Prof. Weisong Wen Interviewed by UBeat on "Drone-Based Curtain Wall Cleaning" Technology and Prospects

UBeat recently ran the feature “Drones for glass curtain wall cleaning: all parties gearing up.” In the interview, Weisong Wen, lead of the Trustworthy AI and Autonomous Systems Laboratory (TASLAB) and Assistant Professor, outlined the technology roadmap, regulatory compliance and application outlook for drone-based curtain wall cleaning, and presented the team’s progress in autonomous localization, control and operational safety.

UBeat feature header showing a drone spraying a glass curtain wall

The UBeat feature "Drones for glass curtain wall cleaning: all parties gearing up."

Industry pain points and opportunities

  • Technical challenges: perception and localization on highly reflective glass; disturbance-rejection control for close-proximity flight; compensation for water-jet reaction forces; enclosure waterproofing and payload reliability.
  • Safety and compliance: advanced operations permissions, exclusion zones and contingency planning, geo-fencing and wind-field assessment, prioritizing “safety first, standards-led.”
  • Application value: reduced high-altitude work risk, improved efficiency, and strong potential for energy savings and carbon reduction.
  • Progress and plans: a staged demonstration path (building mapping → localization and pathing → on-site cleaning), while co-developing standard procedures with property managers and regulators.
Prof. Wen at his desk during the interview
Prof. Wen during the interview
Glass curtain wall of PolyU JCIT Tower
PolyU JCIT Tower

Photos from the UBeat interview.

UBeat feature: https://ubeat.com.cuhk.edu.hk/180_%E7%84%A1%E4%BA%BA%E6%A9%9F%E6%B4%97%E7%8E%BB%E7%92%83%E5%B9%95%E7%89%86-%E5%90%84%E6%96%B9%E8%93%84%E5%8B%A2%E5%BE%85%E7%99%BC/

Previous post
Harbin Engineering University Vice President YU Zhiwen Visits PolyU's TASLAB to Strengthen Research Ties
Next post
Quadruped Robot Steals Spotlight at 28th Beijing-Hong Kong Economic Cooperation Symposium