Compliant manipulation for peg-in-hole: Is passive compliance a key to learn contact motion?

Yun, Seung-kook

doi:10.1109/robot.2008.4543437

Cited by 17 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the strategy of passive control, some compliant mechanical devices are used to assist the peg insertion into the hole. Yun et al [30] integrated passive compliance with a learning method to accomplish the peg-in-hole procedure. The compliant device consists of torsional springs and dampers.…”

Section: Introductionmentioning

confidence: 99%

Peg-in-Hole Assembly Based on Six-Legged Robots with Visual Detecting and Force Sensing

Zhao

Gao

Zhao

et al. 2020

Sensors

View full text Add to dashboard Cite

Manipulators with multi degree-of-freedom (DOF) are widely used for the peg-in-hole task. Compared with manipulators, six-legged robots have better mobility performance apart from completing operational tasks. However, there are nearly no previous studies of six-legged robots performing the peg-in-hole task. In this article, a peg-in-hole approach for six-legged robots is studied and experimented with a six-parallel-legged robot. Firstly, we propose a method whereby a vision sensor and a force/torque (F/T) sensor can be used to explore the relative location between the hole and peg. According to the visual information, the robot can approach the hole. Next, based on the force feedback, the robot plans the trajectory in real time to mate the peg and hole. Then, during the insertion, admittance control is implemented to guarantee the smooth insertion. In addition, during the whole assembly process, the peg is held by the gripper and attached to the robot body. Connected to the body, the peg has sufficient workspace and six DOF to perform the assembly task. Finally, experiments were conducted to prove the suitability of the approach.

show abstract

Section: Introductionmentioning

confidence: 99%

Peg-in-Hole Assembly Based on Six-Legged Robots with Visual Detecting and Force Sensing

Zhao

Gao

Zhao

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

High Precision Peg-in-Hole Assembly Approach Based on Sensitive Robotics and Deep Recurrent Q-Learning

Afifi,

Schneider,

Kanso

et al. 2023

Annals of Scientific Society for Assembly, Handling and Industrial Robotics 2022

View full text Add to dashboard Cite

Sensitive robot systems are used in various assembly and manufacturing technologies. Assembly is a vital activity that requires high-precision robotic manipulation. One of the challenges faced in high precision assembly tasks is when the task precision exceeds the robot’s precision. In this research, Deep Q-Learning (DQN) is used to perform a very tight clearance Peg-in-Hole assembly task. Moreover, recurrence is introduced into the system via a Long-Short Term Memory (LSTM) layer to tackle DQN drawbacks. The LSTM layer has the ability to encode prior decisions, allowing the agent to make more informed decisions. The robot’s sensors are used to represent the state. Despite the tight hole clearance, this method was able to successfully achieve the task at hand, which has been validated by a 7-DOF Kuka LBR iiwa sensitive robot. This paper will focus on the search phase. Furthermore, our approach has the advantage of working in environments that vary from the learned environment.

show abstract

Improving performance of robots using human-inspired approaches: a survey

Qiao

Zhong

Chen

et al. 2022

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Compliant manipulation for peg-in-hole: Is passive compliance a key to learn contact motion?

Cited by 17 publications

References 17 publications

Peg-in-Hole Assembly Based on Six-Legged Robots with Visual Detecting and Force Sensing

Peg-in-Hole Assembly Based on Six-Legged Robots with Visual Detecting and Force Sensing

High Precision Peg-in-Hole Assembly Approach Based on Sensitive Robotics and Deep Recurrent Q-Learning

Improving performance of robots using human-inspired approaches: a survey

Contact Info

Product

Resources

About