On 29 January 2026, the Trustworthy AI and Autonomous Systems Laboratory (TASLAB) at The Hong Kong Polytechnic University (PolyU) held a strategic cooperation meeting in Hong Kong with SF Express (Hong Kong) and Rino AI. The meeting explored collaboration on smart logistics and autonomous campus delivery vehicles, and reflects PolyU’s commitment to industry-academia partnerships and to practical solutions for next-generation logistics in urban delivery and campus mobility.
Representatives of TASLAB, SF Express (Hong Kong) and Rino AI at the meeting.
The meeting brought together key representatives from the three parties to discuss approaches to intelligent logistics and autonomous delivery. The discussions centred on using AI, robotics, sensor fusion and IoT solutions to address modern logistics challenges, particularly in campus and urban environments where safety, efficiency and sustainability are paramount.
Attendees from PolyU included Prof. Weisong WEN from TASLAB and research team members. SF Express (Hong Kong) was represented by senior executives from its logistics operations and technology innovation divisions, and Rino AI by its leadership team specialising in artificial intelligence solutions and autonomous systems development.
Areas of collaboration
The three-party collaboration will focus on the following technological domains and application scenarios:
- Smart logistics systems: AI-powered solutions for intelligent logistics management, including dynamic route optimisation, real-time package tracking, predictive demand forecasting and intelligent warehouse management. Machine learning models will be integrated with SF Express (Hong Kong)’s extensive operational data to create adaptive logistics systems that respond to changing conditions in real time. This includes algorithms for fleet management, delivery scheduling and resource allocation that can enhance operational efficiency while reducing energy consumption and environmental impact. The system will use big data analytics and cloud computing to process large volumes of logistics data, enabling predictive maintenance, demand forecasting and intelligent decision-making across the entire supply chain.
- Autonomous campus delivery vehicles: Designing and implementing unmanned delivery vehicles tailored to university campuses. The project will address campus-specific challenges, including pedestrian detection and avoidance, navigation in mixed-use environments with students and faculty, compliance with campus safety regulations and integration with existing campus infrastructure. The vehicles will combine perception systems (LiDAR, cameras and radar) with path planning algorithms to ensure safe and efficient delivery. Special attention will be given to human-robot interaction so that the vehicles can operate smoothly in crowded campus settings, with features such as audio-visual alerts, gesture recognition and emergency stop mechanisms. The vehicles will be designed to handle various weather conditions, navigate complex terrain including stairs and ramps, and operate efficiently at peak hours when campus foot traffic is highest.
- Technology integration and system architecture: Combining TASLAB’s research expertise in autonomous systems, localization and navigation with SF Express (Hong Kong)’s logistics experience and operational insights, and Rino AI’s artificial intelligence capabilities and machine learning infrastructure. The aim is a complete technology stack that integrates perception, planning and control with logistics management platforms. This includes robust communication protocols between autonomous vehicles and central dispatch systems, edge computing for real-time decision-making, and fail-safe mechanisms for system reliability. The architecture will incorporate multi-layer redundancy, cybersecurity measures against potential threats and scalable cloud infrastructure for future expansion. Sensor fusion will combine data from multiple sources into accurate environmental models, while deep learning will allow the vehicles to learn from experience and continuously improve.
- Pilot programmes and field testing: Exploring the establishment of testbeds on the PolyU campus for real-world validation and demonstration of autonomous delivery technologies. The pilots will serve as living laboratories where researchers collect operational data, test new algorithms and refine system performance under actual operating conditions, addressing challenges such as weather, varying terrain, obstacle avoidance and user acceptance before broader deployment. The collected data will inform future improvements and provide insights for scaling the technology to other campuses and urban environments. The pilot phase will start with controlled experiments to test specific capabilities, followed by gradual expansion to full operational deployment. User feedback from students, faculty and staff will be gathered to refine user interfaces and improve overall service quality.
- Safety and regulatory compliance: Developing safety protocols and working towards compliance with local regulations governing autonomous vehicle operations in Hong Kong. This includes establishing safety standards for autonomous campus delivery, conducting thorough risk assessments, implementing redundant safety systems with multiple fail-safe mechanisms, and working with regulatory bodies so that the vehicles meet all requirements for operation in public spaces. The collaboration will work closely with university safety departments, local transportation authorities and industry standards organisations to develop best practices. Safety features will include emergency braking, collision avoidance algorithms, remote monitoring and intervention capabilities, and logging of all operational data for incident investigation and continuous improvement.