Professor Jeffrey Herrmann (ME/ISR) has written a new book that introduces key systems engineering concepts and design options for metareasoning to make robots smarter. Metareasoning for Robots: Adapting in Dynamic and Uncertain Environments is published by Springer and is part of its Synthesis Lectures on Computer Science series.

 

This state-of-the-art resource will be useful to robotics researchers and engineers. The comprehensive introduction to metareasoning includes a section on how to select an appropriate metareasoning approach, as well as how to synthesize metareasoning policies. 

Herrmann's systems engineering perspective suggests metareasoning is an approach that can improve the overall robot or autonomous system, not just one component or subsystem.

 

In addition to introducing key concepts, Herrmann discusses design options for metareasoning approaches and policies, and presents approaches for policy testing and evaluation. Every chapter has references to valuable works on robotics and metareasoning, and the book uses examples from the author’s own research and other research groups to illustrate these ideas. In addition, the book provides links to books and papers for readers who wish to investigate these topics further.  

 

Introduction to Metareasoning

Metareasoning Design Options

Implementing Metareasoning

Synthesizing Metareasoning Policies

Testing Metareasoning Policies