No abstract

The peg-in-hole insertion is the most common and often one of the most important procedures in largescale equipment manufacturing. However, in the process of peg-in-hole assembly operation using robot, the parts may not be assembled correctly or even be damaged because of the deviation causing by the inaccuracy of the assembly robot. To overcome this problem, this paper presents a kind of large-scale peg-in-hole robotic assembly system based on laser tracker and its corresponding control strategy. The simulation and analysis are also demonstrated to verify the system efficient.Shuntao Liu, is with AVIC Chengdu Aircraft Industrial

Current latent representation methods using unsupervised learning have no semantic meaning; thus, it is difficult to directly express their physical task in the real world. To this end, this paper attempts to propose a specified latent representation with physical semantic meaning. First, a few labeled samples are used to generate the framework of the latent space, and these labeled samples are mapped to framework nodes in the latent space. Second, a self-learning method using structured unlabeled samples is proposed to shape the free space between the framework nodes in the latent space. The proposed specified latent representation therefore possesses the advantages provided by both supervised and unsupervised learning. The proposed method is verified by numerical simulations and real-world experiments.

No abstract

No abstract