Autonomous Mobile Robots

Planning, Navigation and Simulation

1st Edition - September 1, 2023
Author: Rahul Kala
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 1 8 9 0 8 - 1
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 8 9 0 9 - 8

Autonomous Mobile Robots: Planning, Navigation, and Simulation presents detailed coverage of the domain of robotics in motion planning and associated topics in navigatio… Read more

Purchase options

LIMITED OFFER

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code is needed.

Institutional subscription on ScienceDirect

Request a sales quote

Autonomous Mobile Robots: Planning, Navigation, and Simulation presents detailed coverage of the domain of robotics in motion planning and associated topics in navigation. This book covers numerous base planning methods from diverse schools of learning, including deliberative planning methods, reactive planning methods, task planning methods, fusion of different methods, and cognitive architectures. It is a good resource for doing initial project work in robotics, providing an overview, methods and simulation software in one resource. For more advanced readers, it presents a variety of planning algorithms to choose from, presenting the tradeoffs between the algorithms to ascertain a good choice.

Finally, the book presents fusion mechanisms to design hybrid algorithms.

Cover image
Title page
Table of Contents
Copyright
Preface
Acknowledgements
Chapter 1: An introduction to robotics
Abstract
1.1: Introduction
1.2: Application areas
1.3: Hardware perspectives
1.4: Kinematics
1.5: Computer vision
Questions
References
Chapter 2: Localization and mapping
Abstract
2.1: Introduction
2.2: AI primer
2.3: Localization primer
2.4: Mapping primer
2.5: Planning
2.6: Control
2.7: Tracking
2.8: Localization
2.9: Mapping
2.10: Simultaneous Localization and Mapping
Questions
References
Chapter 3: Visual SLAM, planning, and control
Abstract
3.1: Introduction
3.2: Visual simultaneous localization and mapping
3.3: Configuration space and problem formulation
3.4: Planning objectives
3.5: Assessment
3.6: Terminologies
3.7: Control
3.8: Bug algorithms
Questions
References
Chapter 4: Intelligent graph search basics
Abstract
4.1: Introduction
4.2: An overview of graphs
4.3: Breadth-first search
4.4: State space approach
4.5: Uniform cost search
4.6: A* algorithm
4.7: Adversarial search
Questions
References
Chapter 5: Graph search-based motion planning
Abstract
5.1: Introduction
5.2: Motion planning using A* algorithm
5.3: Planning with robot’s kinematics
5.4: Planning in dynamic environments with the D* algorithm
5.5: Lifelong planning A*
5.6: D* lite
5.7: Other variants
Questions
References
Chapter 6: Configuration space and collision checking
Abstract
6.1: Introduction
6.2: Configuration and configuration space
6.3: Collision detection and proximity query primer
6.4: Types of maps
6.5: Space partitioning
6.6: Bounding volume hierarchy
6.7: Continuous collision detection
6.8: Representations
6.9: State spaces
Questions
References
Chapter 7: Roadmap and cell decomposition-based motion planning
Abstract
7.1: Introduction
7.2: Roadmaps
7.3: Visibility graphs
7.4: Voronoi
7.5: Cell decomposition
7.6: Trapezoids
7.7: Other decompositions
7.8: Navigation mesh
7.9: Homotopy and homology
Questions
References
Chapter 8: Probabilistic roadmap
Abstract
8.1: Introduction to sampling-based motion planning
8.2: Probabilistic roadmaps
8.3: Sampling techniques
8.4: Edge connection strategies
8.5: Lazy PRM
Questions
References
Chapter 9: Rapidly-exploring random trees
Abstract
9.1: Introduction
9.2: The algorithm
9.3: RRT variants
9.4: Sampling-based roadmap of trees
9.5: Parallel implementations of RRT
9.6: Multi-tree approaches
9.7: Distance functions
9.8: Topological aspects of configuration spaces
Questions
References
Chapter 10: Artificial potential field
Abstract
