MODULE - 5​ ​ ​ ​ ​

Robotics
Robotics-an Application of AI,
Drones Using AI
No Code AI
Low Code AI.
Textbook 1: ​​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​
Reema Thareja, Artificial Intelligence: Beyond Classical AI, Pearson Education, 2023
​ Chapter 8 (8.1, 8.2, 8.4), Chapter 9 (9.1- 9.3)
—------------------
Industrial Applications of AI:
Application of AI in Healthcare,
Application of AI in Finance,
Application of AI in Retail, ​
Application of AI in Agriculture,
Application of AI in Education,
Application of AI in Transportation,
AI in Experimentation and Multi-disciplinary research.
Textbook 3: ​​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​
​ Saptarsi Goswami, Amir Kumar Das and Amlan Chakrabarti, "AI for Everyone - A
Beginner's Handbook for Artificial Intelligence", Pearson, 2024.
​ Chapter 3, Chapter 5 (5.1)

1 Robotics
1.1 Artificially Intelligent Robot
AI vs Robotics

●​ AI: Helps machines think and make decisions like humans.

 ●​ Robotics: Focuses on building machines that can perform physical tasks.

1.2 Artificially Intelligent Robots (AIRs)

AIRs combine both AI and [Link] can think + act using AI algorithms.
Examples:
●​ Warehouse robots: Use AI to find the best path to move.
●​ Drones: Automatically return home when battery is low.
●​ Self-driving cars: Detect obstacles and drive safely.

1.3 Types of Robots

1. Pre-Programmed Robots
●​ Do simple, repetitive tasks.
●​ Example: Robots in car manufacturing.
2. Humanoid Robots
●​ Look or act like humans.
●​ Example: Sophia robot.
3. Autonomous Robots
●​ Work on their own without human help.
●​ Examples: Roomba vacuum, medical assistant robots.
4. Teleoperated Robots
●​ Controlled by humans from a distance.
●​ Examples: Drones for landmine detection, underwater repair robots.
5. Augmenting Robots (VR Robots)
●​ Help improve human ability.
●​ Examples: Prosthetic limbs, exoskeleton suits.

1.4 Robots Based on Human Control

●​ Independent Robots
○​ Work completely on their own.
○​ Used in dangerous or boring [Link]: Bomb disposal robots, deep-sea
robots.
●​ Dependent Robots
○​ Need human [Link]: Prosthetic limbs controlled by human signals.
●​ Chatbots
○​ Software robots that talk to [Link] in customer service.

1.5 Components of a Robot

●​ Control System
 ○​ The robot’s “brain” that controls all actions.
●​ Sensors
○​ Help robots sense their environment.
○​ Examples: Cameras, microphones, light sensors.
●​ Actuators
○​ Parts that help robots move.
○​ Example: Electric motors.
●​ Power Supply
○​ Provides energy (battery, solar, hydraulic systems).
●​ End Effectors
○​ Tools attached at the robot’s end to perform tasks.
○​ Examples: Grippers, robotic hands.

1.6 AI Technologies Used in Robotics

●​ Computer Vision: Lets robots “see” and understand images.
●​ NLP: Helps robots understand and respond to human language.
●​ Edge Computing: Faster processing near the robot.
●​ CEP (Complex Event Processing): Handles multiple real-time events.
●​ Transfer Learning: Uses pre-trained models to save time.
●​ Reinforcement Learning: Robots learn by trial and error.
●​ Affective Computing: Gives robots emotional understanding.
●​ Mixed Reality: Combines real and virtual worlds for training robots.

1.7 Planning and Navigation

●​ Cognition
●​ Ability of a robot to make decisions to reach its goal.
●​ Path Planning
●​ Finding the best route from the start to the destination while avoiding obstacles.

1.7.1 Competencies for Planning

●​ Strategic Problem Solving
○​ Planning the best path to reach a goal.
●​ Tactical Problem Solving
○​ Avoiding obstacles and reacting to real-world changes.

