Embodied intelligent industrial robotics: Concepts and techniques

In recent years, embodied intelligent robotics (EIR) advances significantly in multi-modal perception, autonomous decision-making, and physical interaction. Some robots have already been tested in general-purpose scenarios, such as homes and shopping malls. However, EIR currently lacks a deep understanding of the semantics of industrial environments and the normative constraints between industrial operating objects. The goal of this paper is to advance the research and application of embodied intelligence in industrial scenarios. This paper first reviews the history of industrial robotics and the mainstream EIR frameworks. Herein, the concept of embodied intelligent industrial robotics (EIIR) is formulated and a knowledge-driven EIIR technical framework for industrial environments is proposed. The framework includes four primary modules: a world model, a high-level task planner, a low-level skill controller, and a simulator. The development of techniques related to each module are also thoroughly discussed, and recent progress regarding their adaption to industrial applications is emphasized. Finally, the key challenges that EIIR encounters in industrial scenarios are summarized and future research directions are suggested. The authors believe that EIIR technology is shaping the next generation of industrial robotics. EIIR-based industrial systems have strong potential to enable intelligent manufacturing. It is expected that this review could serve as a valuable reference for scholars and engineers that are interested in industrial embodied intelligence. Together, scholars can use this research to drive the rapid advancement and application of EIIR techniques. The authors would continue to track and summarize new studies in the project page this https URL.