DM4Manufacturing
Aligning Manufacturing Decision Making with Advanced Manufacturing Technologies
The project
The number of new disruptive technologies with expected global impact is growing on many fronts. Technologies such as Advanced Robotics, big data analysis, the Internet of things or 3D printing are listed as drivers that will change “life, business and global economy”[MaChBuDoBiMa2013]. Looking into the past and from a manufacturing point of view, the advent of such disruptive technologies, such as CAD/CAM or the internet, only fulfills its potential when the overall management practices adjust to the new reality. Therefore, there is a need for integrated development of these advanced manufacturing technologies with the development of new multi-level decision-making tools. This is the main focus of this project. Recent developments in Robotics are expected to change the landscape of manufacturing processes. Robots are nowadays interacting closely with humans, are
Recent developments in Robotics are expected to change the landscape of manufacturing processes. Robots are nowadays interacting closely with humans, are programmable-by demonstration, easily pluggable at any point on the shop-floor, and capable of interacting in spaces designed for human use. This paradigm change has strong implications for the development of future manufacturing decision-making tools.
Objectives
The main objective of the DM4Manufacturing project is the integrated development of manufacturing decision-making tools aligned with the efficient use of advanced manufacturing technologies to address upcoming challenges in the high-mix high customization industry. To fulfill the potential of Advanced Robotics in these scenarios there is a need for agile real-time decisions integrated into Adaptive Production Systems. The project will pursue the following multidisciplinary challenges.
Challenge 1 - Optimal automation levels
Plant managers and engineers in general struggle to adjust the level of automation of production lines to product variations and market demand: especially when robots are involved, updates are slow, complex and cost-intensive, and the loss of productivity is considerable due to a stopped manufacturing line. The most common solution is to keep the level of automation deliberately low to guarantee the fast updatability of the system. Another solution is to simply design the manufacturing lines from the start for the maximum estimated customer demand, but this means high initial investment and low equipment utilization during large parts of the product cycle and a huge difficulty to change the product.
Challenge 2 - Human-centered automation
The flexibility of robotic systems to perform a variety of tasks is increasing but the major benefit from the use of collaborative robotics comes from the close cooperation with humans, exploring the best abilities of humans and robots. To maximize this potential, there is a need for decision-making tools that can cope the robot/machine limitations with the human dimension in ergonomic, social and productivity terms.
Challenge 3 - Simulation and Optimization tools for adaptive production systems
Scheduling and controlling manufacturing activities in a dynamic environment, subject to a high level of uncertainty imposed by various unexpected events like machine breakdowns or frequent changes in orders quantity, mix and due dates, is a difficult task. Additionally, increased flexibility allowed by new manufacturing technologies, like robotics, has amplified, rather than reduced, planning, scheduling and control problems. Thus, novel optimization, simulation or simulation-based optimization tools are required to, not only generate robust production schedules but also to undertake real-time rescheduling to cope with the production environment uncertainty.
Consortium
The DM4Manufacturing project consortium is constituted of three Portuguese institutions: INESC TEC, the University of Coimbra (UC) and the Association of Instituto Superior Técnico for R&D (IST-ID).
DM4Manufacturing @UC
At the University of Coimbra, the work focused on human-robot collision avoidance. Robots are increasingly present in our lives, sharing the workspace with humans. Existing robots do not have autonomy to perceive its unstructured and time-varying surrounding environment, nor the ability to real-time avoid collisions with humans while keeping the task target. Human-robot collision avoidance is critical for robots acceptance as co-workers. Research will focus on the study of novel real-time collision avoidance techniques based on potential fields. Hypothetical repulsion and attraction vectors are computed considering not only the human-robot minimum distance but also the relative velocities, joint limits, redundancy and the Goals-Non-Reachable-with-Obstacle-nearby (GNRON) effect. A controller using Newton method (Hessian) will allow reducing robot vibration escaping to local minima. Kinematics and dynamics controllers ensure a smooth path control at joint and end-effector level. Robot(s) and human(s) are modelled by geometric primitives to mutually compute the analytical minimum distance between them. The proposed methodology will be validated with a real collaborative robot.
