Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Edge AI and TinyML
- Overview of AI applications at the edge
- Advantages and obstacles associated with on-device AI execution
- Specific use cases in robotics and automation
Fundamentals of TinyML
- Machine learning techniques for resource-constrained systems
- Strategies for model quantization, pruning, and compression
- Review of supported frameworks and compatible hardware platforms
Model Development and Conversion
- Training lightweight models utilizing TensorFlow or PyTorch
- Converting models for use with TensorFlow Lite and PyTorch Mobile
- Procedures for testing and validating model accuracy
On-Device Inference Implementation
- Deploying AI models to embedded boards such as Arduino, Raspberry Pi, and Jetson Nano
- Linking inference processes with robotic perception and control systems
- Executing real-time predictions and monitoring system performance
Optimization for Edge Performance
- Methods for minimizing latency and reducing energy consumption
- Leveraging hardware acceleration through NPUs and GPUs
- Benchmarking and profiling embedded inference workflows
Edge AI Frameworks and Tools
- Utilizing TensorFlow Lite and Edge Impulse
- Investigating deployment options with PyTorch Mobile
- Debugging and fine-tuning embedded ML processes
Practical Integration and Case Studies
- Architecting edge AI perception systems for robots
- Integrating TinyML into ROS-based robotics architectures
- Examining case studies involving autonomous navigation, object detection, and predictive maintenance
Summary and Next Steps
Requirements
- A solid grasp of embedded systems principles
- Proficiency in Python or C++ programming
- Familiarity with foundational machine learning concepts
Target Audience
- Embedded software developers
- Robotics engineers
- System integrators focused on intelligent devices
21 Hours
Testimonials (2)
Supply of the materials (virtual machine) to get straight into the excersises, and the explanation of the Ros2 core. Why things work a certain way.
Arjan Bakema
Course - Autonomous Navigation & SLAM with ROS 2
its knowledge and utilization of AI for Robotics in the Future.
