Module-5.pptxzdgr5urtdfxcdghyjyulitgdfxvg

dtgjuki7i6redvbhjuyredfgy

1. I N T R O D U C T I O N T O A I A N D A P P L I C A T I O N S 1BAIA103/203 DR. ABHISHEK S. RAO Associate Professor, Dept. of IS&E Canara Engineering College, Mangaluru.

2. Robotics 1. Introduction to Robotics Content to Cover: Robot = programmable machine that completes tasks. Robotics = design, development, and programming of robots. Levels of autonomy: from human-controlled to fully autonomous. How to Teach: Begin with real-life examples (vacuum cleaner robots, Mars Rover). Ask students to classify robots they know into manual/semi-autonomous/autonomous. Use short video clips of simple vs. advanced robots to trigger discussion. 2. Artificially Intelligent Robots (AIRs) Content to Cover: Difference between an AI program and a robot (highlight Table & Venn diagram in syllabus). AIRs = overlap between robotics & AI. Examples: warehouse navigation robots, drones, self-driving cars. How to Teach: Explain with case studies rather than theory. Consider a small classroom exercise: “Is this robot intelligent or not?” (a washing machine vs. a self-driving car). Encourage use of diagrams (Venn diagram from text, flow of AI algorithms).

3. 3. Types of Robots What’s in the syllabus: Robots vary in design, size & tasks (tiny RoboBee → giant robotic ship). Categories: Pre-programmed → fixed repetitive tasks (assembly line arm). Humanoid → mimic humans (Sophia, Atlas). Autonomous → act independently with sensors (Roomba, drones). Cobots → collaborate with humans (pick & place tasks). Teleoperated → remote-controlled in dangerous areas (mine-detection drones). Augmenting → enhance human ability (prosthetics, exoskeletons). How can you explain in class: Use simple videos/images to show each type. Relate to familiar examples (photocopier, Uber driverless car, Iron Man suit). Small activity: ask students to classify robot examples into the right category.

4. 4. Types of Robots Based on Degree of Human Control What’s in the syllabus: Independent robots → fully autonomous, programmed for dangerous/tedious tasks (bomb diffusion, deep-sea travel, factory automation). Dependent robots → non-autonomous, work with humans (advanced prosthetics controlled by brain signals; e.g., Johns Hopkins prosthetic arm). Chatbots (software robots) → simulate conversations, often used in customer service. Types of Bots (not physical robots): Chatbots → conversations (24x7 service). Spam bots → collect/send spam. Download bots → auto-download apps/software. Search engine crawlers → scan/index websites. Monitoring bots → track website performance. How can you explain in class: Contrast independent vs. dependent with real-life examples (factory robot vs. prosthetic limb). Demonstrate the chatbot by showing students a live example (bank/retail website). Clarify the difference → robots have physical form, bots exist in software only. Quick activity: ask students to identify if an example is an independent robot, a dependent robot, or a bot .

5. 5. Components of a Robot What’s in the syllabus: Control system → CPU, like the robot’s brain (decision-making & task execution). Sensors → detect environment (camera = eyes, mic = ears, light sensors, etc.). Actuators → motors for movement (electrical, hydraulic, pneumatic). Power supply → batteries/AC power; future: solar, nuclear, etc. End effectors → external tools (claws, sprayers, grippers, prosthetic hands). How can you explain in class: Relate each component to the human body analogy : Brain = Control system Senses = Sensors Muscles = Actuators Food = Power supply Hands = End effectors Show simple images/videos of robots performing tasks (e.g., robotic arm gripping, drones flying). Quick activity: ask students to map each robot part to a human equivalent .

6. 6. AI Technology Used in Robotics What’s in the syllabus: Computer Vision → robots interpret images/videos (object detection). Natural Language Processing (NLP) → speech/voice commands, language understanding. Edge Computing → faster data processing, secure, low-cost, reliable. Complex Event Processing (CEP) → handle multiple real-time events (airbags triggered by sensors). Transfer Learning → reuse pre-trained models to reduce cost/time. Reinforcement Learning → robots learn by trial & error, rewarded for correct actions. Affective Computing → robots recognize & simulate human emotions. Mixed Reality → programming by demonstration, combining real + virtual objects. How can you explain in class: Relate each technology with simple, relatable examples : CV → self-driving cars detecting lanes. NLP → Alexa/Siri voice assistants. Edge Computing → data processed on the robot itself, not always cloud. CEP → “car airbags activate only when multiple conditions are met.” Transfer Learning → “learning football after already knowing cricket.” Reinforcement Learning → “robot learns like a child through trial & error.” Affective Computing → robots that smile/respond to emotions. Mixed Reality → demo with AR/VR classroom tools. Use short demo videos (voice command robot, self-driving clips). Activity: give students one real-world scenario → ask which AI technology it relates to.

7. 7. Planning and Navigation What’s in the syllabus: Cognition in robots → decision-making for mobility. Path planning vs. Trajectory planning → Path = route from start to goal. Trajectory = path + timing + velocity. Competencies → planning (strategy) + reacting (adjusting to obstacles). Degrees of Freedom (DOF) → number of ways a robot can move (robotic arm joints). Challenges → holonomic vs. non-holonomic movement, dynamic environments. Planning algorithms (overview only) → Potential Field, Sampling-based, Grid-based, Roadmap, Visibility Graph, Voronoi, Cell Decomposition. How can you explain in class: Start with a simple analogy : “GPS navigation in your car – it plans the route (path planning) and updates in traffic (reacting/trajectory).” Use a diagram/map example (start point → obstacles → goal). For DOF → demonstrate with your hand/arm (up, down, rotate, etc.). Keep algorithms conceptual only : Potential Field → “like a ball rolling downhill toward the goal.” Voronoi → “stay midway between obstacles for safety.” Grid/Cell Decomposition → “map divided into squares; robot finds path through free cells.” Classroom activity: ask students, “How would a delivery robot reach a hostel room, avoiding people and furniture?”

8. 1.7. Robotics – An Application of AI What’s in the syllabus: Robotics = interdisciplinary field (engineering + CS + AI + electronics + mechatronics). Asimov’s 3 Rules → safety, obey humans, self-protection. Key aspects → robots need electrical power, mechanical design, and programming. Types of Robots → pre-programmed, humanoid, autonomous, teleoperated, augmenting. Uses of Robotics → Manufacturing (assembly lines, cobots ). Logistics (warehouses, last-mile delivery). Healthcare (surgery assistants, hospital service robots). Space (rovers, Robonaut , spacecraft). Defense (bomb diffusion, drones). Daily life (companionship, household, education). Humanoids (ASIMO, Pepper, Buddy, REEM, etc.). How can you explain in class: Start with Asimov’s 3 Rules of Robotics → makes students curious. Use images/videos (Sophia, Atlas, Pepper) to show types. Relate uses to student life examples (delivery robots, hospital robots, vacuum cleaners). Small discussion activity: “Where would you like to see robots helping in your field?”

9. 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.

10. 1.8 Drones Using AI What’s in the syllabus: Emergency & Disaster Relief → search & rescue, thermal imaging. Conservation & Disease Control → tracking wildlife, testing mosquitoes. Healthcare & Delivery → COVID vaccine delivery, medicines in remote areas. Défense & Security → bomb detection, air strikes, surveillance. Agriculture → crop monitoring, yield prediction. Weather & Environment → forecasting, oceanic/climate data. Energy & Mining → site surveys, leak detection, stockpile measurement. Urban Planning & Construction → smart cities, project monitoring. Transport → passenger drones (Uber, EHANG). Space → NASA Mars drone, Titan mission. Other industries → telecom towers, internet access, tourism, journalism, food delivery. How can you explain in class: Begin with a simple definition : “Drone = flying robot (UAV) with AI.” Show 1–2 real videos (vaccine delivery drone in India, Mars helicopter). Group discussion: “Which drone application do you think is most useful for India?” Optional demo: show students a low-cost drone or video from local use-cases (agriculture, surveillance).

11. 1.10. No-Code AI What’s in the syllabus: Definition → build AI systems without writing code (drag-and-drop / visual tools). Examples of tools → Webflow (websites), Bubble/ Thunkable (apps), Octane/Kore.ai (chatbots), Airtable (databases), Shopify (e-commerce), Mailchimp (newsletters). Why No-Code AI? Enables non-coders to use AI. Saves time, cost, and resources . Increases accessibility for SMEs/startups. Reduces errors with plug-and-play automation. Applications → CV (image recognition), NLP (chatbots), Predictive Analytics (forecasts). Advantages → faster prototyping, collaboration between AI & domain experts, adoption across industries. Trends → By 2024, ~65% of apps will use low-code/no-code platforms. How can you explain in class: Start with a relatable example : “You can design a chatbot in 10 minutes without writing a single line of code.” Show 1–2 tools live ( Teachable Machine or ChatGPT-based bot builder ). Activity : Ask students to suggest one simple app/solution they would build using a no-code tool (e.g., attendance tracker, college event chatbot). Use Steve Jobs’ quote → “The fastest code is the one you never have to write” → to make the session engaging.

12. 1.11. Low-Code AI What’s in the syllabus: Definition → introduced in 2011; uses visual interfaces + drag-and-drop to speed up app development. Platforms → Mendix , Outsystems , Creatio , Appian, Zoho Creator. Who uses it → beginners (easy entry to AI), developers (custom integrations), researchers (fast prototyping). Applications → rapid AI app development (computer vision with viso.ai). Components → GUI, pre-built integrations, app manager. Disadvantages → security concerns, limited customization, vendor lock-in, and scalability issues. Future trend → By 2024, 65%+ of applications built using low-code/no-code platforms; market growing rapidly. ChatGPT Example → advanced NLP, reinforcement learning, but has bias/accuracy limitations. How can you explain in class: Begin with a contrast: traditional coding (Python) vs. low-code (drag-and-drop app builder). Use an analogy: “Think of low-code like making Maggi with a ready-to-cook kit – you don’t start from scratch.” Show 1 live demo (Zoho Creator / Bubble / Appian) – even a 2-minute overview video works. Activity idea: Ask students, “If you could build a simple AI app in 1 hour without coding, what would it be?” For ChatGPT: show a live query demo (but also stress limitations → bias, factual errors, etc.).

13. Industrial Applications of AI 3.1 Applications of AI in Healthcare What’s in the syllabus Medical Diagnosis Early Detection & Prevention Drug Discovery & Development AI-Powered Virtual Medical Assistants (VMAs) AI-Powered Robotics in Healthcare Challenges How can you explain in class: Use real-life cases : AI detecting cancer early, ChatGPT-style bots for patient queries, and robot-assisted surgery. Relate to India-specific examples (AI in TB detection, Apollo Hospitals using AI). Show one demo/video (Google’s retinal AI project or da Vinci surgical robot). Activity idea: Ask students, “Which healthcare AI use-case would you trust most as a patient? Why?”

14. 3.2 Applications of AI in Finance What’s in the syllabus: Algorithmic Trading → high-speed, AI-driven stock trading. Financial Risk Management → fraud detection, credit scoring. AI-Based Customer Service → chatbots in banks, financial assistants. Challenges → data security, ethical concerns, and over-reliance on AI in critical decisions. How can you explain in class: Start with a simple analogy : “AI in finance is like a smart calculator that not only computes but also predicts market moves.” Use examples : Zerodha (India), JP Morgan, PayTM fraud detection, SBI YONO chatbots. Short classroom activity : ask “Would you prefer a human or AI to approve your loan? Why?” → triggers ethics discussion. Show news clippings (AI predicting stock crashes, fraud detection success stories).