Related Publications
M. Safeea, P. Neto, R. Bearee, Robot dynamics: A recursive algorithm for efficient calculation of Christoffel symbols, Mechanism and Machine Theory, Elsevier, Volume 142, December 2019, Article 103589, DOI 10.1016/j.mechmachtheory.2019.103589 [www]
M. A. Simão, O. Gibaru, P. Neto, Online Recognition of Incomplete Gesture Data to Interface Collaborative Robots, IEEE Transactions on Industrial Electronics, IEEE, Volume 66, Issue 12, December 2019, Pages 9372-9382, DOI 10.1109/TIE.2019.2891449 [www] [pdf]
M. Simão, P. Neto, O. Gibaru, EMG-based online classification of gestures with recurrent neural networks, Pattern Recognition Letters, Elsevier, Volume 128, December 2019, Pages 45–51, DOI 10.1016/j.patrec.2019.07.021 [www]
N. Mendes, M. Simão, P. Neto, Segmentation of electromyography signals for pattern recognition, IECON 2019 – 45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal, October 2019, Pages 732-737, DOI 10.1109/IECON.2019.8927221 [www] [pdf]
M. Safeea, P. Neto, R. Béarée, Precise hand-guiding of redundant manipulators with null space control for in-contact obstacle navigation, IECON 2019 – 45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal, October 2019, Pages 693-698, DOI 10.1109/IECON.2019.8927766 [www] [pdf]
J. R. Silva, M. Simão, N. Mendes, P. Neto, Navigation and obstacle avoidance: a case study using Pepper robot, IECON 2019 – 45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal, October 2019, Pages 5263-5268, DOI 10.1109/IECON.2019.8927009 [www] [pdf]
M. Babcinschi, B. Freire, P. Neto, L. Ferreira, B. Señaris, F. Vidal, AutomationML for Data Exchange in the Robotic Process of Metal Additive Manufacturing, 2019 24th IEEE Conference on Emerging Technologies and Factory Automation (ETFA), Zaragoza, Spain, September 2019, Pages 65-70, DOI 10.1109/ETFA.2019.8869079 [www] [pdf]
M. Safeea, P. Neto, R. Bearee, On-line collision avoidance for collaborative robot manipulators by adjusting off-line generated paths: an industrial use case, Robotics and Autonomous Systems, Elsevier, Volume 119, September 2019, Pages 278–288, DOI 10.1016/j.robot.2019.07.013 [www]
M. Simão, P. Neto, O. Gibaru, Improving novelty detection with generative adversarial networks on hand gesture data, Neurocomputing, Elsevier, Volume 358, September 2019, Pages 437–445, DOI 10.1016/j.neucom.2019.05.064 [www]
M. Safeea, P. Neto, Minimum distance calculation using laser scanner and IMUs for safe human-robot interaction, Robotics and Computer-Integrated Manufacturing, Elsevier, Volume 58, August 2019, Pages 33-42, DOI 10.1016/j.rcim.2019.01.008 [www]
M. Safeea, P. Neto, R. Béarée, A Quest Towards Safe Human Robot Collaboration, Towards Autonomous Robotic Systems. TAROS 2019. Lecture Notes in Computer Science, Springer, Cham Nature, Volume 11650, July 2019, Pages 493-495, DOI 10.1007/978-3-030-25332-5_48 [www]
M. Safeea, P. Neto, R. Béarée, The Third hand, Cobots Assisted Precise Assembly, Towards Autonomous Robotic Systems. TAROS 2019. Lecture Notes in Computer Science, Springer, Cham Nature, Volume 11650, July 2019, Pages 454-457, DOI 10.1007/978-3-030-25332-5_39 [www]
M. Safeea, P. Neto, R. Béarée, A Geometric Dynamics Algorithm for Serially Linked Robots, Towards Autonomous Robotic Systems. TAROS 2019. Lecture Notes in Computer Science, Springer Nature, Volume 11649, June 2019, Pages 425-435, DOI 10.1007/978-3-030-23807-0_35 [www]
M. Simão, N. Mendes, O. Gibaru, P. Neto, A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction, IEEE Access, IEEE, Volume 7, March 2019, Pages 39564–39582, DOI 10.1109/ACCESS.2019.2906584 [www] [pdf]
M. Safeea, P. Neto, KUKA Sunrise Toolbox: Interfacing Collaborative Robots With MATLAB, IEEE Robotics & Automation Magazine, Volume 26, Issue 1, March 2019, Pages 91-96, DOI 10.1109/MRA.2018.2877776 [www] [pdf]
