Learning Global Inverse Statics Solution for a Redundant Soft Robot

@inproceedings{Thuruthel2016LearningGI,
  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},
  booktitle={ICINCO},
  year={2016}
}
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

TLDR
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

TLDR
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.

TLDR
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

TLDR
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.

Optimization-Based Inverse Model of Soft Robots With Contact Handling

TLDR
This letter uses the finite-element method to simulate the nonlinear deformation of the soft structure, its actuators, and surroundings and proposes a control method relying on a quadratic optimization to find the inverse of the model.

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

TLDR
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

TLDR
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.

Model Reference Predictive Adaptive Control for Large-Scale Soft Robots

TLDR
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

TLDR
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.

References

SHOWING 1-10 OF 18 REFERENCES

Neural Network and Jacobian Method for Solving the Inverse Statics of a Cable-Driven Soft Arm With Nonconstant Curvature

TLDR
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
TLDR
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.

Neural Networks based approach for inverse kinematic modeling of a Compact Bionic Handling Assistant trunk

TLDR
A new inverseKinematic modeling approach capable to approximate the inverse kinematics of a class of hyper-redundant continuum robots, namely Compact Bionic Handling Assistant (CBHA) is proposed in the present work and makes use of Multilayer Perceptron and Radial Basis Function Neural Networks as approximation methods.

A 3D steady-state model of a tendon-driven continuum soft manipulator inspired by the octopus arm.

TLDR
This work presents a geometrically exact steady-state model of a tendon-driven manipulator inspired by the octopus arm that takes a continuum approach, fast enough to be implemented in the control law, and includes a model of the actuation system.

Dynamic Model of a Multibending Soft Robot Arm Driven by Cables

TLDR
A dynamic model of a continuum soft robot arm driven by cables and based upon a rigorous geometrically exact approach is developed, which fully investigates both dynamic interaction with a dense medium and the coupled tendon condition.

Design and control of a soft and continuously deformable 2D robotic manipulation system

TLDR
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

TLDR
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.

Continuous Backbone “Continuum” Robot Manipulators

TLDR
The history and state of the art of continuous backbone robot manipulators are described and the relationships of these robots and their models to their counterparts in conventional rigid-link robots are discussed.

Learning Global Direct Inverse Kinematics

TLDR
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
TLDR
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.