Computer Vision for Robotics: Perception with OpenCV & Deep Learning Training Course

Artificial Intelligence (AI) for Robotics integrates machine learning, control systems, and sensor fusion to develop intelligent machines that can perceive, reason, and act autonomously. Leveraging contemporary tools such as ROS 2, TensorFlow, and OpenCV, engineers are now able to design robots that navigate, plan, and interact with real-world environments with intelligence.

This instructor-led live training, available either online or onsite, is designed for intermediate-level engineers who wish to develop, train, and deploy AI-driven robotic systems using current open-source technologies and frameworks.

Upon completion of this training, participants will be equipped to:

• Utilise Python and ROS 2 to construct and simulate robotic behaviours.
  
• Implement Kalman and Particle Filters for precise localization and tracking.
  
• Apply computer vision techniques using OpenCV for perception and object detection.
  
• Employ TensorFlow for motion prediction and learning-based control.
  
• Integrate SLAM (Simultaneous Localisation and Mapping) to enable autonomous navigation.
  
• Develop reinforcement learning models to enhance robotic decision-making.
  

Format of the Course

• Interactive lectures and discussions.
  
• Hands-on implementation using ROS 2 and Python.
  
• Practical exercises conducted in both simulated and real robotic environments.
  

Course Customisation Options

To arrange a customised training session for this course, please contact us to discuss your requirements.

ROS 2 (Robot Operating System 2) is an open-source framework designed to support the development of complex and scalable robotic applications.

This instructor-led, live training (online or onsite) is aimed at intermediate-level robotics engineers and developers who wish to implement autonomous navigation and SLAM (Simultaneous Localization and Mapping) using ROS 2.

By the end of this training, participants will be able to:

• Set up and configure ROS 2 for autonomous navigation applications.
• Implement SLAM algorithms for mapping and localization.
• Integrate sensors such as LiDAR and cameras with ROS 2.
• Simulate and test autonomous navigation in Gazebo.
• Deploy navigation stacks on physical robots.

Format of the Course

• Interactive lecture and discussion.
• Hands-on practice using ROS 2 tools and simulation environments.
• Live-lab implementation and testing on virtual or physical robots.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

A bot, or chatbot, functions as a virtual assistant designed to automate user interactions across various messaging platforms, enabling faster task completion without requiring human intervention.

Through this instructor-led live training, participants will learn the fundamentals of bot development by creating sample chatbots using industry-standard tools and frameworks.

Upon completion of this training, participants will be able to:

• Identify the various uses and applications of bots
• Comprehend the end-to-end process of developing bots
• Explore the diverse tools and platforms utilised in bot creation
• Construct a sample chatbot for Facebook Messenger
• Construct a sample chatbot using the Microsoft Bot Framework

Audience

• Developers keen on creating their own bots

Course Format

• A blend of lectures, discussions, exercises, and extensive hands-on practice

Edge AI allows artificial intelligence models to operate directly on embedded or resource-limited devices, thereby reducing latency and power usage while enhancing autonomy and privacy within robotic systems.

This instructor-led, live training (available online or onsite) targets intermediate-level embedded developers and robotics engineers who wish to implement machine learning inference and optimization techniques directly on robotic hardware using TinyML and edge AI frameworks.

By the end of this training, participants will be able to:

• Understand the fundamentals of TinyML and edge AI for robotics.
• Convert and deploy AI models for on-device inference.
• Optimize models for speed, size, and energy efficiency.
• Integrate edge AI systems into robotic control architectures.
• Evaluate performance and accuracy in real-world scenarios.

Format of the Course

• Interactive lecture and discussion.
• Hands-on practice using TinyML and edge AI toolchains.
• Practical exercises on embedded and robotic hardware platforms.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

This instructor-led, live training in South Africa (online or onsite) is aimed at intermediate-level participants who wish to explore the role of collaborative robots (cobots) and other human-centric AI systems in modern workplaces.

By the end of this training, participants will be able to:

• Understand the principles of Human-Centric Physical AI and its applications.
• Explore the role of collaborative robots in enhancing workplace productivity.
• Identify and address challenges in human-machine interactions.
• Design workflows that optimize collaboration between humans and AI-driven systems.
• Promote a culture of innovation and adaptability in AI-integrated workplaces.

