Learning and generalising object extraction skill for contact-rich disassembly tasks: an introductory study

Remanufacturing automation must be designed to be flexible and robust enough to overcome the uncertainties, conditions of the products, and complexities in the planning and operation of the processes. Machine learning methods, in particular reinforcement learning, are presented as techniques to learn, improve, and generalise the automation of many robotic manipulation tasks (most of them related to grasping, picking, or assembly). However, not much has been exploited in remanufacturing, in particular in disassembly tasks. This work presents the state of the art of contact-rich disassembly using reinforcement learning algorithms and a study about the generalisation of object extraction skills when applied to contact-rich disassembly tasks. The generalisation capabilities of two state-of-the-art reinforcement learning agents (trained in simulation) are tested and evaluated in simulation, and real world while perform a disassembly task. Results show that at least one of the agents can generalise the contact-rich extraction skill. Besides, this work identifies key concepts and gaps for the reinforcement learning algorithms’ research and application on disassembly tasks.

Object extraction in video sequences based on spatiotemporal independent component analysis

Video object extration is one of the most important areas of video processing in which objects from video sequences are extracted and used for many applications such as surveillance systems, pattern recognition etc. In this research work, an object-based technique based on the spatiotemporal independent component analysis (stICA) is developed to extract moving objects from video sequences. Using the stICA, the preliminary source images containing moving objects in the video sequence are extracted. These images are processed using wavelet analysis, edge detection, region growing and multiscale segmentation techniques to improve the accuracy of the extracted objects. A novel compensation method is applied to deal with the nonlinear problem caused by the application of the stICA directly to the video sequences. The recovered objects are indexed by the singular calue decompensation (SVD) and linear combination analysis. Simulation results demonstrate the effectiveness of the stICA-based object extraction technique in content-based video processing applications.

Object extraction in video sequences based on spatiotemporal independent component analysis

Video object extration is one of the most important areas of video processing in which objects from video sequences are extracted and used for many applications such as surveillance systems, pattern recognition etc. In this research work, an object-based technique based on the spatiotemporal independent component analysis (stICA) is developed to extract moving objects from video sequences. Using the stICA, the preliminary source images containing moving objects in the video sequence are extracted. These images are processed using wavelet analysis, edge detection, region growing and multiscale segmentation techniques to improve the accuracy of the extracted objects. A novel compensation method is applied to deal with the nonlinear problem caused by the application of the stICA directly to the video sequences. The recovered objects are indexed by the singular calue decompensation (SVD) and linear combination analysis. Simulation results demonstrate the effectiveness of the stICA-based object extraction technique in content-based video processing applications.

Learning and Generalising Object Extraction Skill for Contact-rich Disassembly Tasks: An Introductory Study

Remanufacturing automation must be designed to be flexible and robust enough to overcome the uncertainties, conditions of the products, and complexities in the process's planning and operation. Machine learning, particularly reinforcement learning, methods are presented as techniques to learn, improve, and generalise the automation of many robotic manipulation tasks (most of them related to grasping, picking, or assembly). However, not much has been exploited in remanufacturing, in particular in disassembly tasks. This work presents the State-of-the-Art of contact-rich disassembly using reinforcement learning algorithms and a study about the object extraction skill's generalisation when applied to contact-rich disassembly tasks. The generalisation capabilities of two State-of-the-Art reinforcement learning agents (trained in simulation) are tested and evaluated in simulation and real-world while perform a disassembly task. Results shows that, at least, one of the agents can generalise the contact-rich extraction skill. Also, this work identifies key concepts and gaps for the reinforcement learning algorithms' research and application on disassembly tasks.