1.7.2 Key Terms in Trajectory Planning

●​ Trajectory Planning: Moving from point A to B safely.
●​ Configuration Space: All possible positions a robot can take.
 ●​ Free Space: Areas where the robot can move without hitting anything.

1.7.3 Constraints in Trajectory Planning

●​ Holonomicity: Ability of a robot to move freely in all directions.
●​ Dynamic Environments: Obstacles may move, making planning harder.

1.7.4 Planning Algorithms

●​ Artificial Potential Field
○​ Goal attracts the robot; obstacles push it away.
●​ Sampling-based Planning
○​ Selects sample points and searches for a path.
●​ Grid-based Planning
○​ Divides the area into a grid and finds a safe path.
●​ Reward-based Planning
○​ Robot chooses actions that give maximum future reward (used in RL).

1.7.5 Visibility Graph

●​ Connects visible points in the environment to find the shortest path around
obstacles.

1.7.6 Voronoi Diagram

●​ Creates paths that keep the robot as far as possible from obstacles, improving
safety.

1.7.7 Cell Decomposition

●​ Exact Cell Decomposition
○​ Breaks the area into clean cells and marks free space.
●​ Approximate Cell Decomposition
○​ Uses fixed-size grids; faster but may miss small paths.

1.7.8 Potential Field Path Planning

●​ Uses attractive (goal) and repulsive (obstacle) forces to guide the robot like
gravity.

Asimov’s 3 Rules of Robotics

Isaac Asimov’s Three Laws of Robotics (introduced in the 1940s)
First Law
 A robot may not injure a human being or, through inaction, allow a human being to
come to harm.
Second Law
A robot must obey the orders given it by human beings except where such orders would
conflict with the First Law.
Third Law
A robot must protect its own existence as long as such protection does not conflict with
the First or Second Law.

Applications of Drones Using Artificial Intelligence (AI)

1.​ Emergency & Disaster Relief
○​ Used in search and rescue operations during floods, earthquakes, and fires.
○​ Thermal imaging helps detect trapped or injured people.
○​ Enables fast assessment of disaster-affected areas.
2.​ Conservation & Disease Control
○​ Helps in tracking and monitoring wildlife populations.
○​ Used to identify illegal hunting and forest encroachment.
○​ Assists in testing mosquitoes and monitoring disease-prone areas.
3.​ Healthcare & Medical Delivery
○​ Used to deliver COVID vaccines, medicines, and blood samples.
○​ Useful in reaching remote and rural areas quickly.
○​ Reduces delivery time and human risk.
4.​ Defense & Security
○​ Used for bomb detection and surveillance.
○​ Supports border monitoring and intelligence gathering.
○​ Helps in air strikes with minimal human involvement.
5.​ Agriculture
○​ Used for crop monitoring and health analysis.
○​ Helps in yield prediction using AI data analysis.
○​ Supports precision farming and pest detection.
6.​ Weather & Environmental Monitoring
○​ Collects data for weather forecasting.
○​ Used to study climate change and ocean conditions.
○​ Helps monitor pollution and natural resources.
7.​ Energy & Mining
○​ Used for site surveys and inspections.
○​ Helps detect gas or oil leaks.
○​ Measures stockpiles in mining areas accurately.
 8.​ Urban Planning & Construction
○​ Supports smart city development.
○​ Used for project monitoring and progress tracking.
○​ Helps in land surveying and infrastructure planning.
9.​ Transportation
○​ Passenger drones are being developed for urban travel.
○​ Examples include Uber Air and EHANG drones.
○​ Aims to reduce traffic congestion.
10.​Space Exploration
○​ NASA uses drones on Mars for surface exploration.
○​ Planned missions include drones for Saturn’s moon Titan.
○​ Helps explore areas unreachable by rovers.
11.​Other Industries
○​ Used for telecom tower inspection.
○​ Provides internet access in remote regions.
○​ Applied in tourism, journalism, and food delivery services.

