Get in Touch
 Duration 21 hours

Course Outline

TinyML Foundations for Robotics

  • Core capabilities and limitations of TinyML
  • The function of edge AI within autonomous systems
  • Hardware considerations for mobile robots and drones

Embedded Hardware and Sensor Interfaces

  • Microcontrollers and embedded boards suited for robotics
  • Integration of cameras, IMUs, and proximity sensors
  • Balancing energy consumption and compute resources

Data Engineering for Robotic Perception

  • Collection and labeling of data for robotic tasks
  • Signal and image preprocessing methods
  • Feature extraction strategies for resource-constrained devices

Model Development and Optimization

  • Choosing architectures for perception, detection, and classification
  • Training pipelines tailored for embedded ML
  • Model compression, quantization, and latency refinement

On-Device Perception and Control

  • Executing inference on microcontrollers
  • Combining TinyML outputs with control algorithms
  • Ensuring real-time safety and system responsiveness

Enhancing Autonomous Navigation

  • Lightweight, vision-based navigation techniques
  • Obstacle detection and avoidance mechanisms
  • Maintaining environmental awareness under resource constraints

Testing and Validation of TinyML-Driven Robots

  • Simulation tools and field testing methodologies
  • Performance metrics for embedded autonomy
  • Debugging strategies and iterative improvement

Integration into Robotics Platforms

  • Implementing TinyML within ROS-based pipelines
  • Connecting ML models with motor controllers
  • Ensuring reliability across different hardware variations

Summary and Next Steps

Requirements

  • A solid grasp of robotics system architectures
  • Practical experience with embedded development
  • Working knowledge of machine learning concepts

Target Audience

  • Robotics engineers
  • AI researchers
  • Embedded developers

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories