Robots can utilize machine learning, deep learning, reinforcement learning, as well as probabilistic techniques to achieve intelligent behavior. This application of AI to robotic systems is found in the automotive, healthcare, logistics, and military industries. With increasing computing power and sophistication in small robots, more industry use cases are likely to emerge, making AI development for robotics a useful AI developer skill.
In this course, you'll explore the main concepts, frameworks, and approaches needed to work with robotics and apply AI to robots. You'll examine how AI and robotics are used across multiple industries. You'll learn how to work with commonly used algorithms and strategies to develop simple AI systems that improve the performance of robots. Finally, you'll learn how to control a robot in a simulated environment using deep Q-networks.
- discover the key concepts covered in this course
- outline a brief history of the robotics industry
- identify the role AI plays in the robotics industry
- describe the concept of a cobot and list multiple cobot use cases
- list possible applications and use cases of AI in the robotics industry
- specify how AI and robotics are used in the automotive industry
- specify how AI and robotics are used in the healthcare industry
- specify how AI and robotics are used in the manufacturing industry
- specify how AI and robotics are used for warehouse automation and logistics
- specify how AI and robotics are applied in the military
- list open source robotics frameworks and identify the context of their application
- define the role of reinforcement learning in robotics
- give examples of how cognitive and deep learning models are used in the robotics industry
- use common AI tools to improve the navigation of robots across surfaces
- work with deep Q-networks to control a robot in a simulated environment
- configure a robotics AI pipeline using the ROS framework in Jupyter Notebooks
- summarize the key concepts covered in this course