No-Code AI
Definition
●​ No-Code AI refers to building Artificial Intelligence applications without writing
programming code.
●​ It uses drag-and-drop and visual interfaces to create AI systems.

Examples of No-Code AI Tools

●​ Webflow – Used for creating websites.
●​ Bubble / Thunkable – Used for developing mobile and web applications.
●​ Octane / [Link] – Used for building AI chatbots.
●​ Airtable – Used as a database and data management tool.
●​ Shopify – Used for e-commerce platforms.
●​ Mailchimp – Used for email marketing and newsletters.

Why No-Code AI?

●​ Enables non-programmers to use AI technologies.
●​ Saves time, cost, and development resources.
●​ Increases AI accessibility for SMEs and startups.
●​ Reduces human errors using plug-and-play automation.

Applications of No-Code AI
 ●​ Computer Vision (CV) – Image recognition and object detection.
●​ Natural Language Processing (NLP) – Chatbots and virtual assistants.
●​ Predictive Analytics – Forecasting trends and future outcomes.

Advantages of No-Code AI
●​ Faster prototyping and deployment.
●​ Encourages collaboration between AI experts and domain experts.
●​ Promotes AI adoption across multiple industries.

Low-Code AI
Definition
●​ Low-Code AI was introduced around 2011.
●​ It uses visual interfaces and drag-and-drop tools along with minimal coding.
●​ Helps in faster AI and application development.

Popular Low-Code AI Platforms

●​ Mendix
●​ OutSystems
●​ Creatio
●​ Appian
●​ Zoho Creator

Who Uses Low-Code AI?

●​ Beginners – Easy entry into AI and application development.
●​ Developers – Allows custom integrations and extensions.
●​ Researchers – Useful for rapid prototyping and experimentation.

Applications of Low-Code AI
●​ Rapid development of AI applications.
●​ Used in Computer Vision applications (e.g., [Link]).
●​ Business automation and intelligent workflows.

Main Components of Low-Code AI

●​ GUI (Graphical User Interface) – Visual design of applications.
●​ Pre-built Integrations – Ready-made connectors and APIs.
●​ Application Manager – Deployment, monitoring, and management.

Disadvantages of Low-Code AI
●​ Security concerns due to platform dependency.
 ●​ Limited customization compared to full-code solutions.
●​ Vendor lock-in issues.
●​ Scalability limitations for large-scale systems.

Future Trends
●​ By 2024, more than 65% of applications are expected to be built using
low-code/no-code platforms.
●​ The low-code AI market is growing rapidly due to digital transformation

ChatGPT as an Example
●​ ChatGPT uses advanced NLP and Reinforcement Learning.
●​ Capable of understanding and generating human-like text.
●​ Has limitations such as bias, accuracy issues, and dependency on training data.

Applications of Artificial Intelligence (AI) in Healthcare

1. Medical Diagnosis
●​ AI helps doctors in diagnosing diseases accurately.
●​ Used in medical imaging such as X-rays, CT scans, and MRI scans.
●​ Helps in detecting diseases like cancer, heart disease, and brain disorders at an early
stage.
2. Early Detection & Prevention
●​ AI systems analyze patient data to identify diseases at an early stage.
●​ Helps in predicting risks and preventing serious health conditions.
●​ Example: AI-based systems for early cancer and diabetic detection.
3. Drug Discovery & Development
●​ AI speeds up the process of discovering new drugs.
●​ Helps in analyzing chemical compounds and predicting drug effectiveness.
●​ Reduces time and cost involved in traditional drug development.
4. AI-Powered Virtual Medical Assistants (VMAs)
●​ AI chatbots assist patients by answering health-related questions.
●​ Helps in booking appointments and providing basic medical guidance.
●​ Example: ChatGPT-like healthcare bots for patient support.
5. AI-Powered Robotics in Healthcare
●​ Used in robot-assisted surgeries for high precision.
●​ Helps surgeons perform complex procedures with minimal invasion.
●​ Example: da Vinci Surgical Robot.
6. Challenges of AI in Healthcare
●​ Data privacy and security issues.
 ●​ High implementation cost.
●​ Risk of errors and bias in AI systems.
●​ Need for skilled professionals and ethical regulations.
Real-Life Examples:
●​ AI systems detect cancer at an early stage using imaging data.
●​ AI chatbots answer patient queries and provide medical guidance.
●​ Robot-assisted surgery improves accuracy and recovery time.
India-Specific Examples:
●​ AI used in TB detection through chest X-ray analysis.
●​ Apollo Hospitals use AI for diagnostics and patient management.

