Recent Advances in Robot Path Planning Algorithms: A Review of Theory and Experiment

Contents
Preface
Chapter 1
Introduction and Overview
	Routing, an Ongoing Challenge in  Robot Guidance
Chapter 2
Path Planning in  Unknown Environments
	Introduction
	Bug Algorithms Family
		Indication and Terminology of Bug Algorithms
		Bug 1 Algorithm
		Bug 2 Algorithm
		ALG1 Algorithm
		ALG2 Algorithm
		DistBug Algorithm
		The TangBug Algorithm
			Surround Tangential Chart
			Local Tangent Graph
			Local Minimum
		Other Bug Algorithms
			HD-I Algorithm
			Ave Algorithm
			VisBug 21 and 22 Algorithms
			WedgeBug Algorithm
			CautiousBug Algorithm
			Three-Dimensional Bug (3DBug) Algorithm
			Axis-Angle Algorithm
			Opitm-Bug Algorithm
			Unknown Bug Algorithm
			SensBug Algorithm
		D* Algorithm
			D* Algorithm Performance without Barriers
			Case of Taking Obstacles in D* Algorithm into Account
		Com Algorithm
		Class 1 Algorithm
		Rev 1 and Rev 2 Algorithms
	Two Chosen Methodologies for Routing in Unknown Environments
		Histograms of Vector Fields
			Calculation of Each Vector
			Calculation of Sectors
			Histogram Calculation
			How to Use Histogram
		Designing Path Based on Multi-Strategy Approach
			Concepts and Definitions Used in the Proposed Multi Strategic Method
			Building an Environmental Representation Matrix
			Path Design Methods Based on Multi Strategic Approaches
				Minimal Method
				Median Approach
				Full Method
			Output of Proposed Multiple Strategy Approach
				Static Environments
				Full Dynamic Environment
				Partial Dynamic Environment
			Multi Strategic in Action
Chapter 3
Path Planning in  Known Environments
	Introduction
	Feature-Based Guidance
		Preparing Feature Maps
		Storing Feature Maps
		Coinciding Edges
		Adding Bridges
		Graph-Based Guidance towards the Target
	Guidance in Potential Field
		Calculating Potential Field Vectors at Target and  Reference Points
		Calculating Potential Field Vectors of Barriers
		Combining Potential Vectors
		Path Planning Based on Combinational Potential Field Vectors
		Local Minimum
Chapter 4
Path Planning and Robot’s Hardware
	Introduction
	Path Planning Based on Mapping Capabilities
		Mapping Obstacle Maps Using Polygonal and Gridding Methods
		Hierarchical Maps
			Topological Maps
			Feature Maps
	Robot Path Planning Using Vision Sensors
	Robot Path Planning Using Rasterizing
		Configuration Space Method
			Definition of Configuration Space
			Making c-Space Equivalent with Physical Space
			Rasterizing Methods in c-Space
		Potential Field Methods
			Vector Presentation in Potential Field Method
			Bitmap Representation in Potential Field Method
		Combinational Algorithm
			Creating Configuration Space Representation
			Calculating Navigation Function
			Path Design
			How to Display
			Hardware Utilization
			Testing Algorithms
				Example 1: Two-Dimensional Robot Motion in R2×S1 Space
				Example 2: Three-Dimensional Robot Motion (Piano) in R2×S1 Space
Chapter 5
Implementation of Path  Planning Algorithms
	Introduction
	Comparisons among Bug Family Algorithms
		Implementation
		Tests and Results
	An Analytical Method to Avoid Collision of Mobile Robot with Obstacles
		Target Searching at Open Spaces
		Kinematic Model of the Robot
		Position Control in Open Space
		Rotation Control at Target
		Stability in Switching Control System
		Suggested Method
			Facing Corner-Shaped Obstacles
			Facing Concave Obstacles
			Using the Stored Information of the Observed Obstacles
			Simulation and Laboratory Results
	Robot Path Planning Using Vision Sensors
		The Color Models
		Low-Pass Filter
		Segmentation and Mode Filter
		Expansion
		Schematic Structure of Vision System
	Path Planning in the Absence of Danger Space
		Synthetic Potential Field Method
			The Rectifier
			Result of Synthetic Potential Field Method
		Linguistic Method
			Simplification
			Result of Linguistic Method
		Markov Decision Processes
			Path Planning
			Results of Markov Decision Processes
			Fuzzy Markov Decision Processes
			Result of Fuzzy Markov Decision Processes in the Absence of  Danger Space
	Path Planning in the Presence of Danger Space
		Disadvantages of Reward Calculation by Linear Relations
		Reward Calculation by the Fuzzy Inference System
		Schematic Structure of Fuzzy Markov Decision Processes
		Results of Fuzzy Markov Decision Processes in the Presence of Danger Space
References
About the Authors
Index
Blank Page