View Proposal

---

Proposer

Christian Dondrup

Title

Neural Network based Inverse Kinematics for Robotic Arm

Goal

Create a lecture on state-of-the-art methods for neural inverse kinematics for a robot arm

Description

This lecture should focus on the state-of-the-art in neural approaches for inverse kinematics for a robot arm. The arm itself does not need to have sensors and the approach can be offline instead of online. The general aim is to identify the most promising approach for offline approaches to inverse kinematics using neural networks from the literature and to create a lecture that introduces this approach. Ultimately, I would like to use the outcome of this to update the content of the Intelligent Robotics course for one of its lectures. You can find a review paper on the topic here to give you an overview of the field: https://www.mdpi.com/1999-4893/18/1/23

Resources

Background

Robotics, machine learning

Url

Difficulty Level

Moderate

Ethical Approval

None

Number Of Students

1

Supervisor

Christian Dondrup

Keywords

robotics, robot arm, industrial robotics, industrial robot, inverse kinematics, neural networks

Degrees

Master of Engineering in Software Engineering