15. 3.3 Applications of AI in Retail What’s in the syllabus: Inventory & Store Layout Management → AI predicts demand, manages stock, optimizes shelf placement. Personalized Shopping Experience → recommendation engines (Amazon, Flipkart), targeted ads. Customer Support → chatbots, virtual shopping assistants. Challenges → data privacy, algorithm bias, cost of implementation. How can you explain in class: Relate to everyday examples : “When you shop online, AI suggests ‘customers also bought…’ → that’s personalization.” Use a visual demo : screenshot of Flipkart/Amazon recommendations. Talk about offline retail too → AI cameras tracking footfall in malls, dynamic store layouts. Class activity: ask “What AI features have you noticed while shopping online?” (students will recall ads, suggestions, chatbots).

16. 3.4 Applications of AI in Agriculture What’s in the syllabus: Precision Farming → optimize use of seeds, fertilizers, pesticides using AI & sensors. Crop Monitoring & Management → drones + computer vision for detecting pests/diseases, yield prediction. Smart Irrigation Systems → AI-based water management using soil/moisture data. Challenges → high cost, lack of farmer training, poor rural connectivity, data limitations. How can you explain in class: Begin with India-focused examples : AI in predicting crop yield (ICRISAT, NITI Aayog projects). Show short video/picture : drone spraying crops or an AI app identifying leaf disease. Connect to students’ local context : “Farmers in Karnataka/Andhra are already using AI apps for soil health checks.” Quick discussion: “How can AI reduce farmer suicides?” → links technology to social impact.

17. 3.5 Applications of AI in Education What’s in the syllabus: Personalized Learning → adaptive platforms (custom learning paths, quizzes). Administrative Tasks → grading automation, attendance, timetabling. AI-Based Language Tools → translation, speech-to-text, grammar correction. Challenges → digital divide, data privacy, over-dependence on tech, loss of human touch. How can you explain in class: Start with a relatable example : Byju's , Coursera, or Khan Academy using AI for adaptive learning. Demo real tools : Google Translate, Grammarly, speech-to-text → students instantly connect. Highlight benefits for teachers : less admin work → more focus on teaching. Class activity: ask “Would you prefer feedback from an AI tutor or a human teacher? Why?” → sparks debate.

18. 3.6 Applications of AI in Transportation What’s in the syllabus: Traffic Management & Optimization → smart signals, congestion prediction. Ride-Sharing & Mobility Services → Uber, Ola, autonomous shuttles. Safety & Security → driver assistance (ADAS), accident prediction, surveillance. Challenges → infrastructure cost, legal/ethical concerns, data privacy, and reliability. How can you explain in class: Start with a local example : Bengaluru smart traffic system, FASTag toll booths. Show a short clip : self-driving cars, smart traffic lights. Relate to students: “Your Ola/Uber fares are dynamic because AI predicts demand.” Quick discussion: “Would you trust a self-driving car in India today? Why/why not?”

19. 5.1 AI in Experimentation & Multi-Disciplinary Research What’s in the syllabus: Particle Physics → analyzing massive collider data (CERN experiments). Astrophysics & Space → detecting exoplanets, analyzing telescope images, space mission data. Experimental Chemistry → drug molecule simulation, material discovery. Biology → protein structure prediction (AlphaFold), gene sequencing. Environmental Science → climate modeling , pollution monitoring, disaster prediction. How can you explain in class: Use real global examples : AlphaFold in biology, NASA using AI for Mars rover data, and AI in climate change research. Relate to student curiosity : “AI is helping scientists discover new planets and new medicines.” Show 1–2 images (Hubble/James Webb AI-processed space images, protein folding). Quick discussion: “Which field do you think AI will impact the most in the next 10 years?”

20. T h a n k Y o u M o d u l e 5 - C o m p l e t e d