Multiagent Robotic Systems 1st Edition by Jiming Liu, Jianbing Wu ISBN 9781420038835 1420038834
Original price was: $50.00.$35.00Current price is: $35.00.
Multiagent Robotic Systems 1st Edition by Jiming Liu, Jianbing Wu- Ebook PDF Instant Download/Delivery: 9781420038835, 1420038834
Full download Multiagent Robotic Systems 1st Edition after payment
Product details:
ISBN 10: 1420038834
ISBN 13: 9781420038835
Author: Jiming Liu, Jianbing Wu
Multiagent Robotic Systems (1st Edition) by Jiming Liu and Jianbing Wu is a seminal work in the field of decentralized robotics, published by CRC Press in 2001. This book delves into the methodologies, computational models, and techniques essential for developing multi-agent robotic systems, with a focus on learning, adaptation, and self-organization
Table of contents:
I Motivation, Approaches, and Outstanding Issues
1 Why Multiple Robots?
1.1 Advantages
1.2 Major Themes
1.3 Agents and Multi-Agent Systems
1.4 Multi-Agent Robotics
2 Toward Cooperative Control
2.1 Cooperation-Related Research
2.1.1 Distributed Artificial Intelligence
2.1.2 Distributed Systems
2.1.3 Biology
2.2 Learning, Evolution, and Adaptation
2.3 Design of Multi-Robot Control
3 Approaches
3.1 Behavior-Based Robotics
3.2 Collective Robotics
3.3 Evolutionary Robotics
3.4 Inspiration from Biology and Sociology
3.5 Summary
4 Models and Techniques
4.1 Reinforcement Learning
4.1.1 Markov Decision Process
4.1.2 Reinforcement Learning Algorithms
4.1.3 Temporal Differencing Techniques
4.1.4 Q-Learning
4.1.5 Multi-Agent Reinforcement Learning
4.2 Genetic Algorithms
4.3 Artificial Life
4.4 Artificial Immune System
4.5 Probabilistic Modeling
4.6 Related Work on Multi-Robot Planning and Coordination
5 Outstanding Issues
5.1 Self-Organization
5.2 Local vs. Global Performance
5.3 Planning
5.4 Multi-Robot Learning
5.5 Coevolution
5.6 Emergent Behavior
5.7 Reactive vs. Symbolic Systems
5.8 Heterogeneous vs. Homogeneous Systems
5.9 Simulated vs. Physical Robots
5.10 Dynamics of Multi-Agent Robotic Systems
5.11 Summary
II Case Studies in Learning
6 Multi-Agent Reinforcement Learning: Technique
6.1 Autonomous Group Robots
6.1.1 Overview
6.1.2 Sensing Capability
6.1.3 Long-Range Sensors
6.1.4 Short-Range Sensors
6.1.5 Stimulus Extraction
6.1.6 Primitive Behaviors
6.1.7 Motion Mechanism
6.2 Multi-Agent Reinforcement Learning
6.2.1 Formulation of Reinforcement Learning
6.2.2 Behavior Selection Mechanism
6.3 Summary
7 Multi-Agent Reinforcement Learning: Results
7.1 Measurements
7.1.1 Stimulus Frequency
7.1.2 Behavior Selection Frequency
7.2 Group Behaviors
7.2.1 Collective Surrounding
7.2.2 Cooperation among RANGER Robots
7.2.2.1
Moving away from Spatially Cluttered Locations
7.2.2.2 Changing a Target
7.2.2.3 Cooperatively Pushing Scattered Objects
7.2.2.4 Collective Manipulation of Scattered Objects
7.2.3
Concurrent Learning in Different Groups of Robots
7.2.3.1 Concurrent Learning in Predator and Prey
7.2.3.2 Chasing
7.2.3.3 Escaping from a Surrounding Crowd
8 Multi-Agent Reinforcement Learning: What Matters?
8.1 Collective Sensing
8.2 Initial Spatial Distribution
8.3 Inverted Sigmoid Function
8.4 Behavior Selection Mechanism
8.5 Motion Mechanism
8.6 Emerging a Periodic Motion
8.7 Macro-Stable but Micro-Unstable Properties
8.8 Dominant Behavior
9 Evolutionary Multi-Agent Reinforcement Learning
9.1 Robot Group Example
9.1.1 Target Spatial Distributions
9.1.2 Target Motion Characteristics
9.1.3 Behavior Learning Mechanism
9.2 Evolving Group Motion Strategies
9.2.1 Chromosome Representation
9.2.2 Fitness Functions
9.2.3 The Algorithm
9.2.4 Parameters in the Genetic Algorithm
9.3 Examples
9.4 Summary
III Case Studies in Adaptation
10 Coordinated Maneuvers in a Dual-Agent System
10.1 Issues
10.2 Dual-Agent Learning
10.3 Specialized Roles in a Dual-Agent System
10.4 The Basic Capabilities of the Robot Agent
10.5 The Rationale of the Advice-Giving Agent
10.5.1 The Basic Actions: Learning Prerequisites
10.5.2 Genetic Programming of General Maneuvers
10.5.3 Genetic Programming of Specialized Strategic Maneuvers
10.6 Acquiring Complex Maneuvers
10.6.1 Experimental Design
10.6.2 The Complexity of Robot Environments
10.6.3 Experimental Results
10.6.4 Lightweight or Heavyweight Flat Posture
