Workshop
Autonomous Mobile Robot (AMR) using ROS 2
This workshop is an intensive, hands-on training program that introduces participants to the fundamentals of autonomous robotics using the Robot Operating System 2 (ROS 2). The session combines conceptual understanding with practical demonstrations, enabling participants to experience the complete workflow of developing an autonomous mobile robot — from modeling and simulation through to understanding real hardware deployment.
To maximize learning within the available time, all software packages, robot models, and simulation environments will be pre-configured on the laboratory systems. Participants will execute the complete workflow, observe the outputs, and understand the concepts through guided demonstrations — no time spent on software installation.
AGENDA
1. AMR Foundations
Introduction to SDV Labs, overview of Autonomous Mobile Robots, AMR architecture, applications across industries, and differential drive mechanism
2. ROS 2 Introduction
ROS 2 architecture, advantages of developing AMRs with ROS 2 vs. conventional software, and comparison of differential drive vs. steering-based robots
3. Robot Modeling & Simulation
Creating robot models using URDF, launching and simulating an AMR in Gazebo, and building an indoor simulation environment
4. Sensor Integration & Visualization
Integrating LiDAR, Camera, and Wheel Encoder sensors in simulation, and visualizing robot data using RViz
5. SLAM & Navigation
Understanding SLAM (Simultaneous Localization and Mapping), generating and saving occupancy maps, and autonomous navigation using the Nav2 framework
6. Live Demo & Lab Visit
Live demonstration of a real AMR developed at SDV Labs, visit to explore ongoing robotics and AI research projects, and interactive discussion with instructors
Schedule
00:00 – 00:20 Workshop Overview and Introduction to SDV Labs
00:20 – 00:40 Introduction to AMRs, Architecture, Applications, and Drive Mechanisms
00:40 – 01:00 Introduction to ROS 2, ROS 2 Architecture, and AMRs with vs. without ROS 2
01:00 – 01:40 Robot Modeling using URDF and Robot Simulation in Gazebo
01:40 – 02:20 Sensor Integration (LiDAR, Camera, Wheel Encoders) and Data Visualization using RViz
02:20 – 02:50 SLAM (Simultaneous Localization and Mapping) and Map Generation
02:50 – 03:20 Autonomous Navigation using Nav2
03:20 – 03:40 Live Demonstration of a Real AMR and Interactive Q&A
03:40 – 03:55 SDV Labs Visit and Research Showcase
03:55 – 04:00 Workshop Conclusion, Feedback, and Networking
Stats strip
4 hrs — Total Duration
6 — Core Modules
1 — Live Robot Demo
0 — Prior ROS 2 Experience Required
Systems Thinking Approach to Complex Systems Development
A MathWorks session on managing complexity in modern engineering systems through systems thinking and Model-Based Systems Engineering (MBSE)
This presentation explores how systems thinking and Model-Based Systems Engineering help manage the rising complexity of modern engineering systems. It explains how stakeholder needs can be translated into requirements, architectures, interfaces, trade studies, and verification activities while maintaining traceability across the development lifecycle. Using practical examples, the session shows how MBSE connects with Model-Based Design to create a digital thread from concept to implementation, analysis, testing, and validation.
Speaker Profile
Ramana Anchuri
Principal Customer Success Engineer, Education Team — MathWorks, Hyderabad
Ramana Anchuri is a principal customer success engineer within the Education team at MathWorks in Hyderabad, where he collaborates closely with academic institutions across India. Prior to MathWorks, he worked in both academia and industry. Ramana is dedicated to education, teaching, and continuous learning. His expertise encompasses power electronics, control design, Model-Based Design, and GenAI/Agentic AI. Ramana holds a bachelor's degree in electrical and electronics engineering, and a master's degree in power electronics from JNTU Hyderabad.
