Autonomous Robotics Master Class
Training workshop on advanced Advanced Autonomous Robotics with hands-on practicals
What you will learn and the outcome
- Insightful and conceptual live training on the concepts of Autonomous Robotics
- Hands on session for Autonomous Robotics using modern AI and ML
- Access to the course material
- Access to online platform for AI/ML operations
- Certificate of achievement
Delivery mode
- You can choose to join either on-site training in Adelaide, or join online from anywhere virtually
- 2 hours x 5 sessions
Best suited for
- Professionals (Engineering, Healthcare, Education, Industrial, Government, etc) who is looking forward to develop Autonomous Robotics solutions
- Business executives (C-level, directors, management) who would like to have advanced understanding of Autonomous Robotics
- University students
- School leavers
- High school students
- Any enthusiasts
Pre-requisite
- Ability to understand scientific concepts
- Basic understanding with Artificial Intelligence and Machine Learning
- Coding with Python
Your trainer
Dr. Kalana Withanage has Ph.D in Computer Vision / Machine Learning BSc. (Hons) in Electrical and Information Engineering 16+ years industrial experience in architecting and developing solutions with machine learning, computer vision, robotics, and embedded systems. He is an inspiring trainer and international community educational event speaker.
Course content
Session 1
AI and ML Overview
Classic programmatic robotics vs Autonomous Robotics
Levels of autonomy
Applications of autonomous robotics - drones, self-driving cars, industrial robots, home companion robots
Autonomous robotic tasks: perception, planning, decision-making, control
Sensors: Cameras, LIDAR, IMU, etc
Actuators: Motors, Engines, Brakes
Communication and Computational Systems
Introduction to ROS
URDF - Universal Robot Definition Format
Hands-on session on communication between robotics sub systems
Session 2
Computer Vision for Autonomous Robotics
Object detection, tracking, recognition
Scene understanding for navigation and manipulation
Data sources from cameras, LIDAR, IMUs.
Sensor fusion
SLAM - Simultaneous Localization and Mapping
Hands-on session on building robot model in simulator, add cameras, LIDAR, and setup navigation using SLAM
Session 3
Trajectory planning - A*, Dijekstra, RRT
Dynamic motion planning with real-time re-planning
Collision avoidance and reactive motion planning
MoveIt simulator for robotic arm motions
Hands-on session on object grasping using real-time path planning in the Moveit simulator
Session 4
Reinforcement Learning for Autonomous Robotics
Policy gradients, Q-learning, Deep reinforcement learning
Hands-on session in RL applied in simulation
Session 5
Real-Time Control for Autonomous Robotics
Closed loop feedback control
PID for position, velocity, acceleration and force control
Decision making framework
Finite State Machine (FSM) and behaviour trees
Human robot collaboration
Hands-on session feedback control and decision making applied in simulator