Knowledge acquisition for visually oriented planning:
Abstract: "Many planning tasks can be represented using mental models in which an expert manipulates objects from one state to another (delivery route planning -- trucks, buildings, packages, routes, etc.; part machining -- parts, drill, mill, drill-bit, etc.). This suggests a highly graphical...
Saved in:
| Main Author: | |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Pittsburgh, PA
School of Computer Science, Carnegie Mellon Univ.
1992
|
| Series: | School of Computer Science <Pittsburgh, Pa.>: CMU-CS
1992,188 |
| Subjects: | |
| Online Access: | Inhaltsverzeichnis |
| Summary: | Abstract: "Many planning tasks can be represented using mental models in which an expert manipulates objects from one state to another (delivery route planning -- trucks, buildings, packages, routes, etc.; part machining -- parts, drill, mill, drill-bit, etc.). This suggests a highly graphical knowledge acquisition tool where the expert is able to capture the visual intuition of the problem solving to facilitate the encoding of a domain knowledge base. By exploring knowledge acquisition for object manipulation domains, insight will be gained in how knowledge is acquired and represented for such visually oriented tasks. This thesis addresses graphical knowledge acquisition in visually oriented domains in the context of Prodigy, a general problem solving and planning architecture The prototype system, called APPRENTICE, demonstrates the main ideas in the thesis. This system establishes the feasibility of a graphical interface to enhance the ability of the expert to develop factual domain knowledge (objects, relations, and operators) in multiple domains. The system has been evaluated in four studies. In the first study, 32 AI students used the system to build their own domains. In the second study, domains developed by different types of users were completed faster using graphical input than using textual input. The third study was a learning study in which a subject developed several domains in APPRENTICE Finally, the fourth study demonstrated the ability to develop a larger domain in the system. APPRENTICE and its techniques proved to be usable, flexible and extendable. |
| Item Description: | Zugl.: Pittsburgh, Pa., Univ., Diss., 1992 |
| Physical Description: | Getr. Zählung graph. Darst. |
Staff View
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV010171781 | ||
| 003 | DE-604 | ||
| 005 | 20010102 | ||
| 007 | t | ||
| 008 | 950509s1992 d||| m||| 00||| eng d | ||
| 035 | |a (OCoLC)27308295 | ||
| 035 | |a (DE-599)BVBBV010171781 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91 | ||
| 082 | 0 | |a 510.7808 |b C28r 92-188 | |
| 084 | |a DAT 760d |2 stub | ||
| 084 | |a DAT 703d |2 stub | ||
| 088 | |a CMU CS 92 188 | ||
| 100 | 1 | |a Joseph, Robert L. |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Knowledge acquisition for visually oriented planning |c Robert Leonard Joseph |
| 246 | 1 | 3 | |a CMU CS 92 188 |
| 264 | 1 | |a Pittsburgh, PA |b School of Computer Science, Carnegie Mellon Univ. |c 1992 | |
| 300 | |a Getr. Zählung |b graph. Darst. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a School of Computer Science <Pittsburgh, Pa.>: CMU-CS |v 1992,188 | |
| 500 | |a Zugl.: Pittsburgh, Pa., Univ., Diss., 1992 | ||
