Week 23/06/2024 - 29/06/2024

Preliminary Studies

Search for journals related to my selected topic. Keywords used to search for journals are:

1. Robot arm object manipulation. 
2. Robot arm object grasping

Some journals found that seems significant to the project are:

1. RGBGrasp: Image-Based Object Grasping by Capturing Multiple Views During Robot arm Movement With Neural Radiance Fields (https://ieeexplore.ieee.org/abstract/document/10517376)
2. A Vision-Based Robot Grasping System (https://ieeexplore.ieee.org/abstract/document/9745523)
3. Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers (https://ieeexplore.ieee.org/abstract/document/9095225)
4. Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey (https://ieeexplore.ieee.org/abstract/document/9212350)
5. Vision-Based Robotic Arm Control Algorithm Using Deep Reinforcement Learning for Autonomous Objects Grasping (https://www.mdpi.com/2076-3417/11/17/7917)
6. Robotic object recognition and grasping with a natural background (https://journals.sagepub.com/doi/full/10.1177/1729881420921102)
7. Modeling, learning, perception, and control methods for deformable object manipulation (https://www.science.org/doi/full/10.1126/scirobotics.abd8803)

Find out more about the UR5 robot that I intend to use for this project by going through some videos on YouTube:

1. Universal Robot UR5 Operations Review (https://www.youtube.com/watch?v=Sk9AdsUy4SQ)

Hardware Setup

Robot arm = UR5

Camera = Intel Real Sense Depth Camera

Some examples found that are of interest:

Example system setup from "A Vision-Based Robot Grasping System"

Example system setup from "RGBGrasp: Image-Based Object Grasping by Capturing Multiple Views During Robot Arm Movement With Neural Radiance Fields"

26/06/2024

At the workshop we attended today, we were asked to determine our objectives and goals for the project:

Objective

By the end of this project, I would have investigated if a robot system is able to pick an object based on spoken instruction through vision and then place the item picked onto the speaker’s palm within 15 seconds.

Goals

Investigate if:

1. Robot arm is able to identify object based on speech and vision

2. Robot is able to automatically grasp objects through vision. 

3. Robot is able to grasp objects of different shapes and sizes

4. Robot is able to grasp an object in a different orientation.

5. Place the object onto the palm of a person.

Week 16/6/2024 - 22/06/2024

This is my first journal entry for my MSc Robotics project for Middlesex university.

This week, I thought hard about what I wanted to work on for my MSc Robotics Project. I narrowed down my project ideas to 4:

I presented my ideas to Dr Purav and Alex on Wednesday (19/06/2024). I was actually quite keen on the 1st and 2nd ideas, but rather not do the 3rd and 4th one as it involves the Turtlebot 4, which I found tricky to manage. 

Fig. 1 A rough sketch of each idea.

After further discussion with them, I have decided to work on a project that aims to evaluate the different ways a robotic arm is able to pick different objects of different sizes, textures, shapes and firmness, and then place said object onto the palms of different people using computer vision. 

The equipment that I have in mind for now are the UR5 arm, a camera and microphone. 

I will now have to find out more about object handling by a robotic arm.