Human-Robot Interaction (HRI): Voice, Gesture & Collaborative Control is a practical course aimed at introducing participants to the design and implementation of intuitive interfaces for human–robot communication. This training blends theoretical foundations, design principles, and programming practice to create natural and responsive interaction systems leveraging speech, gesture, and shared control techniques. Participants will acquire skills in integrating perception modules, developing multimodal input systems, and engineering robots that collaborate safely with humans.

This instructor-led, live training (available online or onsite) targets beginner to intermediate-level participants keen on designing and implementing human–robot interaction systems that improve usability, safety, and user experience.

Upon completion of this training, participants will be able to:

• Grasp the foundations and design principles of human–robot interaction.
• Develop voice-based control and response mechanisms for robots.
• Implement gesture recognition using computer vision techniques.
• Design collaborative control systems for safe and shared autonomy.
• Evaluate HRI systems based on usability, safety, and human factors.

Format of the Course

• Interactive lectures and demonstrations.
• Hands-on coding and design exercises.
• Practical experiments in simulation or real robotic environments.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Industrial Robotics Automation: Integrating ROS and PLC with Digital Twins is a practical course designed to bridge the gap between industrial automation and contemporary robotics frameworks. Participants will learn how to integrate ROS-based robotic systems with PLCs for synchronized operations, while exploring digital twin environments to simulate, monitor, and optimise production processes. The course places emphasis on interoperability, real-time control, and predictive analysis using digital replicas of physical systems.

This instructor-led, live training (available online or onsite) targets intermediate-level professionals who wish to develop practical skills in connecting ROS-controlled robots with PLC environments and implementing digital twins for automation and manufacturing optimisation.

Upon completion of this training, participants will be able to:

• Understand the communication protocols between ROS and PLC systems.
• Implement real-time data exchange between robots and industrial controllers.
• Develop digital twins for monitoring, testing, and process simulation.
• Integrate sensors, actuators, and robotic manipulators within industrial workflows.
• Design and validate industrial automation systems using hybrid simulation environments.

Course Format

• Interactive lectures and architecture walkthroughs.
• Hands-on exercises integrating ROS and PLC systems.
• Simulation and digital twin project implementation.

Course Customisation Options

• To request customised training for this course, please contact us to arrange.

This instructor-led, live training in South Africa (online or onsite) is designed for engineers who wish to learn about the applicability of artificial intelligence to mechatronic systems.

By the end of this training, participants will be able to:

• Gain an overview of artificial intelligence, machine learning, and computational intelligence.
• Understand the concepts of neural networks and different learning methods.
• Choose artificial intelligence approaches effectively for real-life problems.
• Implement AI applications in mechatronic engineering.

Multi-Robot Systems and Swarm Intelligence is an advanced training course that delves into the design, coordination, and control of robotic teams inspired by biological swarm behaviours. Participants will acquire skills in modelling interactions, implementing distributed decision-making, and optimising collaboration across multiple agents. The curriculum blends theoretical foundations with practical simulation exercises to prepare learners for applications in logistics, defence, search and rescue, and autonomous exploration.

This instructor-led, live training (available online or onsite) targets advanced-level professionals keen to design, simulate, and implement multi-robot and swarm-based systems using open-source frameworks and algorithms.

Upon completion of this training, participants will be able to:

• Grasp the principles and dynamics of swarm intelligence and cooperative robotics.
• Develop communication and coordination strategies for multi-robot systems.
• Implement distributed decision-making and consensus algorithms.
• Simulate collective behaviours such as formation control, flocking, and coverage.
• Apply swarm-based techniques to real-world scenarios and optimisation problems.

Course Format

• Advanced lectures featuring algorithmic deep dives.
• Practical coding and simulation sessions using ROS 2 and Gazebo.
• A collaborative project applying swarm intelligence principles.

Course Customisation Options

• To request customised training for this course, please contact us to arrange.

This instructor-led, live training in South Africa (online or onsite) is aimed at advanced-level robotics engineers and AI researchers who wish to utilize Multimodal AI for integrating various sensory data to create more autonomous and efficient robots that can see, hear, and touch.

By the end of this training, participants will be able to:

• Implement multimodal sensing in robotic systems.
• Develop AI algorithms for sensor fusion and decision-making.
• Create robots that can perform complex tasks in dynamic environments.
• Address challenges in real-time data processing and actuation.

This instructor-led, live training in South Africa (online or on-site) is designed for intermediate-level participants looking to sharpen their skills in designing, programming, and deploying intelligent robotic systems for automation and other applications.

