LAUSR

The rapid advancement of IoT and AI technologies has accelerated the development of human–robot collaborative warehouses, enabling real-time monitoring and intelligent automation. By combining human adaptability with robotic precision, this hybrid model offers greater flexibility than fully automated systems. However, existing research predominantly concentrates on specific collaboration tasks such as order picking and storage, while important areas like human-robot coexistence scenarios and inbound/outbound logistics remain underexplored. This imbalance highlights gaps in understanding dynamic task allocation, safety considerations, and process integration across different warehouse stages. This paper presents a comprehensive literature review on human–robot collaboration in warehouse environments, analyzing 52 representative studies across multiple dimensions. The review identifies key research gaps, including limited exploration of human-centered factors, insufficient integration of physical and decision-making collaboration, and a lack of unified frameworks for multi-agent and cross-mode coordination. To address these gaps, future research directions are proposed, focusing on dynamic cross-modal collaboration, trust and fatigue-aware systems, and leveraging natural language interfaces to enhance human-centered interaction. By emphasizing these aspects, this review aims to guide the design of more efficient, adaptive, and human-friendly collaborative warehouse systems that better meet the challenges of real-world operations.