Learning Robust Grasping Strategy Through Tactile Sensing and Adaption Skill

Robust grasping represents an essential task in robotics, necessitating tactile feedback and reactive grasping adjustments for robust grasping of objects. Previous research has extensively combined tactile sensing with grasping, primarily relying on rule-based approaches, frequently neglecting post-grasping difficulties such as external disruptions or inherent uncertainties of the object's physics and geometry. To address these limitations, this paper introduces an human-demonstration-based adaptive grasping policy base on tactile, which aims to achieve robust gripping while resisting disturbances to maintain grasp stability. Our trained model generalizes to daily objects with seven different sizes, shapes, and textures. Experimental results demonstrate that our method performs well in dynamic and force interaction tasks and exhibits excellent generalization ability.

Using Hopfield to Solve Resource-Leveling Problem

Although the traditional permute matrix coming along with Hopfield is able to describe many common problems, it seems to have limitation in solving more complicated problem with more constrains, like resource leveling which is actually a NP problem. This paper tries to find a better solution for it by using neural network. In order to give the neural network description of resource leveling problem, a new description method called Augmented permute matrix is proposed by expending the ability of the traditional one. An Embedded Hybrid Model combining Hopfield model and SA are put forward to improve the optimization in essence in which Hopfield servers as State Generator for the SA. The experiment results show that Augmented permute matrix is able to completely and appropriately describe the application. The energy function and hybrid model given in this study are also highly efficient in solving resource leveling problem.