Feature Recognition (FR) in Computer-aided Design (CAD) models is central for Design and Manufacturing. FR is a problem whose computational burden is intractable (NP-hard), given that its underlying task is the detection of graph isomorphism. Until now, compromises have been reached by only using FACE-based geometric information of prismatic CAD models to prune the search domain. Responding to such shortcomings, this manuscript presents an interactive FR method that more aggressively prunes the search space with reconfigurable geometric tests. Unlike previous approaches, our reconfigurable FR addresses curved EDGEs and FACEs. This reconfigurable approach allows enforcing arbitrary confluent topologic and geometric filters, thus handling an expanded scope. The test sequence is itself a graph (i.e., not a linear or total-order sequence). Unlike the existing methods that are FACE-based, the present one permits combinations of topologies whose dimensions are two (SHELL or FACE), one (LOOP or EDGE), or 0 (VERTEX). This system has been implemented in an industrial environment, using icon graphs for the interactive rule configuration. The industrial instancing allows industry based customization and itis faster when compared to topology-based feature recognition. Future work is required in improving the robustness of search conditions, treating the problem of interacting or nested features, and improving the graphic input interface.

This work presents an industrial bin-picking framework for robotics called PickingDK. The proposed framework employs a plugin based architecture, which allows it to integrate different types of sensors, robots, tools, and available open-source software and state-of-the-art methods. It standardizes the bin-picking process with a unified workflow based on generally defined plugin interfaces, which promises the hybridization of functional/virtual plugins for fast prototyping and proof-of-concept. It also offers different levels of controls according to the user’s expertise. The presented use cases demonstrate flexibility when building bin-picking applications under PickingDK framework and the convenience of exploiting hybrid style prototypes for evaluating specific steps in a bin-picking system, such as parameter fine-tuning and picking cell design.