Applications of Artificial Intelligence (AI) in Finance

1. Algorithmic Trading
●​ AI is used for high-speed stock trading.
●​ Analyzes market data and executes trades automatically.
●​ Helps in identifying profitable trading opportunities quickly.
●​ Reduces human error and emotional decision-making.

2. Financial Risk Management

●​ AI helps in fraud detection by identifying unusual transaction patterns.
●​ Used for credit scoring to assess customer loan eligibility.
●​ Improves accuracy in risk assessment and financial decision-making.
●​ Example: AI-based fraud detection in digital payment systems.

3. AI-Based Customer Service

●​ Banks use AI chatbots to handle customer queries.
●​ Provides 24/7 support for balance checks, fund transfers, and account details.
●​ Improves customer experience and reduces workload on bank staff.
●​ Example: SBI YONO chatbot and virtual banking assistants.

4. Challenges of AI in Finance
●​ Data security and privacy issues.
●​ Ethical concerns in automated decision-making.
●​ Over-reliance on AI for critical financial decisions.
●​ Risk of bias and lack of transparency in AI models.

Real-World Examples
●​ Zerodha uses AI for trading insights and analytics.
●​ JP Morgan uses AI for financial analysis and risk management.
 ●​ PayTM uses AI for fraud detection.
●​ SBI YONO uses AI chatbots for customer support.

Applications of Artificial Intelligence (AI) in Retail

1. Inventory & Store Layout Management
●​ AI predicts customer demand using sales data.
●​ Helps manage inventory and avoid overstock or stock shortages.
●​ Optimizes shelf placement and store layout for better sales.
●​ Used in both online and offline retail stores.
2. Personalized Shopping Experience
●​ AI provides product recommendations based on user behavior.
●​ Shows suggestions like “Customers also bought”.
●​ Used for targeted advertisements and personalized offers.
●​ Examples: Amazon and Flipkart recommendation systems.
3. Customer Support
●​ AI-powered chatbots and virtual shopping assistants handle customer queries.
●​ Provides 24/7 support for orders, returns, and product information.
●​ Improves customer satisfaction and reduces response time.
4. Challenges of AI in Retail
●​ Data privacy concerns related to customer information.
●​ Algorithm bias affecting recommendations.
●​ High cost of implementation for small retailers.
●​ Dependence on quality data for accurate results.
Real-Life Examples
●​ Online shopping platforms recommend products based on browsing history.
●​ AI tracks customer behavior to improve shopping experience.
●​ Offline retail stores use AI cameras to analyze footfall and improve store layouts.

Applications of Artificial Intelligence (AI) in Agriculture

1. Precision Farming
●​ AI helps optimize the use of seeds, fertilizers, and pesticides.
●​ Uses data from sensors, satellites, and weather reports.
●​ Reduces wastage and increases crop productivity.
●​ Supports sustainable and cost-effective farming.
2. Crop Monitoring & Management
●​ AI combined with drones and computer vision monitors crop health.
●​ Helps in early detection of pests and plant diseases.
●​ Used for yield prediction and crop growth analysis.
 ●​ Enables timely action by farmers.
3. Smart Irrigation Systems
●​ AI-based systems manage water usage efficiently.
●​ Uses soil moisture and weather data.
●​ Prevents over-irrigation and water wastage.
●​ Improves crop yield and conserves water resources.
4. Challenges of AI in Agriculture
●​ High cost of AI tools and equipment.
●​ Lack of training and awareness among farmers.
●​ Poor internet connectivity in rural areas.
●​ Limited and inaccurate agricultural data.
India-Specific Examples
●​ AI used in crop yield prediction by ICRISAT and NITI Aayog projects.
●​ Farmers in states like Karnataka and Andhra Pradesh are adopting AI-based farming
tools.
●​ AI mobile apps help identify leaf diseases using images.