10.1: Introduction
10.2: Artificial potential field
10.3: Working of artificial potential field in different settings
10.4: Problems with potential fields
10.5: Navigation functions
10.6: Social potential field
10.7: Elastic strip
Questions
References
Chapter 11: Geometric and fuzzy logic-based motion planning
Abstract
11.1: Introduction
11.2: Velocity obstacle method
11.3: Vector field histogram
11.4: Other geometric approaches
11.5: Fuzzy logic
11.6: Training
Questions
References
Chapter 12: An introduction to machine learning and deep learning
Abstract
12.1: Introduction
12.2: Neural network architecture
12.3: Learning
12.4: Limited connectivity and shared weight neural networks
12.5: Recurrent neural networks
12.6: Deep learning
12.7: Auto-encoders
12.8: Deep convolution neural networks
12.9: Long-short term memory networks
12.10: Adaptive neuro-fuzzy inference system
Questions
References
Chapter 13: Learning from demonstrations for robotics
Abstract
13.1: Introduction
13.2: Incorporating machine learning in SLAM
13.3: Dealing with a lack of data
13.4: Data set creation for supervised learning
13.5: Some other concepts and architectures
13.6: Robot motion planning with embedded neurons
13.7: Robot motion planning using behaviour cloning
Questions
References
Chapter 14: Motion planning using reinforcement learning
Abstract
14.1: Introduction
14.2: Planning in uncertainty
14.3: Reinforcement learning
14.4: Deep reinforcement learning
14.5: Pretraining using imitation learning from demonstrations
14.6: Inverse Reinforcement Learning
14.7: Reinforcement learning for motion planning
14.8: Partially observable Markov decision process
Questions
References
Chapter 15: An introduction to evolutionary computation
Abstract
15.1: Introduction
15.2: Genetic algorithms
15.3: Particle swarm optimization
15.4: Topologies
15.5: Differential evolution
15.6: Local search
15.7: Memetic computing
Questions
References
Chapter 16: Evolutionary robot motion planning
Abstract
16.1: Introduction
16.2: Diversity preservation
16.3: Multiobjective optimization
16.4: Path planning using a fixed size individual
16.5: Path planning using a variable sized individual
16.6: Evolutionary motion planning variants
16.7: Simulation results
Questions
References
Chapter 17: Hybrid planning techniques
Abstract
17.1: Introduction
17.2: Fusion of deliberative and reactive algorithms
17.3: Fusion of deliberative and reactive planning
17.4: Behaviours
17.5: Fusion of multiple behaviours
17.6: Behavioural finite state machines
17.7: Behaviour Trees
17.8: Fusion of cell decomposition and fuzzy logic
17.9: Fusion with deadlock avoidance
17.10: Bi-level genetic algorithm
Questions
References
Chapter 18: Multi-robot motion planning
Abstract
18.1: Multi-robot systems
18.2: Planning in multi-robot systems
18.3: Centralized motion planning
18.4: Decentralized motion planning
18.5: Path velocity decomposition
18.6: Repelling robot trajectories
18.7: Co-evolutionary approaches
Questions
References
Chapter 19: Task planning approaches
Abstract
19.1: Task planning in robotics
19.2: Representations
19.3: Backward search
19.4: GRAPHPLAN
19.5: Constraint satisfaction
19.6: Partial order planning
19.7: Integration of task and geometric planning
19.8: Temporal logic
Questions
References
Chapter 20: Swarm and evolutionary robotics
Abstract
20.1: Swarm robotics
20.2: Swarm robotics problems
20.3: Neuro-evolution
20.4: Evolutionary robotics
20.5: Simulations with ARGOS
20.6: Evolutionary mission planning
Questions
References
Chapter 21: Simulation systems and case studies
Abstract
21.1: Introduction
21.2: General simulation framework
21.3: Robot Operating System
21.4: Simulation software
21.5: Traffic simulation
21.6: Planning humanoids
21.7: Case studies
Questions
References
Index

Purchase options

Save 50% on book bundles

Institutional subscription on ScienceDirect

Rahul Kala