Distance-directed Target Searching for a Deep Visual Servo SMA Driven Soft Robot Using Reinforcement Learning

Liu, Wuji; Jing, Zhongliang; Pan, Han; Qiao, Liyan; Leung, Henry; Chen, Wujun

doi:10.1007/s42235-020-0102-8

Cited by 39 publications

(25 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al 65 introduced an 18-DOF SMA-driven soft robot for target searching. Lai et al 66,67 [68][69][70][71][72][73][74][75] and then upgraded it to a two-segment robot.…”

Section: F I G U R E 1 Taxonomy Of Continuum Robots Based On Actuatio...mentioning

confidence: 99%

“…Different modelling approaches have been employed to date, but the efficiency and generalisability of the models are still debatable. Some researchers have derived the kinematic and static models using analytical/numerical modelling approaches, including constant curvature-based methods, 36,39,46,50,52,53,56,59,61,64,67,68,70,75,76,[88][89][90][94][95][96][97][98] Denavit-Hartenberg method, 54 geometric methods, 38,47,48,55,65,83,86,99,100 Cosserat rod theory, 73,85,87 Euler-Bernoulli beam theory, 81 and the principle of virtual work. 84 A set of estimation/approximation-based methods was employed to derive the Jacobian of a CR, including Fourier series, 37 local Gaussian process regression, 91 column-bycolumn independent actuation, 33 numerical approach, 35,49 datadriven method, 57 Kalman filter (KF), 45 and feed-forward neural networks.…”

Section: Modelling Of Continuum Robotsmentioning

confidence: 99%

“…On the other hand, non-medical imaging systems comprised of a single digital camera in different scales, 33,51,65,66,[71][72][73][74]76,83,86,90,93,97,100,104 or a stereo vision system 38,39,58,62,64,67,84,85,87,94,99 have been employed to capture the intended state of CRs. Stereo vision has been implemented either by a single stereo camera or via forming a stereo system using several digital cameras/webcams.…”

Section: Imaging Devicementioning

confidence: 99%

See 2 more Smart Citations

Visual servoing of continuum robots: Methods, challenges, and prospects

Nazari

Zareinia

Janabi–Sharifi

2022

Robotics Computer Surgery

View full text Add to dashboard Cite

Background Recent advancements in continuum robotics have accentuated developing efficient and stable controllers to handle shape deformation and compliance. The control of continuum robots (CRs) using physical sensors attached to the robot, particularly in confined spaces, is difficult due to their limited accuracy in three‐dimensional deflections and challenging localisation. Therefore, using non‐contact imaging sensors finds noticeable importance, particularly in medical scenarios. Accordingly, given the need for direct control of the robot tip and notable uncertainties in the kinematics and dynamics of CRs, many papers have focussed on the visual servoing (VS) of CRs in recent years. Methods The significance of this research towards safe human‐robot interaction has fuelled our survey on the previous methods, current challenges, and future opportunities. Results Beginning with actuation modalities and modelling approaches, the paper investigates VS methods in medical and non‐medical scenarios. Conclusions Finally, challenges and prospects of VS for CRs are discussed, followed by concluding remarks.

show abstract

“…Liu et al 65 introduced an 18-DOF SMA-driven soft robot for target searching. Lai et al 66,67 [68][69][70][71][72][73][74][75] and then upgraded it to a two-segment robot.…”

Section: F I G U R E 1 Taxonomy Of Continuum Robots Based On Actuatio...mentioning

confidence: 99%

Section: Modelling Of Continuum Robotsmentioning

confidence: 99%

Section: Imaging Devicementioning

confidence: 99%

See 1 more Smart Citation

Visual servoing of continuum robots: Methods, challenges, and prospects

Nazari

Zareinia

Janabi–Sharifi

2022

Robotics Computer Surgery

View full text Add to dashboard Cite

show abstract

“…In the aspect of control, the study of manipulator control for soft robots has achieved lots of attention. Due to the controllability of pressure control, the manipulator can accommodate different grasping working conditions [16][17][18]. Most researchers mainly studied the fluid hydraulic actuation [19][20][21][22][23][24] and pneumatic actuation [25][26][27][28] in the field of soft robot.…”

Section: Introductionmentioning

confidence: 99%

An Investigation on the Grasping Position Optimization-Based Control for Industrial Soft Robot Manipulator

Zhang

et al. 2021

Machines

View full text Add to dashboard Cite

Mitigating fatigue damage and improving grasping performance are the two main challenging tasks of applying the soft manipulator into industrial production. In this paper, the grasping position optimization-based control strategy is proposed for the soft manipulator and the corresponding characteristics are studied theoretically and experimentally. Specifically, based on the simulation, the resultant stress of step-function-type channels at the same pressure condition that was smallest compared with those of sine-function- and ramp-function-type channels, hence, a pneumatic network with step-function-type channels was selected for the proposed soft manipulator. Furthermore, in order to improve the grasping performance, the kinematics, mechanical, and grasping modeling for the soft manipulator were established, and a control strategy considering the genetic algorithm is introduced to detect the optimal position of the soft manipulator. The corresponding fabrication process and experiments were conducted to cross verify the results of the modeling and the control strategy. It is demonstrated that the internal pressure of the soft manipulator was reduced by 13.05% at the optimal position, which effectively helped mitigate the fatigue damage of the soft manipulator and prolonged the lifespan.

show abstract

“…A model-based RL was developed to allow computationally efficient closed-loop dynamic control on a soft manipulator by learning the forward dynamics, sampling the control policies, and learning a predictive controller [11]. A model-based RL without explicit prior knowledge was implemented for visual-servoing of a continuum robot during simple target tracking [12]. Model-free approaches, such as Q-learning, were implemented on a pneumatic actuated planar soft manipulator [13], [14].…”

Section: Introductionmentioning

confidence: 99%

Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning

Yan

et al. 2021

Preprint

View full text Add to dashboard Cite

Continuum robotic manipulators are increasingly adopted in minimal invasive surgery. However, their nonlinear behavior is challenging to model accurately, especially when subject to external interaction, potentially leading to poor control performance. In this letter, we investigate the feasibility of adopting a model-free multiagent reinforcement learning (RL), namely multiagent deep Q network (MADQN), to control a 2-degree of freedom (DoF) cable-driven continuum surgical manipulator. The control of the robot is formulated as a one-DoF, one agent problem in the MADQN framework to improve the learning efficiency. Combined with a shielding scheme that enables dynamic variation of the action set boundary, MADQN leads to efficient and importantly safer control of the robot. Shielded MADQN enabled the robot to perform point and trajectory tracking with submillimeter root mean square errors under external loads, soft obstacles, and rigid collision, which are common interaction scenarios encountered by surgical manipulators. The controller was further proven to be effective in a miniature continuum robot with high structural nonlinearitiy, achieving trajectory tracking with submillimeter accuracy under external payload.

show abstract

Distance-directed Target Searching for a Deep Visual Servo SMA Driven Soft Robot Using Reinforcement Learning

Cited by 39 publications

References 25 publications

Visual servoing of continuum robots: Methods, challenges, and prospects

Visual servoing of continuum robots: Methods, challenges, and prospects

An Investigation on the Grasping Position Optimization-Based Control for Industrial Soft Robot Manipulator

Towards Safe Control of Continuum Manipulator Using Shielded Multiagent Reinforcement Learning

Contact Info

Product

Resources

About