In precision robotic assembly visual sensing techniques have been widely used since they can detect large misalignments and also part's shape at a distance. Develops two novel visual sensing methodologies.
Both systems consist of four components: an inside mirror and an outside mirror, a pair of plane mirrors and a camera with a collecting lens. The difference between the two is that system A adopts a pyramidal mirror configuration, while system B employs a conic one. Owing to this configuration difference, system A can detect three‐dimensional measurements of objects with only one image capture, while in addition to this functionality system B is shown to be capable of detecting two omni‐directional image. The measurement principles are described in detail and compared with each other.
The image acquiring process is shown to easily detect the in situ status of each assembly action, while the recognition method is found to be effective to identify instantaneous misalignment between the peg and the hole. The results obtained from a series of experiments show that the proposed visual sensing methods are an effective means of detecting misalignment between mating parts even in the presence of self‐occlusion.
The proposed sensing methods will dramatically increase the rate of success when actually utilized in assembly processes.
Describes the development of two novel visual sensing methodologies.
