Author: Rahul Kala, 2016
Road Intelligent Vehicles: Motion planning of intelligent transportation systems involves autonomous vehicle technology, with special attention to navigation and planning, and is divided into three parts. The first part involves using different sensors to sense the environment and then mapping multi-domain perception to map the operational scenario, including topics such as proximity sensors that provide distance to obstacles, vision cameras, and computer vision techniques that can be used to preprocess images and extract relevant features. , and uses classification techniques such as neural networks and support vector machines to identify roads, lanes, vehicles, obstacles, traffic lights, signs, and pedestrians.
With a detailed understanding of the technology behind the vehicle, the second part of the book focuses on the problem of motion planning. A number of planning techniques are discussed and adapted to multi-vehicle traffic scenarios, including the use of sampling-based methods consisting of genetic algorithms and fast exploration of random trees, and graph search-based methods, including hierarchical decomposition of algorithms and for limited exploration Heuristic selection of nodes, based on reactive planning methods, including fuzzy-based planning, potential field-based planning, and planning based on elastic strips and logic.
The third part of the book covers the macro concepts related to intelligent transportation systems, discussing various topics and concepts related to transportation systems, including the description of traffic flow, the basic theory behind transportation systems, and the generation of shock waves. Comprehensive coverage of autonomous vehicles and intelligent transportation systems; provides detailed coverage of challenging problems in navigation and planning; teaches how to compare, contrast, and differentiate navigation algorithms.
Original book:
Contents:
Acknowledgement
1. Introduction
1.1. Introduction
1.2. Why Autonomous Vehicles?
1.3. A Mobile Robot on the Road
1.4. Artificial Intelligence and Planning
1.5. Fully Autonomous and Semi-Autonomous Vehicles
1.6. A Network of Autonomous Vehicles
1.7. Autonomous Vehicles in Action
1.8. Other Types of Robots
1.9. Into the Future
1.10. Summary
2. Basics of Autonomous Vehicles
2.1. Introduction
2.2. Hardware
2.3. Software
2.4. Localization
2.5. Control
2.6. Summary
3. Perception in Autonomous Vehicles
3.1. Introduction
3.2. Perception
3.3. Computer Vision
3.4. Recognition
3.5. Tracking and Optical Flow
3.6. Vision for General Navigation
3.7. Summary
4. Advanced Driver Assistance Systems
4.1. Introduction
4.2. Information-Based Assistance Systems
4.3. Manipulation-Based Assistance Systems
4.4. Feedback Modalities to Driver
4.5. Multi-Vehicle Systems
4.6. Communication
4.7. Summary
5. Introduction to Planning
5.1. Introduction
5.2. Layers of Planning
5.3. Types of Traffic
5.4. Motion-Planning Primitives
5.5. Multirobot Motion Planning
5.6. Motion Planning for Autonomous Vehicles
5.7. Planning for Special Scenarios
5.8. Summary
6. Optimization-Based Planning
6.1. Introduction
6.2. A Brief Overview of Literature
6.3. A Primer on Genetic Algorithm (GA)
6.4. Motion Planning with Genetic Algorithm
6.5. Coordination
6.6. Results
6.7. Summary
7. Sampling-Based Planning
7.1. Introduction
7.2. A Brief Overview of Literature
7.3. A Primer on Rapidly Exploring Random Trees (RRT)
Algorithm 7.1: RRT(source, goal)
Algorithm 7.2: RRT-Connect (source, goal)
Algorithm 7.3: Bi-directional-RRT (source, goal)
7.4. Solution With RRT
Algorithm 7.4: Plan (vehicles, map)
