PRE2024 3 Group7

Group

Name	Student ID	Email	Major	Ideas
Isaak Christou	1847260	i.christou@student.tue.nl	Electrical Engineering	Agricultural Weeding Robot Smart Trash Bin with AI Sorting (or no AI) Firefighting Drone Smart Walking Cane for the Visually Impaired Robotic Road Crack Detector
Luca van der Wijngaart	1565923	l.y.v.d.wijngaart@student.tue.nl	Computer Science
Daniel Morales Navarrete	1811363	d.morales.navarrete@student.tue.nl	Applied Mathematics	Robotic Beach Cleaner
Jeremiah Kamidi	1778013	j.j.kamidi@student.tue.nl	Psychology and Technology	self driving cars
Joshua Duddles	1719823	j.m.duddles@student.tue.nl	Psychology and Technology

The smart trash bin that auto sorts is a fun idea kind of like the machines used in industries where fast automatic sorting is required (for example sorting potatoes by colour, size, shape etc). This can replace all the bins on campus for example since lots of people don't use them correctly.

Robotic crack detector also looks fun. A prototype could be a cheap RC car with some sensors on it to accurately detect cracks and map out the roads. The city management could use it to better map out faults in roads and pavements that could hinder people.

Problem Statement

Road infrastructure is an essential component for economic growth in any country especially developing ones. Nevertheless the formation of cracks and potholes is common due to a multitude of factors such as weathering, excessive use, inferior design or materials etc. This makes road maintenance a significant challenge for any governing system as traditional methods for detecting such hazards often rely on visual inspection by personnel which is costly and time consuming or depends on the information provided by the general public which more often than not gets overlooked by authorities. With the increase of urbanization and the aging of road networks a more general, automated, cost effective and time efficient solution is required. A crack and pothole detection robot could help to quickly and accurately detect defects which can be quickly fixed reducing the overall cost and burden of the problem if left unchecked.

Our goal is to research on the current state of such technology and find better and more practical approaches. The research will be split into three parts: the carrier which is the form the robot takes for transportation (for example is a drone better than a grounded vehicle), the detection system (what hardware and software give a combination of best performance and cost and how can these also assess the state of the damage) and finally communication (how does the robot relay what it has found to a central hub that marks the location and state of the damage). Communication is especially important as allowing multiple agents to relay information is key in reducing the time needed to map large urban centres.

Objectives

• Examine and determine the ethical implications of autonomous road maintenance and data reaping.
• Determine how cracks in road surfaces can be detected using sensors, imaging, or other methods.
• Determine procedures for assessing the severity of cracks detected and classifying them for maintenance planning.
• Develop a model of the robotic crack inspection system.
• Develop a model for automated crack detection and classification using AI or other methodologies.
• Illustrate the system's usefulness through testing and comparison with traditional manual inspection procedures.

Approach, milestones and deliverables

Our approach to reaching these objectives in regards to the problem statement and the user needs is as follows:

We want to research and design a conceptual framework of a robot that is able to detect road cracks and map these out on a geographical map, for the benefit of road maintenance and infrastructure longevity. We will (partly) perform the first cycle of a multi-phase development cycle consisting of the following phases:

• Research & requirements gathering
  • This includes both research in the technology needed to build this robot but also the societal and economic effects of the robot and road maintenance in general.
• Ethical and legal considerations
• Sensor and other hardware selection
• Explain the road-crack detection and classification model
• Build a model/PoC (Proof of Concept)

Along these phases of our first development cycle we will set some milestones for ourselves as to keep our attention on the objectives set. This will be in the form of documentation of our work in a structured manner, making sure that the work put into each phase is represented. This documentation will in turn be part of our deliverables, as will be the model/PoC of our road-crack detecting robot.

Planning

who is doing what and general timeline

Everyone please fill in the task division that we just discussed. I think this section is also meant for the planning of the rest of project and I guess it's highly dependent on our Approach, milestones and deliverables so I'll also think about this.

Deadline	Student	Responsible topic/chapter	Done
15-02	Luca	Approach, milestone and deliverables
15-02	Dani	Objectives and 5 sources for State of the Art
15-02	Isaak	Problem Statement and 5 relevant papers

State of the art

research and write summary on wiki after finding at least 25 relevant scientific papers (aim for 5 each person if there is an interesting one add it as extra). We can split the research to different parts as to make it easier to put together.

Work Records

Week 1

Name	Hours	Work
Isaak Christou	2 (not done yet)	Made the wiki page
Luca van der Wijngaart	1.5 hours	Group meeting, first start to the Approach section

Week 2

Week 2

Week 3

Week 3

Week 4

Week 4

Week 5

Week 5

Week 6

Week 6

Week 7

Week 7

Week 8

Week 8

References

[1][2][3][4][5]