Multi-robot Exploration for Environmental Monitoring The Resource Constrained Perspective
Auteurs : Tiwari Kshitij, Chong Nak Young
Multi-robot Exploration for Environmental Monitoring: The Resource Constrained Perspective is designed to cater to both beginners and experts in the domain alike. Former parts of the book serve to familiarize the readers with the necessary robotics and mathematical tools required to realize the architecture.
The architecture discussed in the book is not confined to environment monitoring, can be extended to search-and-rescue, border patrolling, crowd management, and related applications. Several law enforcement agencies have already started to deploy UAVs to assist them but instead of using teleoperated UAVs, this book proposed methods to fully automate the surveillance missions. Similarly, several government agencies like the US-EPA can benefit from this book by automating the process.
This book deals with applied machine learning for Robotics applications. As a case study, the environment monitoring application is discussed and the interplay between machine learning models (software) and robots (hardware) is analysed. Several challenges when deploying such models in real missions have been addressed and solved, thereby, laying down stepping stones towards realizing the architecture proposed herewith.
This book will be a great resource for graduate students in Computer Science, Computer Engineering, Robotics, Machine Learning and Mechatronics
- Analyses the constant conflict between the machine learning models and robot resources
- Unlike existing machine learning techniques, this book does not split the data into training and testing data a priori The ?expert is capable of doing this in real time This allows for active data acquisition which is useful especially in situations when robots are deployed in unknown environments
- Presents a novel range estimation framework and tested on real robots (custom built and commercially available)
3. Modelling the Spatial Variations of the Environment using Stationary Homoscedastic GPs
4. Resource Constrained Path Planning with Homing Guarantee
5. Operational Range Estimation
6. Fusion of Distributed Gaussian Process Experts (FuDGE)
7. Towards a Spatiotemporal Environment Monitoring for Continuous Domains
8. Conclusion and Future Works
 Ph.D. students, post-doctoral researchers etc., who intend to develop and optimize state-of-the-art machine learning models to guarantee real-time performance on robotic platforms.
 Government agencies like EPA and other associated bodies who want to monitor and control pollutants and hazardous materials
Nak-Young received the B.S., M.S., and Ph.D. degrees in mechanical engineering from Hanyang University, Seoul, Korea, in 1987, 1989, and 1994, respectively. From 1994 to 2007, he was a member of research staff at Daewoo Heavy Industries and KIST in Korea, and MEL and AIST in Japan. In 2003, he joined the faculty of Japan Advanced Institute of Science and Technology (JAIST), where he currently is a Professor of Information Science. He also served as Vice Dean for Research and Director of the Center for Intelligent Robotics at JAIST. He was a Visiting Scholar at Northwestern University, Georgia Institute of Technology, University of Genoa, and Carnegie Mellon University, and also served as an Associate Graduate Faculty at the University of Nevada, Las Vegas, International Scholar at Kyung Hee University, and Distinguished Invited Research Professor at Hanyang University. He serves as Senior Editor of the IEEE Robotics and Automation Letters, Topic Editor-in-Chief of International Journal of Advanced Robotic Systems, and served as Senior Editor of IEEE ICRA CEB, and
Date de parution : 11-2019
Ouvrage de 290 p.
À paraître, réservez-le dès maintenant
125,75 €Ajouter au panier