An interactive motion planning framework that can learn from experience. (February 2015)

• Record Type: Journal Article
• Authors: Yan, Yu; Poirson, Emilie; Bennis, Fouad
• Is Part Of: Computer aided design. Volume 59(2015)
• Page Start: 23
• Page End: 38
• Publication Date: 2015-02
• Subjects: Accessibility verification -- Assembly path planning -- Narrow passage -- Interactive motion planning -- Scenario retrieval; Computer-aided design -- Periodicals; Engineering design -- Data processing -- Periodicals; Computer graphics -- Periodicals; Conception technique -- Informatique -- Périodiques; Infographie -- Périodiques; Computer graphics; Engineering design -- Data processing; Periodicals; Electronic journals; 620.00420285
• DOI: 10.1016/j.cad.2014.07.007
• Languages: English
• ISSNs: 0010-4485

Abstract

Abstract: The accessibility verification of the assembly/disassembly plays an important role in the process of product design. In the last decade, the sampling based motion planners have been successfully applied to solve the accessibility verification. However, the narrow passage which is a common problem in the assembly tasks is still a bottleneck. Meanwhile, the requirement of perception and emotion assessment drives the interaction between users and automatic path planners in the virtual assembly process. In this paper, a curve matching method is used to explore the implicit relationship between the topological information of scenarios and the motion of objects, based on which an interactive motion planning framework that can learn from experience is constructed. Our framework consists of two main processes: a learning process and a motion generation process. In the former process, the motion segment (a part of motion path) and its related scenario segment (a part of workspace passed through by the object) are gathered, after an interactive motion planning process finds a collision-free motion path or reaches the conclusion of inaccessibility. According to the similarity between the skeletons of scenario segments, the gathered scenario segments and motion segments are organized by a hierarchical structure in the motion library. The latter process permits users to control only one point in the workspace for the selection of a new scenario, and then the similar scenarios are retrieved from the motion library, to help quickly detect the connectivity of the new scenario and generate a repaired motion path to guide users with feasible manipulations. We highlight the performance of our framework on a challenging problem in 2D, in which a non-convex object passes through a cluttered environment filled with randomly shaped and located non-convex obstacles. Highlights: Maximal sphere sequence represents the scenario. The centerline of maximal sphere sequence represents the scenario skeleton. The motion of object has close relationship with the change of the skeleton and volume size of scenario. Motion learning is based on computing the similarity of scenarios by dynamic time warping (DTW). Scenario retrieval is highly efficient due to the hierarchical clustering in motion library. Releasing humans from rotation manipulation in complex assembly verification with learned motion experience.