Algorithm 7.5: RRT (source, segment)
7.5. Results
7.6. Solution With RRT-Connect
Algorithm 7.6: RRT-Connect (source, time, vi)
Algorithm 7.7: CheckConnect (tree, node)
Algorithm 7.8: LocalOptimization(τ)
Algorithm 7.9: Plan (road segment, time)
7.7. Results
7.8. Summary
8. Graph Search-Based Hierarchical Planning
8.1. Introduction
8.2. A Brief Overview of Literature
8.3. A Primer on Graph Search
Algorithm 8.1: Uniform Cost Search (G<V,E>, S, GoalTest)
Algorithm 8.2: PrintPath(n)
Algorithm 8.3: A∗ Search (G<V,E>, S, GoalTest)
8.4. Multilayer Planning
8.5. Hierarchy 1: Path Computation
8.6. Hierarchy 2: Pathway Selection
Algorithm 8.4: getPathwaySegments
Algorithm 8.5: getPathway
8.7. Hierarchy 3: Pathway Distribution
hm 8.6: getDistributedPathway
8.8. Hierarchy 4: Trajectory Generation
Algorithm 8.7: getTrajectory
8.9. Algorithm
Algorithm 8.8: RoadSegmentPlan
8.10. Results
8.11. Summary
9. Using Heuristics in Graph Search-Based Planning
9.1. Introduction
9.2. A Brief Overview of Literature
9.3. Dynamic Distributed Lanes for a Single Vehicle
Algorithm 9.1: Uniform Cost Search for a Single Vehicle
Algorithm 9.2: Expansion for a Single Vehicle
9.4. Dynamic Distributed Lanes for Multiple Vehicles
Algorithm 9.3: Getting Number of Vehicles Requiring Independent Lanes
Algorithm 9.4: Division of the Road Into Lanes
Algorithm 9.5: Trajectory Generation From the Current State to the Expanded State
Algorithm 9.6: Free-State Expansion Strategy
Algorithm 9.7: Vehicle-Following Expansion Strategy
Algorithm 9.8: Wait for Vehicle Expansion Strategy
Algorithm 9.9: Selection of Expansion Strategy
9.5. Results
9.6. Summary
10. Fuzzy-Based Planning
10.1. Introduction
10.2. A Brief Overview of Literature
10.3. A Primer on Fuzzy Logic
10.4. Fuzzy Logic for Planning
10.5. Evolution of the Fuzzy Inference System
10.6. Results
10.7. Summary
11. Potential-Based Planning
11.1. Introduction
11.2. A Brief Overview of Literature
11.3. A Primer on Artificial Potential Field
11.4. Lateral Potentials for Planning
11.5. Results for Lateral Potentials
11.6. A Primer on Elastic Strip
11.7. Problem Modelling With an Elastic Strip
11.8. Solution With an Elastic Strip
Algorithm 11.1: Extend1(τ, τstrat,vq)
Algorithm 11.2: Extend(τ, τstrat, vq)
Algorithm 11.3: Plan(τobs, τ, vq)
11.9. Results With an Elastic Strip
11.10. Summary
12. Logic-Based Planning
12.1. Introduction
12.2. A Brief Overview of Literature
12.3. Problem and Solution Modelling
12.4. Behaviours
Algorithm 12.1: ObstacleAvoidance(Ri, map)
12.5. Single-Lane Overtaking
12.6. Complete Algorithm
Algorithm 12.2: Plan(Vehicle Ri, Map, Previous Plan τ)
12.7. Results
12.8. Summary
13. Basics of Intelligent Transportation Systems
13.1. Introduction
13.2. Traffic Systems and Traffic Flow
13.3. Traffic Simulation
13.4. Intelligent Constituents of the Transportation System
13.5. Summary
14. Intelligent Transportation Systems With Diverse Vehicles
14.1. Introduction
14.2. A Brief Overview of Literature
14.3. Semiautonomous Intelligent Transportation System for Diverse Vehicles
14.4. Congestion Avoidance in City Traffic
14.5. Summary
15. Reaching Destination Before Deadline With Intelligent Transportation Systems
15.1. Introduction
15.2. A Brief Overview of Literature
15.3. Computing Journey Start Times
15.4. Algorithm for Computing Journey Start Times
15.5. Cooperative Transportation Systems
15.6. Results
15.7. Summary
16. Conclusions
16.1. Conclusions
16.2. Autonomous Vehicles
16.3. Intelligent Transportation Systems
16.4. Limitations
16.5. Closing Remarks
Index
The source code of the algorithm implemented in the book: