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.
Duration 21 hours
Course Outline
Introduction to Edge AI and TinyML
- An overview of AI deployment at the edge.
- The advantages and challenges of executing AI on physical devices.
- Relevant use cases in robotics and automation.
Core Concepts of TinyML
- Machine learning tailored for resource-constrained systems.
- Techniques for model quantization, pruning, and compression.
- An examination of supported frameworks and hardware platforms.
Model Development and Conversion
- Training lightweight models using TensorFlow or PyTorch.
- Converting models to TensorFlow Lite and PyTorch Mobile formats.
- Testing and validating model accuracy.
Implementing On-Device Inference
- Deploying AI models on embedded boards such as Arduino, Raspberry Pi, and Jetson Nano.
- Integrating inference processes with robotic perception and control systems.
- Executing real-time predictions and monitoring system performance.
Optimizing for Edge Performance
- Strategies to minimize latency and energy consumption.
- Leveraging hardware acceleration via NPUs and GPUs.
- Benchmarking and profiling embedded inference workloads.
Edge AI Frameworks and Tools
- Utilizing TensorFlow Lite and Edge Impulse.
- Exploring deployment options with PyTorch Mobile.
- Debugging and tuning embedded machine learning workflows.
Practical Integration and Case Studies
- Designing edge AI perception systems specifically for robots.
- Integrating TinyML into ROS-based robotics architectures.
- Case study analyses: autonomous navigation, object detection, and predictive maintenance.
Summary and Future Directions
Requirements
- A solid foundation in embedded systems.
- Proficiency in Python or C++ programming.
- A working knowledge of fundamental machine learning concepts.
Target Audience
- Embedded developers.
- Robotics engineers.
- System integrators focused on intelligent device development.
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.