Upon completion of this training, participants will be able to:

• Grasp the principles of Physical AI and its applications in robotics and automation.
• Design and programme intelligent robotic systems for dynamic environments.
• Implement AI models to enable autonomous decision-making in robots.
• Utilise simulation tools for robotic testing and optimisation.
• Tackle challenges such as sensor fusion, real-time processing, and energy efficiency.

Practical Rapid Prototyping for Robotics with ROS 2 & Docker is a hands-on course designed to assist developers in building, testing, and deploying robotic applications efficiently. Participants will acquire skills in containerizing robotics environments, integrating ROS 2 packages, and prototyping modular robotic systems using Docker to ensure reproducibility and scalability. The course places a strong emphasis on agility, version control, and collaborative practices that are well-suited for early-stage development and innovation teams.

This instructor-led, live training (available online or onsite) targets participants at the beginner to intermediate level who wish to accelerate their robotics development workflows using ROS 2 and Docker.

Upon completing this training, participants will be able to:

• Configure a ROS 2 development environment within Docker containers.
• Develop and test robotic prototypes within modular and reproducible setups.
• Utilise simulation tools to validate system behaviour prior to hardware deployment.
• Collaborate effectively through containerised robotics projects.
• Apply continuous integration and deployment concepts within robotics pipelines.

Format of the Course

• Interactive lectures and demonstrations.
• Hands-on exercises involving ROS 2 and Docker environments.
• Mini-projects focused on real-world robotic applications.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Reinforcement learning (RL) represents a machine learning paradigm where agents acquire decision-making skills through interaction with their surroundings. Within the field of robotics, RL empowers autonomous systems to cultivate adaptive control and decision-making capabilities by leveraging experience and feedback.

This instructor-led live training, available either online or onsite, is tailored for advanced-level machine learning engineers, robotics researchers, and developers who aim to design, implement, and deploy reinforcement learning algorithms within robotic applications.

Upon completion of this training, participants will be capable of:

• Gaining a solid grasp of reinforcement learning principles and mathematics.
• Implementing RL algorithms, including Q-learning, DDPG, and PPO.
• Integrating RL with robotic simulation environments utilising OpenAI Gym and ROS 2.
• Training robots to execute complex tasks autonomously via trial and error.
• Enhancing training performance using deep learning frameworks such as PyTorch.

Course Format

• Interactive lectures and discussions.
• Hands-on implementation exercises using Python, PyTorch, and OpenAI Gym.
• Practical assignments in simulated or physical robotic environments.

Customisation Options

• Should you require a customised training programme for this course, please contact us to arrange accordingly.

Robot Manipulation and Grasping with Deep Learning is an advanced course that bridges robotic control with modern machine learning techniques. Participants will explore how deep learning can enhance perception, motion planning, and dexterous grasping in robotic systems. Through theory, simulation, and practical coding exercises, the course guides learners from perception-based control to end-to-end policy learning for manipulation tasks.

This instructor-led, live training (online or onsite) is aimed at advanced-level professionals who wish to apply deep learning methods to enable intelligent, adaptable, and precise robotic manipulation.

By the end of this training, participants will be able to:

• Develop perception models for object recognition and pose estimation.
• Train neural networks for grasp detection and motion planning.
• Integrate deep learning modules with robotic controllers using ROS 2.
• Simulate and evaluate grasping and manipulation strategies in virtual environments.
• Deploy and optimize learned models on real or simulated robotic arms.

Format of the Course

• Expert-led lecture and algorithmic deep dives.
• Hands-on coding and simulation exercises.
• Project-based implementation and testing.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

Smart Robotics involves integrating artificial intelligence into robotic systems to enhance perception, decision-making capabilities, and autonomous control.

This instructor-led live training (available online or onsite) targets advanced-level robotics engineers, systems integrators, and automation leads who aim to implement AI-driven perception, planning, and control within smart manufacturing environments.

Upon completing this training, participants will be able to:

• Understand and apply AI techniques for robotic perception and sensor fusion.
• Develop motion planning algorithms for both collaborative and industrial robots.
• Deploy learning-based control strategies for real-time decision-making.
• Integrate intelligent robotic systems into smart factory workflows.

Course Format

• Interactive lectures and discussions.
• Extensive exercises and practical work.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request customized training for this course, please contact us to arrange your session.