Learning Global Inverse Statics Solution for a Redundant Soft Robot

  title={Learning Global Inverse Statics Solution for a Redundant Soft Robot},
  author={Thomas George Thuruthel and Egidio Falotico and Matteo Cianchetti and Federico Renda and Cecilia Laschi},
This paper presents a learning model for obtaining global inverse statics solutions for redundant soft robots. Our motivation begins with the opinion that the inverse statics problem is analogous to the inverse kinematics problem in the case of soft continuum manipulators. A unique inverse statics formulation and data sampling method enables the learning system to circumvent the main roadblocks of the inverting problem. Distinct from previous researches, we have addressed static control of both… 

Figures and Tables from this paper

Efficient Jacobian-Based Inverse Kinematics of Soft Robots by Learning
A learning-based method to solve the inverse kinematic (IK) problem in real-time on soft robots with highly non-linear deformation by employing neural networks to learn both the mapping function of forward kinematics and also the Jacobian of this function.
Cerebellum-inspired approach for adaptive kinematic control of soft robots
Simulation results show how such an architecture can provide monotonously decreasing tracking error reductions online and the robustness of the algorithm to changes in the inverse kinematic component and morphology of the soft robot itself is shown.
Control Strategies for Soft Robotic Manipulators: A Survey.
This review article attempts to provide an insight into various controllers developed for continuum/soft robots as a guideline for future applications in the soft robotics field.
Learning dynamic models for open loop predictive control of soft robotic manipulators.
This paper provides a machine learning-based approach for the development of dynamic models for a soft robotic manipulator and a trajectory optimization method for predictive control of the manipulator in task space and indicates that such an approach is promising for developing fast and accurate dynamic model for soft robotic Manipulators while being applicable on a wide range of soft manipulators.
The Computation of the Inverse Kinematics of a 3 DOF Redundant Manipulator via an ANN Approach and a Virtual Function
: In this paper a method based on Artificial Neural Networks (ANNs) is presented to solve the Inverse Kinematics (IK) of 3 degrees of freedom (DOF) redundant manipulators. In order to obtain the
Efficient Jacobian-Based Inverse Kinematics with Sim-to-Real Transfer of Soft Robots by Learning
Ancient learning-based method to solve the inverse kinematic (IK) problem on soft robots with highly non-linear deformation by employing neural networks to learn both the mapping function of forward kinematics and also the Jacobian of this function.
Closed loop control of a braided-structure continuum manipulator with hybrid actuation based on learning models
This paper presents a novel continuum manipulator with variable diameter and a general control strategy for closed loop task space control and indicates how such an approach can deal with singularities and provide smooth and accurate motion.
Exploiting Morphology of a Soft Manipulator for Assistive Tasks
Experimental results indicate that significant improvements in the tracking accuracy can be achieved by a simple yet appropriate environmental constraint.
Model Reference Predictive Adaptive Control for Large-Scale Soft Robots
A novel dynamic model formulation for continuum joint soft robots that is more accurate than previous models yet remains tractable for fast MPC, and like MRAC, MRPAC is robust to “structure mismatch” such as unmodeled disturbance forces not represented in the form of the adaptive regressor model.
Learning Inverse Statics Models Efficiently With Symmetry-Based Exploration
It is demonstrated that the number of samples required for learning inverse statics mappings for 2R and 3R manipulators can be reduced at least by factors of approximately 8 and 16, respectively–depending on thenumber of discovered symmetries.


Neural Network and Jacobian Method for Solving the Inverse Statics of a Cable-Driven Soft Arm With Nonconstant Curvature
This study presents both a model-based method and a supervised learning method to solve the inverse statics of nonconstant curvature soft manipulators and chooses a Jacobian-based and a feedforward neural network to solve this problem.
Learning inverse kinematics
  • Aaron D'SouzaS. VijayakumarS. Schaal
  • Mathematics
    Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180)
  • 2001
This paper investigates inverse kinematics learning for resolved motion rate control (RMRC) employing an optimization criterion to resolve kinematic redundancies and demonstrates how a recently developed statistical learning algorithm, locally weighted projection regression, allows efficient learning of inverse k Cinematic mappings in an incremental fashion even when input spaces become rather high dimensional.
Design and control of a soft and continuously deformable 2D robotic manipulation system
Results with a robot consisting of six segments show that controlled movement of a soft and highly compliant manipulator is feasible and algorithms to compute the arm's forward and inverse kinematics in a manner consistent with piece-wise constant curvature continuum manipulators are developed.
Self-motion analysis of extensible continuum manipulators
The null-space of 2-section, planar, extensible, redundant continuum manipulators is analyzed to consider the underlying structure of general continuum robot self-motions and discuss their importance to real-world examples and applications.
Learning Global Direct Inverse Kinematics
A bootstrap method for construction of an inverse function for the robot kinematic mapping using only sample configuration--space/ workspace data is introduced and a global inverse kinematics solution for the wristless Puma manipulator is developed.
Inverse kinematics learning by modular architecture neural networks
  • E. OyamaS. Tachi
  • Biology
    IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339)
  • 1999
A novel modular neural network architecture for the inverse kinematics model learning is proposed consisting of a single neural network and it is proposed that this model can be approximated by a well-known multilayer neural network.
Efficient Exploratory Learning of Inverse Kinematics on a Bionic Elephant Trunk
This work presents an approach to learn the inverse kinematics of the “bionic handling assistant”-an elephant trunk robot, and provides the first functioning control concept for this challenging robot platform.
Design, fabrication and control of soft robots
This Review discusses recent developments in the emerging field of soft robotics, and explores the design and control of soft-bodied robots composed of compliant materials.
Adaptive visual pursuit involving eye-head coordination and prediction of the target motion
This work presents an adaptive model based on a neuro-controller for visual pursuit that allows the robot to follow a moving target with no delay (zero phase lag) using a predictor of the target motion.
Integrating Feedback and Predictive Control in a Bio-Inspired Model of Visual Pursuit Implemented on a Humanoid Robot
A model able to integrate the major characteristics of visually guided and predictive control of the smooth pursuit is proposed, composed of an Inverse Dynamics Controller IDC for the feedback control, a neural predictor for the anticipation of the target motion and a Weighted Sum module that is able to combine the previous systems in a proper way.