Model-free object grasping : Model-free object grasping with a learning-free approach

Abstract

The industry standards and capability are constantly advancing and pushing forward to increase data collection, efficiency, profit, and quality as well as decrease downtime, injuries, and hazards as much as possible. In recent years, robot systems have received more attention in the context of a large number of industrial applications, such as automotive manufacturing, additive manufacturing, assembly, quality inspection, and co-packing. The collaboration between multiple robots and human operators is considered to be the most prominent strategy in Industry 4.0 and future Industry 5.0, sharing the same space and collaborating on tasks according to their complementary capabilities. With the use of robots and their abilities could efficiency, profit, safety, and quality be further increased, potentially revolutionizing the industry and production. This project was supported in part by DEEPCOBOT Project. DEEPCOBOT, Collective Efficient Deep Learning and Networked Control for Multiple Collaborative Robot Systems, are a research project funded by IKTPLUSS under Grant 306640/O70 from the Research Council of Norway. The project will investigate the design of a new generation of decentralized data-driven Deep Learning based controllers for multiple coexisting collaborative robots, which interact both between them-selves and with human operators in order to collectively learn from each other’s experiences and perform cooperatively different complex tasks in large-scale industrial environments. This is motivated by the increasing demand of automation in industry, especially the demand of a safer and more efficient collaboration between multiple robots and human operators to integrate the best of human abilities and robotic automation.