Outcomes
Understand the fundamentals of systems thinking and model-based systems engineering (MBSE)
Learn how to manage complexity across the system development lifecycle
Explore methods for requirements management, architecture design, and system validation
Gain insights into digital engineering workflows that improve collaboration and traceability
Discover industry best practices through practical examples and real-world applications
Build Your First VCU Prototype in One Day
1-Day Hands-on Training · Intermediate → Advanced
A hands-on training program by ANCIT covering the complete ECU development workflow — from microcontroller fundamentals and CAN communication to DBC creation, AUTOSAR architecture, ECU development, and UDS diagnostics. Participants build and validate a working Interior Light ECU using industry-standard tools and hardware.
Agenda
1. Microcontroller Fundamentals
Introduction to microcontrollers, peripherals (GPIO, ADC, Timers, UART, CAN controller), and ECU basics and embedded architecture
2. CAN Communication
CAN protocol fundamentals, CAN frame structure (Standard vs Extended ID), Signal vs Message concept, and introduction to DBC
3. Automotive Development Process
V-Model architecture and software development lifecycle in automotive
4. AUTOSAR vs Legacy Architecture
Layered architecture (Application, RTE, BSW) and comparison with bare-metal / legacy stack
5. Interior Light ECU Design
System architecture, signal identification, and functional behaviour definition
6. DBC Creation
Creating CAN messages & signals, naming conventions, and validation of DBC structure
7. ECU Development using GenX
Project setup, code/config generation, and integration of signals into ECU logic
8. CAN Simulation & Testing (TSMaster)
Importing DBC, sending & receiving CAN messages, and signal monitoring
9. Diagnostics (UDS Integration)
Introduction to UDS protocol, Diagnostic Session Control (DSC), RDBI (Read Data By Identifier), WDBI (Write Data By Identifier), and diagnostic flow from tester to ECU
Hardware Provided
ANCIT-NXPS32K144 SmartWheels Evaluation Kit, TOSUN CAN interface hardware (USB-to-CAN), USB Cable, Jumper Wires
(Provided to all participants on a returnable basis)
Software
S32 Design Studio, ANCIT GenX Tool (ECU configuration & generation), TSMaster (CAN simulation & analysis)
(Installation support provided before the training delivery date)
Hands-on Activities
Microcontroller — Identify peripherals in ECU hardware
CAN — Decode raw CAN frames; identify ID, DLC, signals
DBC Creation — Create DBC for Interior Light ECU; define signals
GenX ECU Development — Configure ECU project; map signals into application logic
TSMaster — Import DBC; simulate CAN messages; monitor live signals
Diagnostics — Send UDS request (RDBI – 0x22, WDBI – 0x2E, DSC – 0x10); observe ECU response; trace full diagnostic flow
Expected Learning Outcomes
Understand ECU architecture and microcontroller basics
Interpret and analyse CAN communication
Create and validate a DBC file using industry conventions
Develop a simple ECU using configuration tools (ANCIT GenX)
Simulate and debug CAN communication using TSMaster
Understand AUTOSAR vs legacy system differences
Perform basic UDS diagnostics (RDBI, WDBI, DSC flow)
Visualize complete ECU communication stack (Application → CAN bus)
Prerequisites- Basic C programming knowledge Understanding of embedded systems fundamentals
Level of Depth : Intermediate → Advanced
Workshop on Deploying Vision AI at the Edge: A Hands-On Helmet Detection
Date: 18 September 2026
Time: 9:30 AM
Venue: SB 535, GITAM (Deemed to be University), Bengaluru
Resource Person:
Mubeen Jukaku
Technology Head, Emertxe Information Technologies, Bangalore
Who Can Participate:
Academicians, Industry Professionals, Research Scholars, and UG/PG Students.
Learning Outcomes
Understand Edge AI fundamentals and the importance of on-device inference for real-time transportation and smart-mobility applications.
Build a computer vision pipeline for helmet detection using a pre-trained YOLO object-detection model.
Perform real-time object detection on video streams to identify two-wheeler riders and determine helmet compliance.
Apply model optimization techniques such as quantization and convert models into deployment-friendly formats including TensorFlow Lite and ONNX.
Benchmark AI models and interpret the trade-offs between detection accuracy, inference latency, throughput, and model size.
Apply the learned techniques to vehicular, surveillance, industrial, and smart-mobility computer vision applications.
Contact:
Dr. Zameer Ahmed Adhoni
8971251590
