公开(公告)号：US12097619B2

公开(公告)日：2024-09-24

申请号：US17935293

申请日：2022-09-26

Applicant: FANUC CORPORATION

Inventor： Hsien-Chung Lin ,  Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16

CPC classification number: B25J9/1633 ,  B25J9/163 ,  B25J9/1638 ,  B25J9/1641 ,  B25J9/1651 ,  B25J9/1664

Abstract: A method and system for robot motion control using a model predictive control (MPC) technique including torque rate control and suppression of end tooling oscillation. An MPC module includes a robot dynamics model which inherently reflects response nonlinearities associated with changes in robot configuration, and an optimization solver having an objective function with a torque rate term and inequality constraints defining bounds on both torque and torque rate. The torque rate control in the MPC module provides an effective means of controlling jerk in robot joints, while accurately modeling robot dynamics as the robot changes configuration during a motion program. End tooling oscillation dynamics may also be included in the MPC objective function and constraints in order to automatically control end tooling vibration in the calculations of the MPC module.

公开(公告)号：US20240201677A1

公开(公告)日：2024-06-20

申请号：US18068760

申请日：2022-12-20

Applicant: FANUC CORPORATION

Inventor： Kaimeng Wang ,  Yu Zhao

IPC: G05B19/423 ,  B25J9/16 ,  G06N3/092

CPC classification number: G05B19/423 ,  B25J9/1697 ,  G06N3/092

Abstract: A method for teaching a robot to perform an operation including human demonstration using inverse reinforcement learning and a reinforcement learning reward function. A demonstrator performs an operation with contact force and workpiece motion data recorded. The demonstration data is used to train an encoder neural network which captures the human skill, defining a Gaussian distribution of probabilities for a set of states and actions. Encoder and decoder neural networks are then used in live robotic operations, where the decoder is used by a robot controller to compute actions based on force and motion state data from the robot. After each operation, the reward function is computed, with a Kullback-Leibler divergence term which rewards a small difference between human demonstration and robot operation probability curves, and a completion term which rewards a successful operation by the robot. The decoder is trained using reinforcement learning to maximize the reward function.

公开(公告)号：US12179362B2

公开(公告)日：2024-12-31

申请号：US18594139

申请日：2024-03-04

Applicant: FANUC CORPORATION

Inventor： Yu Zhao ,  Tetsuaki Kato

IPC: B23P21/00 ,  B25J9/16

Abstract: A method for tuning the force control parameters for a general robotic assembly operation. The method uses numerical optimization to evaluate different combinations of the parameters for a robot force controller in a simulation environment that is built based on a real-world robotic setup. This method performs autonomous tuning for assembly tasks based on closed loop force control simulation, where random samples from a distribution of force control parameter values are evaluated, and the optimization routine iteratively redefines the parameter distribution to find optimal values of the parameters. Each simulated assembly is evaluated using multiple simulations including random part positioning uncertainties. The performance of each simulated assembly is evaluated by the average of the simulation results, thus ensuring that the selected control parameters will perform well in most possible conditions. Once the parameters have been optimized, they are applied to real robots to perform the actual assembly operation.

公开(公告)号：US11813756B2

公开(公告)日：2023-11-14

申请号：US17226179

申请日：2021-04-09

Applicant: FANUC CORPORATION

Inventor： Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16

CPC classification number: B25J9/1687

Abstract: A robot motion planning technique for component assembly operations. Inputs to the motion planning technique include geometric models of the components being assembled, and initial and target configurations. The method begins at a tightly-constrained target or final configuration and plans in the direction of a loosely-constrained initial configuration. A randomly-sampled waypoint configuration is proposed, followed by a local search for feasible configurations which generates nodes that extend a path toward the initial configuration while sliding through the tightly-constrained region. The local search can be repeated multiple times for a given randomly-sampled configuration. When a completed path is found, the action sequence is trimmed to eliminate unnecessary extraneous motions in the loosely-constrained region. The disclosed method dramatically reduces the number of unproductive configurations evaluated and finds assembly solutions much faster in comparison to known tree-based motion planning methods.

公开(公告)号：US20250026009A1

公开(公告)日：2025-01-23

申请号：US18356497

申请日：2023-07-21

Applicant: FANUC CORPORATION

Inventor： Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16

Abstract: A method and system for robot skill learning for high precision assembly tasks employing a compliance controller. A reinforcement learning (RL) controller is pre-trained in an offline mode using human demonstration data, where several repetitions of the demonstration are performed while collecting state and action data for each repetition. The demonstration data is used to pre-train a neural network in the RL controller, with no interaction of the RL controller with the compliance controller/robot system. Following pre-training, the RL controller is moved to online production where it is coupled to the compliance controller/robot system in a self-learning mode. During self-learning, the neural network-based RL controller uses action, state and reward data to continue learning correlations between states and effective actions. Co-training is provided as needed during self-learning, where a human operator overrides the RL controller actions to ensure successful assembly operations, which improves the learned performance of the RL controller.

