Peg-in-hole assembly based on master-slave coordination for a compliant dual-arm robot

Huang, Yanjiang; Zheng, Yanglong; Wang, Nianfeng; Ota, Jun; Zhang, Xianmin

doi:10.1108/aa-10-2018-0164

Cited by 22 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, the separate position or orientation DMP has been studied widely [35]; however, research on the composite DMPs, modelling the position and orientation simultaneously, is not common. In real practice, most manipulation skills often mix the position and orientation skills, which requires robots to satisfy the specific position constraints as well the orientation for many tasks, such as polishing, spraying, assembly [36,37]. In addition, for human-robot interaction tasks, such as two partners collaborating an object handover interaction, the target position is always changing.…”

Section: Composite Position and Orientation Dynamic Movement Primitivesmentioning

confidence: 99%

Composite dynamic movement primitives based on neural networks for human–robot skill transfer

Wang

Yang

2021

Neural Comput & Applic

View full text Add to dashboard Cite

In this paper, composite dynamic movement primitives (DMPs) based on radial basis function neural networks (RBFNNs) are investigated for robots’ skill learning from human demonstrations. The composite DMPs could encode the position and orientation manipulation skills simultaneously for human-to-robot skills transfer. As the robot manipulator is expected to perform tasks in unstructured and uncertain environments, it requires the manipulator to own the adaptive ability to adjust its behaviours to new situations and environments. Since the DMPs can adapt to uncertainties and perturbation, and spatial and temporal scaling, it has been successfully employed for various tasks, such as trajectory planning and obstacle avoidance. However, the existing skill model mainly focuses on position or orientation modelling separately; it is a common constraint in terms of position and orientation simultaneously in practice. Besides, the generalisation of the skill learning model based on DMPs is still hard to deal with dynamic tasks, e.g., reaching a moving target and obstacle avoidance. In this paper, we proposed a composite DMPs-based framework representing position and orientation simultaneously for robot skill acquisition and the neural networks technique is used to train the skill model. The effectiveness of the proposed approach is validated by simulation and experiments.

show abstract

Section: Composite Position and Orientation Dynamic Movement Primitivesmentioning

confidence: 99%

Composite dynamic movement primitives based on neural networks for human–robot skill transfer

Wang

Yang

2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…For solving the peg-in-hole with a dual arm robot, Ref. [17] describes the problem of insertion as a search problem of the hole, where force/torque (F/T) sensor data was used to identify the different assembly stages using thresholds. The challenge with thresholds is the continuous tuning due to changes in the assembly conditions.…”

Section: Related Workmentioning

confidence: 99%

“…Another study proposes skill acquisition, where low accuracy of conventional methods is compensated by a learning method without parameter tuning [16]. For the case of peg-in-hole with a dual arm robot, a three step method inspired by humans operations is designed in [17]. Seed works that inspired many recent studies such as force/toque maps [18], self-organizing maps [19], reinforcement learning [20], and event discrete systems [21].…”

Section: Introductionmentioning

confidence: 99%

Dual-Arm Peg-in-Hole Assembly Using DNN with Double Force/Torque Sensor

et al. 2021

View full text Add to dashboard Cite

Assembly tasks executed by a robot have been studied broadly. Robot assembly applications in industry are achievable by a well-structured environment, where the parts to be assembled are located in the working space by fixtures. Recent changes in manufacturing requirements, due to unpredictable demanded products, push the factories to seek new smart solutions that can autonomously recover from failure conditions. In this way, new dual arm robot systems have been studied to design and explore applications based on its dexterity. It promises the possibility to get rid of fixtures in assembly tasks, but using less fixtures increases the uncertainty on the location of the components in the working space. It also increases the possibility of collisions during the assembly sequence. Under these considerations, adding perception such as force/torque sensors have been done to produce useful data to perform control actions. Unfortunately, the interaction forces between mating parts produced non-linear behavior. Consequently, machine learning algorithms have been considered an alternative tool to avoid the non-linearity. In this work we introduce an assembly strategy for an industrial dual arm robot based on the combination of a discrete event controller and Deep Neural Networks (DNN) to solve the peg-in-hole assembly. Our results show the difference between the use of DNN with one and with two force/torque sensors during the assembly task and demonstrate a 30% increase in the assembly success ratio when using a double force/torque sensor.

show abstract

“…where Y is a column vector composed by the q 1 -q 7 , fkine() is the forwards kinematics function, 7 R 0 is the attitude transformation matrix, and 7 P 0 is the position vector of the last frame with respect to the base frame.…”

Section: Forward Kinematicsmentioning

confidence: 99%

“…Compared with a single-arm space robot, a multiarm robotic system has much more dexterity and flexibility and is capable of completing more complex tasks. 7 Especially, the humanoid robot astronaut has arms like human beings and has the unique advantages of a wide range of applications, strong collaboration ability, high reliability, and ability extension, which can serve the astronaut better. 8 In recent years, NASA's astronaut Robonaut 2 and Japanese robot astronaut KIROBO have launched into the international space station to serve the astronaut.…”

Section: Introductionmentioning

confidence: 99%

Coordinated compliance control of dual-arm robot astronaut for payload operation

Yan

Han³

et al. 2021

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Dual-arm robot astronaut has more general and dexterous operation ability than single-arm robot, and it can interact with astronaut more friendly. The robot will inevitably use both arms to grasp payloads and transfer them. The force control of the arms in closed chains is an important problem. In this article, the coordinated kinematic and dynamic equations of the dual-arm astronaut are established by considering the closed-chain constraint relationship. Two compliance control methods for dual-arm astronaut coordinated payload manipulating are proposed. The first method is called master–slave force control and the second is the shared force control. For the former, the desired path and operational force of the master arm should be given in advance and that of slave arm are calculated from the dual-arm robot closed-chain constraint equation. In the share control mode, the desired path and end operational force of dual arms are decomposed from the dual-arm robot closed-chain constraint equation directly and equally. Finally, the two control algorithms are verified by simulation. The results of analysis of variance of the simulation data show that the two control methods have no obvious difference in the accuracy of force control but the second control method has a higher position control accuracy, and this proves that the master–slave mode is better for tasks with explicit force distribution requirements and the shared force control is especially suitable for a high-precision requirement.

show abstract

Peg-in-hole assembly based on master-slave coordination for a compliant dual-arm robot

Cited by 22 publications

References 31 publications

Composite dynamic movement primitives based on neural networks for human–robot skill transfer

Composite dynamic movement primitives based on neural networks for human–robot skill transfer

Dual-Arm Peg-in-Hole Assembly Using DNN with Double Force/Torque Sensor

Coordinated compliance control of dual-arm robot astronaut for payload operation

Contact Info

Product

Resources

About