This book addresses the use of constrained control and machine learning approaches within data-driven settings in the field of autonomous robots for Industry 5.0 and Intelligent Transportation Systems. The primary aim of the book is to highlight the strict connection between constrained control and machine learning when tackling real-like phenomena in terms of a data-driven framework. The book shows how constrained control techniques and machine learning approaches can be adequately combined to derive novel and more efficient hybrid control architectures for data-driven based scenarios. To this end, several control problems ranging from planning and formation of autonomous multi-vehicles, routing decisions in urban road networks, freeway traffic modeling, to autonomous robotics in healthcare, are considered to highlight the capability of the data-driven approach to combine techniques coming from different research domains. The book is mainly devoted to researchers that, starting from a solid expertise on the constrained control and/or machine learning tools, would improve their ability to jointly use these technicalities in the data-driven setting.

• Addresses use of constrained control and machine learning within data-driven settings;
• Focuses on applications in autonomous robots for Industry 5.0 and intelligent transportation systems;
• Shows how combined constrained control and ML techniques can create efficient hybrid control architectures.

This book addresses the use of constrained control and machine learning approaches within data-driven settings in the field of autonomous robots for Industry 5.0 and Intelligent Transportation Systems. The primary aim of the book is to highlight the strict connection between constrained control and machine learning when tackling real-like phenomena in terms of a data-driven framework. The book shows how constrained control techniques and machine learning approaches can be adequately combined to derive novel and more efficient hybrid control architectures for data-driven based scenarios. To this end, several control problems ranging from planning and formation of autonomous multi-vehicles, routing decisions in urban road networks, freeway traffic modeling, to autonomous robotics in healthcare, are considered to highlight the capability of the data-driven approach to combine techniques coming from different research domains. The book is mainly devoted to researchers that, starting from a solid expertise on the constrained control and/or machine learning tools, would improve their ability to jointly use these technicalities in the data-driven setting.

Addresses use of constrained control and machine learning within data-driven settings; Focuses on applications in autonomous robots for Industry 5.0 and intelligent transportation systems; Shows how combined constrained control and ML techniques can create efficient hybrid control architectures.