Artificial Intelligence in Wireless Robotics.

Cover -- Half Title -- Series Page -- Title Page -- Copyright Page -- Table of Contents -- Preface -- List of Figures -- List of Tables -- List of Abbreviations -- 1: Introduction to Artificial Intelligence and Robotics -- 1.1 Common Sense Knowledge of AI, Cybernetics, and Robotics -- 1.2 Intelligent Agents -- 1.2.1 The Concept of Rationality -- 1.2.2 System Dynamics -- 1.2.3 Task Environments -- 1.2.4 Robotics and Multi-Agent Systems -- 1.3 Reasoning -- 1.3.1 Constraint Satisfaction Problems -- 1.3.2 Solving CSP by Search -- References -- 2: Basic Search Algorithms -- 2.1 Problem-Solving Agents -- 2.2 Searching for Solutions -- 2.3 Uniform Search -- 2.3.1 Breadth-First Search -- 2.3.2 Dynamic Programming -- 2.3.3 Depth-First Search -- 2.4 Informed Search -- 2.5 Optimization -- 2.5.1 Linear Programming -- 2.5.2 Nonlinear Programming -- 2.5.3 Convex Optimization -- References -- 3: Machine Learning Basics -- 3.1 Supervised Learning -- 3.1.1 Regression -- 3.1.2 Bayesian Classification -- 3.1.3 KNN -- 3.1.4 Support Vector Machine -- 3.2 Unsupervised Learning -- 3.2.1 K-Means Clustering -- 3.2.2 EM Algorithms -- 3.2.3 Principal Component Analysis -- 3.3 Deep Neural Networks -- 3.4 Data Preprocessing -- References -- 4: Markov Decision Processes -- 4.1 Statistical Decisions -- 4.1.1 Mathematical Foundation -- 4.1.2 Bayes Decision -- 4.1.3 Radar Signal Detection -- 4.1.4 Bayesian Sequential Decision -- 4.2 Markov Decision Processes -- 4.2.1 Mathematical Formulation of Markov Decision Process -- 4.2.2 Optimal Policies -- 4.2.3 Developing Solutions to Bellman Equation -- 4.3 Decision Making and Planning: Dynamic Programming -- 4.4 Application of MDP to Search A Mobile Target -- 4.5 Multi-Armed Bandit Problem -- 4.5.1 .-Greedy Algorithm -- 4.5.2 Upper Confidence Bounds -- 4.5.3 Thompson Sampling -- References -- 5: Reinforcement Learning.

5.1 Fundamentals of Reinforcement Learning -- 5.1.1 Revisit of Multi-Armed Bandit Problem -- 5.1.2 Basics in Reinforcement Learning -- 5.1.3 Reinforcement Learning Based on Markov Decision Process -- 5.1.4 Bellman Optimality Principle -- 5.2 Q-Learning -- 5.2.1 Partially Observable States -- 5.2.2 Q-Learning Algorithm -- 5.2.3 Illustration of Q-Learning -- 5.3 Model-Free Learning -- 5.3.1 Monte Carlo Methods -- 5.3.2 Temporal Difference Learning -- 5.3.3 SARSA -- 5.3.4 Relationship Between Q-Learning and TD-Learning -- References -- 6: State Estimation -- 6.1 Fundamentals of Estimation -- 6.1.1 Linear Estimator from Observations -- 6.1.2 Linear Prediction -- 6.1.3 Bayesian Estimation -- 6.1.4 Maximum Likelihood Estimation -- 6.2 Recursive State Estimation -- 6.3 Bayes Filters -- 6.4 Gaussian Filters -- 6.4.1 Kalman Filter -- 6.4.2 Scalar Kalman Filter -- 6.4.3 Extended Kalman Filter -- References -- 7: Localization -- 7.1 Localization By Sensor Network -- 7.1.1 Time-of-Arrival Techniques -- 7.1.2 Angle-of-Arrival Techniques -- 7.1.3 Time-Difference-of-Arrivals Techniques -- 7.2 Mobile Robot Localization -- 7.3 Simultaneous Localization and Mapping -- 7.3.1 Probabilistic SLAM -- 7.3.2 SLAM with Extended Kalman Filter -- 7.3.3 SLAM Assisted by Stereo Camera -- 7.4 Network Localization and Navigation -- References -- 8: Robot Planning -- 8.1 Knowledge Representation and Classic Logic -- 8.1.1 Bayesian Networks -- 8.1.2 Semantic Representation -- 8.2 Discrete Planning -- 8.3 Planning and Navigation of An Autonomous Mobile Robot -- 8.3.1 Illustrative Example for Planning and Navigation -- 8.3.2 Reinforcement Learning Formulation -- 8.3.3 Fixed Length Planning -- 8.3.4 Conditional Exhaustive Planning -- References -- 9: Multi-Modal Data Fusion -- 9.1 Computer Vision -- 9.1.1 Basics of Computer Vision -- 9.1.2 Edge Detection.

9.1.3 Image Features and Object Recognition -- 9.2 Multi-Modal Information Fusion Based on Visionary Functionalities -- 9.3 Decision Trees -- 9.3.1 Illustration of Decisions -- 9.3.2 Formal Treatment -- 9.3.3 Classification Trees -- 9.3.4 Regression Trees -- 9.3.5 Rules and Trees -- 9.3.6 Localizing A Robot -- 9.3.7 Reinforcement Learning with Decision Trees -- 9.4 Federated Learning -- 9.4.1 Federated Learning Basics -- 9.4.2 Federated Learning Through Wireless Communications -- 9.4.3 Federated Learning over Wireless Networks -- 9.4.4 Federated Learning over Multiple Access Communications -- References -- 10: Multi-Robot Systems -- 10.1 Multi-Robot Task Allocation -- 10.1.1 Optimal Allocation -- 10.1.2 Multiple Traveling Salesmen Problem -- 10.1.3 Factory Automation -- 10.2 Wireless Communications and Networks -- 10.2.1 Digital Communication Systems -- 10.2.2 Computer Networks -- 10.2.3 Multiple Access Communication -- 10.3 Networked Multi-Robot Systems -- 10.3.1 Connected Autonomous Vehicles in Manhattan Streets -- 10.3.2 Networked Collaborative Multi-Robot Systems -- References -- Index -- About the Author.

A unique aspect of the book is to introduce applying communication and signal processing techniques to enhance traditional artificial intelligence in robotics and multi-agent systems.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2024. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.