P. Neto, M. Simão, N. Mendes, M. Safeea, Gesture-based human-robot interaction for human assistance in manufacturing, The International Journal of Advanced Manufacturing Technology, Springer, Volume 101, March 2019, Pages 119-135, DOI 10.1007/s00170-018-2788-x [www] [pdf]
M. Safeea, P. Neto, Richard Bearee, Efficient Calculation of Minimum Distance Between Capsules and Its Use in Robotics, IEEE Access, IEEE, Volume 7, January 2019, Pages 5368 – 5373, DOI 10.1109/ACCESS.2018.2889311 [www] [pdf]
M. Safeea, R. Bearee, P. Neto, Reducing the Computational Complexity of Mass-Matrix Calculation for High DOF Robots, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, October 2018, Pages 5614-5619, DOI 10.1109/IROS.2018.8593775 [www] [pdf]
A. Brás, P. Neto, Unsupervised Feature Extraction from RGB-D Data for Object Classification: a Case Study on the YCB Object and Model Set, IECON 2018 – 44th Annual Conference of the IEEE Industrial Electronics Society, Washington DC, USA, October 2018, Pages 3673-3678, DOI 10.1109/IECON.2018.8591500 [www] [pdf]
N. Mendes, M. Safeea, P. Neto, Flexible programming and orchestration of collaborative robotic manufacturing systems, 2018 IEEE 16th International Conference on Industrial Informatics (INDIN), Porto, Portugal, July 2018, Pages 913-918, DOI 10.1109/INDIN.2018.8472058 [www] [pdf]
A. Brás, M. Simão, P. Neto, Gesture Recognition from Skeleton Data for Intuitive Human-Machine Interaction, TE2018: The 25th International Conference on Transdisciplinary Engineering, IOSpress, Volume 7, July 2018, Pages 271-280, DOI 10.3233/978-1-61499-898-3-271 [www]
M. Safeea, P. Neto, Human-Robot Collision Avoidance for Industrial Robots: A V-REP Based Solution, TE2018: The 25th International Conference on Transdisciplinary Engineering, IOSpress, Volume 7, July 2018, Pages 301-309, DOI 10.3233/978-1-61499-898-3-301 [www]
M. Simão, P. Neto, O. Gibaru, Using data dimensionality reduction for recognition of incomplete dynamic gestures, Pattern Recognition Letters, Elsevier, Volume 99, November 2017, Pages 32-38, DOI 10.1016/j.patrec.2017.01.003 [www]
J. Lopes, M. Simão, N. Mendes, M. Safeea, J. Afonso, P. Neto, Hand/arm gesture segmentation by motion using IMU and EMG Sensing, Procedia Manufacturing, Elsevier, Volume 11, September 2017, Pages 107-113, DOI 10.1016/j.promfg.2017.07.158 [www]
M. Safeea, N. Mendes, P. Neto, Minimum Distance Calculation for Safe Human Robot Interaction, Procedia Manufacturing, Elsevier, Volume 11, September 2017, Pages 99-106, DOI 10.1016/j.promfg.2017.07.157 [www]
N. Mendes, J. Ferrer, J. Vitorino, M. Safeea, P. Neto, Human Behavior and Hand Gesture Classification for Smart Human-robot Interaction, Procedia Manufacturing, Elsevier, Volume 11, September 2017, Pages 91-98, DOI 10.1016/j.promfg.2017.07.156 [www]
C. Silva, V. Ribeiro, P. Coelho, V. Magalhães, P. Neto, Job Shop Flow Time Prediction using Neural Networks, Procedia Manufacturing, Elsevier, Volume 11, September 2017, Pages 1767-1773, DOI 10.1016/j.promfg.2017.07.309 [www]
N. Silva, L. M. Ferreira, C. Silva, V. Magalhães, P. Neto, Improving Supply Chain Visibility With Artificial Neural Networks, Procedia Manufacturing, Elsevier, Volume 11, September 2017, Pages 2083-2090, DOI 10.1016/j.promfg.2017.07.329 [www]
M. Tavakoli, A. Sayuk, J. Lourenço, P. Neto, Anthropomorphic finger for grasping applications: 3D printed endoskeleton in a soft skin, The International Journal of Advanced Manufacturing Technology, Springer, Volume 91, July 2017, Pages 2607–2620, DOI 10.1007/s00170-016-9971-8 [www] [pdf]
M. Simão, P. Neto, O. Gibaru, Unsupervised Gesture Segmentation by Motion Detection of a Real-Time Data Stream, IEEE Transactions on Industrial Informatics, IEEE, Volume 13, Issue 2, April 2017, Pages 473-481, DOI 10.1109/TII.2016.2613683 [www] [pdf]