10.6.5 Lightweight Curved Posture
10.6.6 Lightweight Corner Posture
10.6.7 Lightweight Point Posture
10.7 Summary
11 Collective Behavior
11.1 Group Behavior
11.1.1 What is Group Behavior?
11.1.2 Group Behavior Learning Revisited
11.2 The Approach
11.2.1 The Basic Ideas
11.2.2 Group Robots
11.2.3 Performance Criterion for Collective Box-Pushing
11.2.4 Evolving a Collective Box-Pushing Behavior
11.2.5 The Remote Evolutionary Computation Agent
11.3 Collective Box-Pushing by Applying Repulsive Forces
11.3.1 A Model of Artificial Repulsive Forces
11.3.2 Pushing Force and the Resulting Motion of a Box
11.3.3 Chromosome Representation
11.3.4 Fitness Function
11.3.5 Examples
11.3.5.1 Task Environment
11.3.5.2 Simulation Results
11.3.5.3 Generation of Collective Pushing Behavior
11.3.5.4 Adaptation to New Goals
11.3.5.5 Discussions
11.4 Collective Box-Pushing by Exerting External Contact Forces and Torques
11.4.1 Interaction between Three Group Robots and a Box
11.4.2 Case 1: Pushing a Cylindrical Box
11.4.2.1 Pushing Position and Direction
11.4.2.2 Pushing Force and Torque
11.4.3 Case 2: Pushing a Cubic Box
11.4.3.1 The Coordinate System
11.4.3.2 Pushing Force and Torque
11.4.4 Chromosome Representation
11.4.5 Fitness Functions
11.4.6 Examples
11.4.6.1 Task Environment
11.4.6.2 Adaptation to New Goals
11.4.6.3 Simulation Results
11.4.6.4 Adaptation to Dynamically Changing Goals
11.4.6.5 Discussions
11.5 Convergence Analysis for the Fittest-Preserved Evolution
11.5.1 The Transition Matrix of a Markov Chain
11.5.2 Characterizing the Transition Matrix Using Eigenvalues
11.6 Summary
IV Case Studies in Self-Organization
12 Multi-Agent Self-Organization
12.1 Artificial Potential Field (APF)
12.1.1 Motion Planning Based on Artificial Potential Field
12.1.2 Collective Potential Field Map Building
12.2 Overview of Self-Organization
12.3 Self-Organization of a Potential Field Map
12.3.1 Coordinate Systems for a Robot
12.3.2 Proximity Measurements
12.3.3 Distance Association in a Neighboring Region
12.3.4 Incremental Self-Organization of a Potential Field Map
12.3.5 Robot Motion Selection
12.3.5.1 Directional
12.3.5.2 Directional
12.3.5.3 Random
12.4 Experiment 1
12.4.1 Experimental Design
12.4.2 Experimental Result
12.5 Experiment
12.5.1 Experimental Design
12.5.2 Experimental Results
12.6 Discussions
13 Evolutionary Multi-Agent Self-Organization
13.1 Evolution of Cooperative Motion Strategies
13.1.1 Representation of a Proximity Stimulus
13.1.2 Stimulus-Response Pairs
13.1.3 Chromosome Representation
13.1.4 Fitness Functions
13.1.5 The Algorithm
13.2 Experiments
13.2.1 Experimental Design
13.2.2 Comparison with a Non-Evolutionary Mode
13.2.3 Experimental Results
13.3 Discussions
13.3.1 Evolution of Group Behaviors
13.3.2 Cooperation among Robots
13.4 Summary
V An Exploration Tool
14 Toolboxes for Multi-Agent Robotics
14.1 Overview
14.2 Toolbox for Multi-Agent Reinforcement Learning
14.2.1 Architecture
14.2.2 File Structure
14.2.3 Function Description
14.2.4 User Configuration
14.2.5 Data Structure
14.3 Toolbox for Evolutionary Multi-Agent Reinforcement Learning
14.3.1 File Structure
14.3.2 Function Description
14.3.3 User Configuration
14.4 Toolboxes for Evolutionary Collective Behavior Implementation
14.4.1 Toolbox for Collective Box-Pushing by Artificial Repul-sive Forces
14.4.1.1 File Structure
14.4.1.2 Function Description
14.4.1.3 User Configuration
14.4.1.4 Data Structure
14.4.2 Toolbox for Implementing Cylindrical/Cubic Box-Pushing Tasks
14.4.2.1 File Structure
14.4.2.2 Function Description
14.4.2.3 User Configuration
14.4.2.4 Data Structure
14.5 Toolbox for Multi-Agent Self-Organization
14.5.1 Architecture
14.5.2 File Structure
14.5.3 Function Description
14.5.4 User Configuration
14.5.5 Data Structure
14.6 Toolbox for Evolutionary Multi-Agent Self-Organization
14.6.1 Architecture
14.6.2 File Structure
14.6.3 Function Description
14.6.4 User Configuration
14.6.5 Data Structure
14.7 Example
14.7.1 True Map Calculation
14.7.2 Initialization
14.7.3 Start-Up
14.7.4 Result Display
References
People also search for:
multiagent robotic systems
types of robotic system
multi agent robotic systems
robotic systems examples
multi-agent systems
Tags: Jiming Liu, Jianbing Wu, Multiagent Robotic Systems