Control Strategies for Soft Robotic Manipulators: A Survey

Thuruthel, Thomas George; Ansari, Yasmin; Falotico, Egidio; Laschi, Cecilia

doi:10.1089/soro.2017.0007

Cited by 495 publications

(291 citation statements)

References 70 publications

Supporting

Mentioning

256

Contrasting

Unclassified

Order By: Relevance

“…Control of soft continuum arms have been widely explored through both model based and model free methods [10]. Traditional control methods are founded on first-principles based on mathematical models and use of analytical equations to capture the exact behavior within bounding assumptions.…”

Section: Introductionmentioning

confidence: 99%

“…Both implementations work on controlling planar 2D motions, and have a relatively small state-action space and use fixed steps during transitions. In the presented work, we extend this framework to a 3D setting rendered by the BR 2 continuum manipulator with highly nonlinear response characteristics between its actuation space (pneumatic pressure) and the task or the end effector space [10]. Additionally, we also incorporate the notion of adaptive steps to reduce the number of transitions to reach a target.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Satheeshbabu

Uppalapati

Chowdhary

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Soft robots undergo large nonlinear spatial deformations due to both inherent actuation and external loading. The physics underlying these deformations is complex, and often requires intricate analytical and numerical models. The complexity of these models may render traditional modelbased control difficult and unsuitable. Model-free methods offer an alternative for analyzing the behavior of such complex systems without the need for elaborate modeling techniques. In this paper, we present a model-free approach for open loop position control of a soft spatial continuum arm, based on deep reinforcement learning. The continuum arm is pneumatically actuated and attains a spatial workspace by a combination of unidirectional bending and bidirectional torsional deformation. We use Deep-Q Learning with experience replay to train the system in simulation. The efficacy and robustness of the control policy obtained from the system is validated both in simulation and on the continuum arm prototype for varying external loading conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Satheeshbabu

Uppalapati

Chowdhary

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…However, they use those models in an open-loop control scheme which may be problematic in the case of model error, change over time, or any kind of disturbance. A recent survey that explains the state of the field for soft and continuum robot control can be found in George Thuruthel et al (2018).…”

Section: Soft Robot Controlmentioning

confidence: 99%

Model-Based Control of Soft Actuators Using Learned Non-linear Discrete-Time Models

2019

View full text Add to dashboard Cite

Soft robots have the potential to significantly change the way that robots interact with the environment and with humans. However, accurately modeling soft robot and soft actuator dynamics in order to perform model-based control can be extremely difficult. Deep neural networks are a powerful tool for modeling systems with complex dynamics such as the pneumatic, continuum joint, six degree-of-freedom robot shown in this paper.Unfortunately it is also difficult to apply standard model-based control techniques using a neural net. In this work, we show that the gradients used within a neural net to relate system states and inputs to outputs can be used to formulate a linearized discrete state space representation of the system. Using the state space representation, model predictive control (MPC) was developed with a six degree of freedom pneumatic robot with compliant plastic joints and rigid links. Using this neural net model, we were able to achieve an average steady state error across all joints of approximately 1 and 2 • with and without integral control respectively. We also implemented a first-principles based model for MPC and the learned model performed better in terms of steady state error, rise time, and overshoot. Overall, our results show the potential of combining empirical modeling approaches with model-based control for soft robots and soft actuators.

show abstract

“…This is mainly caused by the difficulty in modelling the highly nonlinear characteristics of the soft robotic structure in comparison to the well-established modelling of its rigid-link counterparts [15]. Various techniques for the kinematic and dynamic control of soft robotic manipulators have been developed as reported in [16]. Obstacle avoidance for soft or continuum manipulator has also been reported in recent publications [17], [18], [19].…”

Section: Introductionmentioning

confidence: 99%

Model-Based Pose Control of Inflatable Eversion Robot With Variable Stiffness

Ataka

Abrar

Putzu

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Plant-inspired inflatable eversion robots with their tip growing behaviour have recently emerged. Because they extend from the tip, eversion robots are particularly suitable for applications that require reaching into remote places through narrow openings. Besides, they can vary their structural stiffness. Despite these essential properties which make the eversion robot a promising candidate for applications involving cluttered environments and tight spaces, controlling their motion especially laterally has not been investigated in depth. In this paper, we present a new approach based on model-based kinematics to control the eversion robot's tip position and orientation. Our control approach is based on Euler-Bernoulli beam theory which takes into account the effect of the internal inflation pressure to model each robot bending segment for various conditions of structural stiffness. We determined the parameters of our bending model by performing a least-square technique based on the pressure-bending data acquired from an experimental study. The model is then used to develop a pose controller for the tip of our eversion robot. Experimental results show that the proposed control strategy is capable of guiding the tip of the eversion robot to reach a desired position and orientation whilst varying its structural stiffness.

show abstract

Control Strategies for Soft Robotic Manipulators: A Survey

Cited by 495 publications

References 70 publications

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Open Loop Position Control of Soft Continuum Arm Using Deep Reinforcement Learning

Model-Based Control of Soft Actuators Using Learned Non-linear Discrete-Time Models

Model-Based Pose Control of Inflatable Eversion Robot With Variable Stiffness

Contact Info

Product

Resources

About