Multimodal perception and asynchronous pipeline collaboration for intelligent intra-logistics: a fusion-driven approach
Abstract
This paper proposes MP-APC, a fusion-driven, asynchronous pipeline integrating vision, LiDAR, and RFID to address latency and robustness challenges in intra-logistics. The framework employs attention-based fusion and event-triggered coordination, achieving a 35% reduction in decision latency, 4.5% F1-score improvement, and 27% increase in throughput. Evaluations on over 100,000 warehouse trajectories and simulations validate its scalability and accuracy.
Fields of Study & Subjects
Robotics and Sensor-Based Localization
Advanced Neural Network Applications
Autonomous Vehicle Technology and Safety
Publication details
- Pages
- 3–3
- Publication date
- 8 January 2026