This paper presents the design of an instruction generation system that can be used to automatically generate instructions for complex assembly operations performed by humans on factory shop floors. Multimodal information−text, graphical annotations, and 3D animations− is used to create easy-to-follow instructions. This thereby reduces learning time and eliminates the possibility of assembly errors. An automated motion planning subsystem computes a collision-free path for each part from its initial posture in a crowded scene onto its final posture in the current subassembly. Visualization of this computed motion results in generation of 3D animations. The system also consists of an automated part identification module that enables the human to identify, and pick, the correct part from a set of similar looking parts. The system's ability to automatically translate assembly plans into instructions enables a significant reduction in the time taken to generate instructions and update them in response to design changes.
INTRODUCTIONProduct manufacturing involves complex assembly operations that must be performed by humans and/or robots. Within this setting, it is imperative to define the operational roles of the human and the robot appropriately. Whereas robots are superior to humans at handling repetitive tasks like welding and bolting, humans are better at performing tasks like picking, carrying, and placing a wide range of parts without using special fixtures; humans also have a natural ability to handle several assembly equipment easily. However, humans are prone to committing assembly related mistakes. Human workers usually follow a list of instructions to carry out assembly operations on the shop floor. However, poor instructions lead to assembly errors and increased learning time. Therefore, there is a need for effective, and yet, easy-to-follow assembly instructions for humans. Manual generation of such high quality instructions is a time consuming task when utilizing shared setups and tools. This thereby motivates the need for automated generation of instructions for human workers.In this paper, we present the design of an instruction generation system that can be used to automatically generate instructions