Learning robotic milling strategies based on passive variable operational space interaction control

This paper addresses the problem of robotic cutting during disassembly of products for materials separation and recycling. Waste handling applications differ from milling in manufacturing processes, as they engender considerable variety and uncertainty in the parameters (e.g. hardness) of materials which the robot must cut. To address this challenge, we propose a learning-based approach incorporating elements of interaction control, in which the robot can adapt key parameters, such as feed rate, depth of cut, and mechanical compliance during task execution. We show how a mathematical model of cutting mechanics, embedded in a simulation environment, can be used to rapidly train the system without needing large amounts of data from physical cutting trials. The simulation approach was validated on a real robot setup based on four case study materials with varying structural and mechanical properties. We demonstrate the proposed method minimises process force and path deviations to a level similar to offline optimal planning methods, while the average time to complete a cutting task is within 25% of the optimum, at the expense of reduced volume of material removed per pass. A key advantage of our approach over similar works is that no prior knowledge about the material is required.

[1]  A. Billard,et al.  Learning From Demonstration and Interactive Control of Variable-Impedance to Cut Soft Tissues , 2022, IEEE/ASME Transactions on Mechatronics.

[2]  W. Dong,et al.  A Robotic Milling System Based on 3D Point Cloud , 2021, Machines.

[3]  Juliang Xiao,et al.  Multiple peg-in-hole compliant assembly based on a learning-accelerated deep deterministic policy gradient strategy , 2021, Ind. Robot.

[4]  Rustam Stolkin,et al.  Vision-Guided MPC for Robotic Path Following Using Learned Memory-Augmented Model , 2021, Frontiers in Robotics and AI.

[5]  Birgit Obst,et al.  GPU accelerated voxel-based machining simulation , 2021, The International Journal of Advanced Manufacturing Technology.

[6]  N. Hogan,et al.  Energy budgets for coordinate invariant robot control in physical human–robot interaction , 2021, Int. J. Robotics Res..

[7]  Jianzhong Yang,et al.  Contour error modeling and compensation of CNC machining based on deep learning and reinforcement learning , 2021, The International Journal of Advanced Manufacturing Technology.

[8]  Claudio Pacchierotti,et al.  Bilateral Teleoperation With Adaptive Impedance Control for Contact Tasks , 2021, IEEE Robotics and Automation Letters.

[9]  Akhil Garg,et al.  A hybrid disassembly framework for disassembly of electric vehicle batteries , 2021, International Journal of Energy Research.

[10]  Ying Tang,et al.  Meta-Reinforcement Learning of Machining Parameters for Energy-Efficient Process Control of Flexible Turning Operations , 2021, IEEE Transactions on Automation Science and Engineering.

[11]  R. Stolkin,et al.  Path planning for mobile manipulator robots under non-holonomic and task constraints , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  K. Harada,et al.  Variable Compliance Control for Robotic Peg-in-Hole Assembly: A Deep Reinforcement Learning Approach , 2020, Applied Sciences.

[13]  Lixian Zhang,et al.  Actor-Critic Reinforcement Learning for Control With Stability Guarantee , 2020, IEEE Robotics and Automation Letters.

[14]  Xionghui Zhou,et al.  An effective and automatic approach for parameters optimization of complex end milling process based on virtual machining , 2020, J. Intell. Manuf..

[15]  Daniel Goldmann,et al.  Disassembly 4.0: A Review on Using Robotics in Disassembly Tasks as a Way of Automation , 2020, Chemie Ingenieur Technik.

[16]  Valerio Ortenzi,et al.  Planning Maximum-Manipulability Cutting Paths , 2020, IEEE Robotics and Automation Letters.

[17]  Silvio Savarese,et al.  Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Javad Lavaei,et al.  Stability-Certified Reinforcement Learning: A Control-Theoretic Perspective , 2018, IEEE Access.

[19]  Mohammad Ali Badamchizadeh,et al.  Designing of robust adaptive passivity-based controller based on reinforcement learning for nonlinear port-Hamiltonian model with disturbance , 2018, Int. J. Control.

[20]  Valerio Ortenzi,et al.  Vision-Based Framework to Estimate Robot Configuration and Kinematic Constraints , 2018, IEEE/ASME Transactions on Mechatronics.

[21]  Han Ding,et al.  Posture optimization methodology of 6R industrial robots for machining using performance evaluation indexes , 2017 .

[22]  Marcin Andrychowicz,et al.  Sim-to-Real Transfer of Robotic Control with Dynamics Randomization , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Valerio Ortenzi,et al.  Hybrid motion/force control: a review , 2017, Adv. Robotics.

[24]  Gang Xiong,et al.  A Feed-Direction Stiffness Based Trajectory Optimization Method for a Milling Robot , 2017, ICIRA.

[25]  Alec Radford,et al.  Proximal Policy Optimization Algorithms , 2017, ArXiv.

[26]  Hsiu-Chin Lin,et al.  Kinematics-based estimation of contact constraints using only proprioception , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[27]  Valerio Ortenzi,et al.  Projected inverse dynamics control and optimal control for robots in contact with the environment: A comparison , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Riccardo Muradore,et al.  An Energy Tank-Based Interactive Control Architecture for Autonomous and Teleoperated Robotic Surgery , 2015, IEEE Transactions on Robotics.

[29]  Supachai Vongbunyong,et al.  Learning and revision in cognitive robotics disassembly automation , 2015 .

[30]  Valerio Ortenzi,et al.  An experimental study of robot control during environmental contacts based on projected operational space dynamics , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[31]  Cristian Secchi,et al.  A tank-based approach to impedance control with variable stiffness , 2013, 2013 IEEE International Conference on Robotics and Automation.

[32]  Supachai Vongbunyong,et al.  Basic behaviour control of the vision‐based cognitive robotic disassembly automation , 2013 .

[33]  Yuval Tassa,et al.  MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[34]  Jun Nakanishi,et al.  Operational Space Control: A Theoretical and Empirical Comparison , 2008, Int. J. Robotics Res..

[35]  A. Schaft,et al.  Port-controlled Hamiltonian systems : modelling origins and systemtheoretic properties , 1992 .

[36]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[37]  Yan Wang,et al.  Hybrid Trajectory and Force Learning of Complex Assembly Tasks: A Combined Learning Framework , 2021, IEEE Access.

[38]  K. A. Desai,et al.  Amalgamation of Physics-Based Cutting Force Model and Machine Learning Approach for End Milling Operation , 2020 .

[39]  C. Ott,et al.  Passivity-based variable impedance control for redundant manipulators , 2020, IFAC-PapersOnLine.

[40]  Michael F. Zaeh,et al.  Model-based Planning of Machining Operations for Industrial Robots , 2019, Procedia CIRP.

[41]  Erardo Leal-Muñoz,et al.  Feasibility of machining using low payload robots , 2019, Procedia Manufacturing.

[42]  Lutfi Taner Tunc,et al.  Improved stable conditions in robotic milling by kinematic redundancy , 2019, Procedia CIRP.

[43]  Edouard Rivière-Lorphèvre,et al.  Cutting Force Prediction in Robotic Machining , 2019, Procedia CIRP.

[44]  Luke Berglind,et al.  Discrete Cutting Force Model for 5-Axis Milling with Arbitrary Engagement and Feed Direction , 2017 .

[45]  E. Armarego,et al.  The Machining of Metals , 1969 .