01日 2025

    终稿截稿日期

  • 08月31日 2025

    初稿录用通知日期

  • 10月23日 2025

    注册截止日期

主办单位
International Research Center for Animal Environment and Welfare (IRCAEW)
Chinese Society of Agricultural Engineering (CSAE)
China Agricultural University (CAU)
Rongchang District People’s Government
The National Center of Technology Innovation for Pigs
承办单位
Chongqing Academy of Animal Sciences (CAAS)
Key Lab of Agricultural Engineering in Structure and Environment, Chinese Ministry of Agriculture, Beijing, China
联系方式
历届会议
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询