Analyzing Neural Jacobian Methods in Applications of Visual Servoing and Kinematic Control

by   Michael Przystupa, et al.

Designing adaptable control laws that can transfer between different robots is a challenge because of kinematic and dynamic differences, as well as in scenarios where external sensors are used. In this work, we empirically investigate a neural networks ability to approximate the Jacobian matrix for an application in Cartesian control schemes. Specifically, we are interested in approximating the kinematic Jacobian, which arises from kinematic equations mapping a manipulator's joint angles to the end-effector's location. We propose two different approaches to learn the kinematic Jacobian. The first method arises from visual servoing where we learn the kinematic Jacobian as an approximate linear system of equations from the k-nearest neighbors for a desired joint configuration. The second, motivated by forward models in machine learning, learns the kinematic behavior directly and calculates the Jacobian by differentiating the learned neural kinematics model. Simulation experimental results show that both methods achieve better performance than alternative data-driven methods for control, provide closer approximations to the proper kinematics Jacobian matrix, and on average produce better-conditioned Jacobian matrices. Real-world experiments were conducted on a Kinova Gen-3 lightweight robotic manipulator, which includes an uncalibrated visual servoing experiment, a practical application of our methods, as well as a 7-DOF point-to-point task highlighting that our methods are applicable on real robotic manipulators.


page 1

page 3


Hybrid Data-Driven and Analytical Model for Kinematic Control of a Surgical Robotic Tool

Accurate kinematic models are essential for effective control of surgica...

Kinematic Synthesis of Parallel Manipulator via Neural Network Approach

In this research, Artificial Neural Networks (ANNs) have been used as a ...

Adaptive Identification of Legged Robotic Kinematic Structure

Model-based control usually relies on an accurate model, which is often ...

Predicting Impact-Induced Joint Velocity Jumps on Kinematic-Controlled Manipulator

In order to enable on-purpose robotic impact tasks, predicting joint-vel...

Solving Cosserat Rod Models via Collocation and the Magnus Expansion

Choosing a kinematic model for a continuum robot typically involves maki...

Neural Inverse Kinematics

Inverse kinematic (IK) methods recover the parameters of the joints, giv...

An anthropomorphic continuum robotic neck actuated by SMA spring-based multipennate muscle architecture

This work presents a novel Shape Memory Alloy spring actuated continuum ...

Please sign up or login with your details

Forgot password? Click here to reset