Applications of Artificial Intelligence (AI) in Education

1. Personalized Learning
●​ AI provides adaptive learning platforms based on student performance.
●​ Creates custom learning paths, quizzes, and assignments.
●​ Helps students learn at their own pace.
●​ Examples: Byju’s, Coursera, Khan Academy.
2. Administrative Tasks
●​ AI automates routine tasks such as grading, attendance, and timetabling.
●​ Reduces manual workload for teachers.
●​ Improves accuracy and saves time.
3. AI-Based Language Tools
●​ AI supports language translation and multilingual learning.
●​ Converts speech-to-text for notes and accessibility.
●​ Provides grammar correction and writing assistance.
●​ Examples: Google Translate, Grammarly.
4. Challenges of AI in Education
●​ Digital divide between students with and without technology access.
●​ Data privacy and security concerns.
●​ Over-dependence on technology.
●​ Possible loss of human interaction and emotional guidance.
Benefits of AI in Education
●​ Improves learning outcomes through personalization.
●​ Saves time for teachers by reducing administrative work.
●​ Enhances accessibility for diverse learners.

Applications of Artificial Intelligence (AI) in Transportation

1. Traffic Management & Optimization
●​ AI is used in smart traffic signals to control vehicle flow.
●​ Predicts traffic congestion using real-time data.
●​ Reduces travel time and fuel consumption.
●​ Example: Smart traffic systems in Bengaluru.
2. Ride-Sharing & Mobility Services
●​ AI is used in platforms like Uber and Ola.
●​ Predicts demand and applies dynamic pricing.
●​ Supports route optimization and passenger matching.
●​ Autonomous shuttles and self-driving vehicles use AI for navigation.
3. Safety & Security
●​ AI-powered Advanced Driver Assistance Systems (ADAS) help prevent accidents.
●​ Used for accident prediction and driver behavior analysis.
●​ AI-based surveillance improves road and passenger safety.
4. Challenges of AI in Transportation
●​ High infrastructure and implementation costs.
●​ Legal and ethical concerns in autonomous driving.
●​ Data privacy and security issues.
●​ Reliability and safety in complex road conditions.
India-Specific Examples
●​ FASTag toll booths use AI-based systems for automatic toll collection.
●​ Bengaluru’s AI-enabled traffic monitoring and signal control systems.

AI in Experimentation & Multi-Disciplinary Research

1. Particle Physics
●​ AI is used to analyze huge volumes of data from particle accelerators.
●​ Helps in identifying meaningful patterns from collider experiments.
●​ Example: CERN experiments use AI for faster and accurate data analysis.
2. Astrophysics & Space Science
●​ AI helps in detecting exoplanets and analyzing telescope images.
●​ Processes data from space missions and satellites.
●​ Used in image enhancement and object detection in space.
●​ Example: AI used by NASA for Mars rover and space data analysis.
3. Experimental Chemistry
●​ AI simulates drug molecules to predict their effectiveness.
●​ Helps in new material discovery.
●​ Reduces time and cost involved in laboratory experiments.
4. Biology
●​ AI is used for protein structure prediction.
●​ Helps in gene sequencing and biological data analysis.
●​ Example: AlphaFold predicts protein structures accurately.
5. Environmental Science
●​ AI supports climate modeling and weather prediction.
●​ Used for pollution monitoring and disaster prediction.
●​ Helps in studying climate change and environmental protection.
Advantages of AI in Scientific Research
●​ Speeds up discoveries and experimentation.
●​ Handles complex and large datasets efficiently.
●​ Enables breakthroughs across multiple disciplines.

​ ​ ​ ​ END OF MODULE - 5