公开(公告)号：US20250026008A1

公开(公告)日：2025-01-23

申请号：US18355914

申请日：2023-07-20

Applicant: FANUC CORPORATION

Inventor： Kaimeng Wang ,  Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16

Abstract: A method for robot path planning using skills extracted from human-taught motion programs applied to a new obstacle environment. A three-dimensional convolutional neural network is used to extract features characterizing an obstacle environment, where the feature vector representation of the obstacles overcomes problems encountered when using point cloud obstacle data. The obstacle feature data and robot path start and goal points are provided to an encoder/decoder neural network system which is trained to extract skills from a database of human-generated motion programs. The encoder/decoder neural network system produces a distribution of waypoints for the current obstacle environment and start/goal points. The distribution of waypoints is used to perform a final collision-free path generation using either a rapidly-exploring random tree (RRT) technique or an optimization-based technique.

公开(公告)号：US20240208053A1

公开(公告)日：2024-06-27

申请号：US18594139

申请日：2024-03-04

Applicant: FANUC CORPORATION

Inventor： Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16 ,  B23P21/00

CPC classification number: B25J9/1661 ,  B23P21/00

Abstract: A method for tuning the force control parameters for a general robotic assembly operation. The method uses numerical optimization to evaluate different combinations of the parameters for a robot force controller in a simulation environment that is built based on a real-world robotic setup. This method performs autonomous tuning for assembly tasks based on closed loop force control simulation, where random samples from a distribution of force control parameter values are evaluated, and the optimization routine iteratively redefines the parameter distribution to find optimal values of the parameters. Each simulated assembly is evaluated using multiple simulations including random part positioning uncertainties. The performance of each simulated assembly is evaluated by the average of the simulation results, thus ensuring that the selected control parameters will perform well in most possible conditions. Once the parameters have been optimized, they are applied to real robots to perform the actual assembly operation.

公开(公告)号：US20210323154A1

公开(公告)日：2021-10-21

申请号：US17226179

申请日：2021-04-09

Applicant: FANUC CORPORATION

Inventor： Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16 ,  B25J9/02

Abstract: A robot motion planning technique for component assembly operations. Inputs to the motion planning technique include geometric models of the components being assembled, and initial and target configurations. The method begins at a tightly-constrained target or final configuration and plans in the direction of a loosely-constrained initial configuration. A randomly-sampled waypoint configuration is proposed, followed by a local search for feasible configurations which generates nodes that extend a path toward the initial configuration while sliding through the tightly-constrained region. The local search can be repeated multiple times for a given randomly-sampled configuration. When a completed path is found, the action sequence is trimmed to eliminate unnecessary extraneous motions in the loosely-constrained region. The disclosed method dramatically reduces the number of unproductive configurations evaluated and finds assembly solutions much faster in comparison to known tree-based motion planning methods.

公开(公告)号：US20210316453A1

公开(公告)日：2021-10-14

申请号：US16848189

申请日：2020-04-14

Applicant: FANUC CORPORATION

Inventor： Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16

Abstract: A method for controlling a robot to perform a complex assembly task such as insertion of a component with multiple pins or pegs into a structure with multiple holes. The method uses an impedance controller including multiple reference centers with one set of gain factors. Only translational gain factors are used—one for a spring force and one for a damping force—and no rotational gains. The method computes spring-damping forces from reference center positions and velocities using the gain values, and measures contact force and torque with a sensor coupled between the robot arm and the component being manipulated. The computed spring-damping forces are then summed with the measured contact force and torque, to provide a resultant force and torque at the center of gravity of the component. A new component pose is then computed based on the resultant force and torque using impedance controller calculations.

公开(公告)号：US20240116178A1

公开(公告)日：2024-04-11

申请号：US17935293

申请日：2022-09-26

Applicant: FANUC CORPORATION

Inventor： Hsien-Chung Lin ,  Yu Zhao ,  Tetsuaki Kato

IPC: B25J9/16

CPC classification number: B25J9/1633 ,  B25J9/163 ,  B25J9/1638 ,  B25J9/1641 ,  B25J9/1651 ,  B25J9/1664

Abstract: A method and system for robot motion control using a model predictive control (MPC) technique including torque rate control and suppression of end tooling oscillation. An MPC module includes a robot dynamics model which inherently reflects response nonlinearities associated with changes in robot configuration, and an optimization solver having an objective function with a torque rate term and inequality constraints defining bounds on both torque and torque rate. The torque rate control in the MPC module provides an effective means of controlling jerk in robot joints, while accurately modeling robot dynamics as the robot changes configuration during a motion program. End tooling oscillation dynamics may also be included in the MPC objective function and constraints in order to automatically control end tooling vibration in the calculations of the MPC module.