Atjaunināt sīkdatņu piekrišanu

Hybrid Deliberative Layer for Robotic Agents: Fusing DL Reasoning with HTN Planning in Autonomous Robots [Mīkstie vāki]

  • Formāts: Paperback / softback, 215 pages, height x width: 235x155 mm, weight: 370 g, XXII, 215 p., 1 Paperback / softback
  • Sērija : Lecture Notes in Computer Science 6798
  • Izdošanas datums: 18-Jul-2011
  • Izdevniecība: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3642225799
  • ISBN-13: 9783642225796
Citas grāmatas par šo tēmu:
  • Mīkstie vāki
  • Cena: 46,91 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Standarta cena: 55,19 €
  • Ietaupiet 15%
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Hybrid Deliberative Layer for Robotic Agents: Fusing DL Reasoning with HTN Planning in Autonomous RobotsPalielināt
  • Formāts: Paperback / softback, 215 pages, height x width: 235x155 mm, weight: 370 g, XXII, 215 p., 1 Paperback / softback
  • Sērija : Lecture Notes in Computer Science 6798
  • Izdošanas datums: 18-Jul-2011
  • Izdevniecība: Springer-Verlag Berlin and Heidelberg GmbH & Co. K
  • ISBN-10: 3642225799
  • ISBN-13: 9783642225796
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9783642225796.html
Keywords:
The Hybrid Deliberative Layer (HDL) solves the problem that an intelligent agent faces in dealing with a large amount of information which may or may not be useful in generating a plan to achieve a goal. The information, that an agent may need, is acquired and stored in the DL model. Thus, the HDL is used as the main knowledge base system for the agent.

In this work, a novel approach which amalgamates Description Logic (DL) reasoning with Hierarchical Task Network (HTN) planning is introduced. An analysis of the performance of the approach has been conducted and the results show that this approach yields significantly smaller planning problem descriptions than those generated by current representations in HTN planning.
1 Introduction
1(12)
1.1 Motivation
2(1)
1.2 Problem Statement
3(1)
1.3 Challenges
4(1)
1.4 Scope
5(1)
1.5 Previous Work
6(3)
1.6 Contributions
9(2)
1.7 Outline
11(2)
2 The Hybrid Deliberative Layer
13(30)
2.1 System Architecture
13(4)
2.1.1 A Brief Overview of Robot Control Architectures
13(3)
2.1.2 The Hybrid Deliberative Layer Architecture
16(1)
2.2 HDL Components
17(10)
2.2.1 Knowledge Bases
17(7)
2.2.2 Description Logic Reasoner
24(1)
2.2.3 Planner
25(2)
2.2.4 Planning Problem Extractor
27(1)
2.3 Concept
27(1)
2.4 Ontologies
28(8)
2.4.1 HTN Planning Definition
29(1)
2.4.2 HTN Planning TBox
30(6)
2.5 Reasoning
36(7)
2.5.1 Algorithm for HTN Planning Domain/Problem Generator
36(2)
2.5.2 Algorithm for Generating SHOP2 Code
38(5)
3 HDL Systems in the Robotics Domain
43(36)
3.1 Modelling the HTN Planning Problem in the HDL System
43(2)
3.2 Navigation Domain
45(9)
3.2.1 Step 1: Define the Actions and Objectives
45(2)
3.2.2 Step 2: Define the Task Networks
47(2)
3.2.3 Step 3: Program the Planning Domain
49(1)
3.2.4 Step 4: Test the Planning Domain
50(2)
3.2.5 Step 5: Define the HTN ABox in the HDL System
52(1)
3.2.6 Step 6: Modelling and Instantiating the States in the HDL System
52(1)
3.2.7 Step 7: Testing the HDL System
53(1)
3.3 Exploiting the HDL System
54(4)
3.3.1 Results
57(1)
3.4 Pick-and-Place Domain
58(21)
3.4.1 Problem Specification
58(1)
3.4.2 Modelling Actors and Objects
59(1)
3.4.3 Defining the HTN Planning Domain for Pick-and-Place Tasks
60(10)
3.4.4 Results
70(9)
4 Case Study: "Johnny Jackanapes"
79(24)
4.1 Robocup@Home
79(3)
4.1.1 Test Scenarios
80(1)
4.1.2 Challenges
81(1)
4.2 Johnny Jackanapes, The Robot
82(8)
4.2.1 Hardware Components
82(2)
4.2.2 Software Components
84(2)
4.2.3 Applications
86(4)
4.3 The HDL System in Johnny Jackanapes
90(13)
4.3.1 Using the HDL System as Knowledge Base Component
91(6)
4.3.2 Solving Robocup@Home Tasks with the HDL System
97(6)
5 HDL Systems in the AI Domain
103(20)
5.1 Blocks World
103(6)
5.1.1 Problem Statement
104(1)
5.1.2 The HTN Planning Domain
104(5)
5.2 HDL Implementation of Blocks World
109(7)
5.2.1 HDL's Blocks World Domain
109(1)
5.2.2 Modelling Blocks World in HDL
110(3)
5.2.3 Enhanced Model of Blocks World Domain in HDL
113(3)
5.3 Experimental Results
116(7)
5.3.1 Simple Blocks World
116(1)
5.3.2 Two Simple Blocks World Problems
117(3)
5.3.3 Complex Blocks World Problems
120(3)
6 Results and Evaluation
123(20)
6.1 Complexity of the HDL System
123(5)
6.2 Experiment Design
128(2)
6.3 Experiments
130(11)
6.3.1 Navigation Domain
130(6)
6.3.2 The Blocks World Domain
136(5)
6.4 Concluding Remarks
141(2)
7 Discussion
143(8)
7.1 HTN Blocks World Anomaly
143(1)
7.2 Inconsistencies in the Model
144(1)
7.3 Defining Usable Objects
145(1)
7.4 HDL and Plan-Based-Control Approaches for Robotics
146(1)
7.5 Plan Recovery from Failures
147(1)
7.6 Operator Cost and Plan Optimisation
148(1)
7.7 HDL versus Other DL-Planning Approaches
148(3)
8 Conclusions
151(6)
8.1 Summary
151(1)
8.2 Strengths and Limitations
152(1)
8.3 Future Work
153(4)
8.3.1 Affordance-Based Planning
153(1)
8.3.2 Using Other HTN Planning Implementations
153(1)
8.3.3 Collocate the Planner Using Web-Service
153(1)
8.3.4 Application in Plan-Based Robot Control
154(1)
8.3.5 Using DL Inference Engine for Plan Repair
154(3)
A Generated Planning Domain
157(38)
A.1 Navigation Domain
157(5)
A.1.1 An Example from the Planning-Domain Instance
157(3)
A.1.2 An Example from the Method Instance
160(2)
A.2 Pick-and-Place Domain
162(10)
A.2.1 Partial Pick-and-Place Domain
163(3)
A.2.2 Complete Pick-and-Place Domain
166(6)
A.3 Johnny Jackanapes Domain
172(6)
A.3.1 Solution Using Pick-and-Place Domain
172(1)
A.3.2 Bring an Object Planning Domain
173(5)
A.4 Blocks World Domain
178(17)
A.4.1 Simple Blocks World Planning Example
183(3)
A.4.2 Two Blocks World Planning Example
186(5)
A.4.3 Complex Blocks World Example
191(4)
B HDL ABox Assertion
195(8)
B.1 Navigation Domain
195(1)
B.2 Pick-and-Place Domain
196(4)
B.2.1 Partial Pick-and-Place Domain
196(2)
B.2.2 Complete Pick-and-Place Domain
198(2)
B.3 Blocks World Domain
200(3)
References 203(8)
Index 211