Fast dual-arm manipulation using variable admittance control: Implementation and experimental results

Bjerkeng, Magnus; Schrimpf, Johannes; Myhre, Torstein A.; Pettersen, Kristin Y.

doi:10.1109/iros.2014.6943235

Cited by 15 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is equipped with joint servo controllers produced by the robot manufacturer, and is both highly suitable and commonly used for experimental verification of control algorithms [24]- [27]. This paper is organized as follows: Section II describes the UR5, the overall control structure and communication protocol used in the experiments.…”

Section: Introductionmentioning

confidence: 99%

Experimental results for set-based control within the singularity-robust multiple task-priority inverse kinematics framework

Moe

Antonelli

Pettersen

et al. 2015

2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)

Self Cite

View full text Add to dashboard Cite

Abstract-Inverse kinematics algorithms are commonly used in robotic systems to achieve desired behavior, and several methods exist to ensure the achievement of numerous tasks simultaneously. The multiple task-priority inverse kinematics framework allows a consideration of tasks in a prioritized order by projecting task velocities through the null-spaces of higher priority tasks. Recent results have extended this framework from equality tasks to also handling set-based tasks, i.e. tasks that have an interval of valid values. The purpose of this paper is to further investigate and experimentally validate this algorithm and its properties. In particular, this paper presents experimental results where a number of both set-based and equality tasks have been implemented on the 6 Degree of Freedom UR5 which is an industrial robotic arm from Universal Robots. The experiments validate the theoretical results.

show abstract

Section: Introductionmentioning

confidence: 99%

Experimental results for set-based control within the singularity-robust multiple task-priority inverse kinematics framework

Moe

Antonelli

Pettersen

et al. 2015

2015 IEEE International Conference on Robotics and Biomimetics (ROBIO)

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, besides the required modeling efforts, it is limited by the human teaching process, which introduces a different set of assumptions on top of the previous ones, limiting its applicability to semistructured environments. Besides that, work on centralized methods, mostly focuses on cooperative object manipulation [4]- [6], [11], [14], [26] and highly relies on accurate and complex modeling of the underlying system dynamics.…”

Section: Related Workmentioning

confidence: 99%

“…Based on the dynamics model, commonly a hierarchical control strategy through multiple loops is applied, where the outer loops realizes the main objective such as desired object movements and the inner loop accounts to generate a firm grasp and bounded internal forces. [4]- [6], [11], [14], [26]. The particular control loops can utilize any control strategy.…”

Section: A Controllermentioning

confidence: 99%

Learning to Centralize Dual-Arm Assembly

Aljalbout¹

2021

Preprint

View full text Add to dashboard Cite

Even though industrial manipulators are widely used in modern manufacturing processes, deployment in unstructured environments remains an open problem. To deal with variety, complexity and uncertainty of real world manipulation tasks a general framework is essential. In this work we want to focus on assembly with humanoid robots by providing a framework for dual-arm peg-in-hole manipulation. As we aim to contribute towards an approach which is not limited to dualarm peg-in-hole, but dual-arm manipulation in general, we keep modeling effort at a minimum. While reinforcement learning has shown great results for single-arm robotic manipulation in recent years, research focusing on dual-arm manipulation is still rare. Solving such tasks often involves complex modeling of interaction between two manipulators and their coupling at a control level. In this paper, we explore the applicability of model-free reinforcement learning to dual-arm manipulation based on a modular approach with two decentralized singlearm controllers and a single centralized policy. We reduce modeling effort to a minimum by using sparse rewards only. We demonstrate the effectiveness of the framework on dualarm peg-in-hole and analyze sample efficiency and success rates for different action spaces. Moreover, we compare results on different clearances and showcase disturbance recovery and robustness, when dealing with position uncertainties. Finally we zero-shot transfer policies trained in simulation to the realworld and evaluate their performance.

show abstract

“…Ren et al (2016) built an impedance architecture that showed adaptive or impedance behaviors to different external forces, and they verified this by using a humanoid dual-arm robot. Bjerkeng et al (2014) proposed a variable admittance control structure that assumed high-speed operation and used a dual-arm system to move an object. Han et al (2019) used impedance control to realize the coordinated compliance of a dual-arm robot without any force or torque sensors.…”

Section: Introductionmentioning

confidence: 99%

A dual-arm manipulation strategy using position/force errors and Kalman filter

Yang

Chen

Lin

2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

This paper presents a new coordination manipulation strategy for a custom-made dual-arm robot. With master and slave coordination infrastructure, both spatial relation and sense of touch are considered to hold an object stably. Given the known trajectory of the master arm, the slave arm fuses position and force commands by using the Kalman filter to yield optimal compensation amounts. The proposed strategy has been experimentally evaluated, and the results confirm that it was capable of dealing with fragile and flexible objects. In addition, the influence of the loop time of the digital controller on force control for this task was also investigated in mathematical and simulated ways. Furthermore, a series of experiments were designed to explore the effects that have influences on errors in force control. The main factors that affect force control error were analyzed.

show abstract

Fast dual-arm manipulation using variable admittance control: Implementation and experimental results

Cited by 15 publications

References 33 publications

Experimental results for set-based control within the singularity-robust multiple task-priority inverse kinematics framework

Experimental results for set-based control within the singularity-robust multiple task-priority inverse kinematics framework

Learning to Centralize Dual-Arm Assembly

A dual-arm manipulation strategy using position/force errors and Kalman filter

Contact Info

Product

Resources

About