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
Foundations of TinyML in Robotics
- Key capabilities and constraints inherent to TinyML
- The role of edge AI in enhancing autonomous systems
- Hardware considerations for mobile robots and drones
Embedded Hardware and Sensor Interfaces
- Selection of microcontrollers and embedded boards for robotics
- Integration of cameras, IMUs, and proximity sensors
- Balancing energy consumption and compute budgets
Data Engineering for Robotic Perception
- Strategies for collecting and labeling data for robotics tasks
- Techniques for signal and image preprocessing
- Feature extraction methods suitable for constrained devices
Model Development and Optimization
- Selecting appropriate architectures for perception, detection, and classification
- Establishing training pipelines for embedded ML
- Model compression, quantization, and latency optimization
On-Device Perception and Control
- Executing inference directly on microcontrollers
- Fusing TinyML outputs with control algorithms
- Ensuring real-time safety and system responsiveness
Enhancing Autonomous Navigation
- Implementing lightweight vision-based navigation
- Obstacle detection and avoidance mechanisms
- Maintaining environmental awareness under resource constraints
Testing and Validation of TinyML-Driven Robots
- Utilization of simulation tools and field testing approaches
- Performance metrics specific to embedded autonomy
- Debugging techniques and iterative improvement cycles
Integration into Robotics Platforms
- Deploying TinyML within ROS-based pipelines
- Interfacing ML models with motor controllers
- Maintaining reliability across varying hardware configurations
Summary and Next Steps
Requirements
- A solid understanding of robotics system architectures
- Practical experience with embedded development
- Familiarity with core machine learning concepts
Target Audience
- Robotics engineers
- AI researchers
- Embedded developers
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.