| 520 | 3 | |a Abstract: "Many planning tasks can be represented using mental models in which an expert manipulates objects from one state to another (delivery route planning -- trucks, buildings, packages, routes, etc.; part machining -- parts, drill, mill, drill-bit, etc.). This suggests a highly graphical knowledge acquisition tool where the expert is able to capture the visual intuition of the problem solving to facilitate the encoding of a domain knowledge base. By exploring knowledge acquisition for object manipulation domains, insight will be gained in how knowledge is acquired and represented for such visually oriented tasks. This thesis addresses graphical knowledge acquisition in visually oriented domains in the context of Prodigy, a general problem solving and planning architecture | |
| 520 | 3 | |a The prototype system, called APPRENTICE, demonstrates the main ideas in the thesis. This system establishes the feasibility of a graphical interface to enhance the ability of the expert to develop factual domain knowledge (objects, relations, and operators) in multiple domains. The system has been evaluated in four studies. In the first study, 32 AI students used the system to build their own domains. In the second study, domains developed by different types of users were completed faster using graphical input than using textual input. The third study was a learning study in which a subject developed several domains in APPRENTICE | |
| 520 | 3 | |a Finally, the fourth study demonstrated the ability to develop a larger domain in the system. APPRENTICE and its techniques proved to be usable, flexible and extendable. | |
| 650 | 4 | |a Knowledge acquisition (Expert systems) | |
| 650 | 0 | 7 | |a Maschinelles Sehen |0 (DE-588)4129594-8 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Wissenserwerb |0 (DE-588)4241169-5 |2 gnd |9 rswk-swf |
| 655 | 7 | |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Wissenserwerb |0 (DE-588)4241169-5 |D s |
| 689 | 0 | 1 | |a Maschinelles Sehen |0 (DE-588)4129594-8 |D s |
| 689 | 0 | |5 DE-604 | |
| 830 | 0 | |a School of Computer Science <Pittsburgh, Pa.>: CMU-CS |v 1992,188 |w (DE-604)BV006187264 |9 1992,188 | |
| 856 | 4 | 2 | |m GBV Datenaustausch |q application/pdf |u http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=006756174&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |3 Inhaltsverzeichnis |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-006756174 | ||
Record in the Search Index
| _version_ | 1804124569073614848 |
|---|---|
| adam_text | IMAGE 1
KNOWLEDGE ACQUISITION FOR VISUALLY ORIENTED PLANNING
ROBERT LEO NARD JOSEPH AUGUST 24, 1992
CMU-CS-92-188
SCHOOL OF COMPUTER SCIENCE CARNEGIE MELLON UNIVERSITY PITTSBURGH, PA
15213-3890
SUBMITTED IN PARTIALFULFILLMENT OF THE REQUIREMENTSFOR THE
DEGREE OFDOCTOR OFPHILOSOPHY
1992 ROBERT L. JOSEPH
THIS RESEARCH WAS SPONSORED IN PART BY AT&T BELL LABORATORIES AND IN
PART BY THE AVIONICS LABORATORY, WRIGHT RESEARCH AND DEVELOPMENT CENTER,
AERONAUTICAL SYSTEMS DIVISION (AFSC), U. S. AIR FORCE, WRIGHT-PATTERSON
AFB, OH 45433-6543 UNDER CONTRACT F33615-90-C-1465, ARPA ORDER NO. 7597.
THE VIEWS AND CONCLUSIONS CONTAINED IN THIS DOCUMENT ARE THOSE OF THE
AUTHOR AND SHOULD NOT BE INTERPRETED AS REPRESENTING THE OFFICIAL
POLICIES, EITHER EXPRESSED OR IMPLIED, OF AT&T BELL LABORATORIES OR THE
U.S. GOVERNMENT.
UB/TIB HANNOVER 111 985 331
IMAGE 2
TABLE OF CONTENTS
CHAPTER 1 -MOTIVATION 1
1.1 PREVIEW OF THESIS 1
1.1.1 EXAMPLE OF A DOMAIN BEINGDEVELOPED IN APPRENTICE 2 1.2 PROBLEM
OUTLINE 6
1.3 SIGNIFICANCE OF RESEARCH
7
1.4 RESULTS 8
1.5 READER S GUIDE 10
CHAPTER 2-RELATED WORK
11
CHAPTER 3 - APPRENTICE ARCHITECTURE 17
3.1 PRODIGY 17
3.1.1 OPERATION OF THE PRODIGY PLANNER
18
3.1.2 PRODIGY FORMAT 20
3.1.2.1 DEFINING OBJECT TYPES 20
3.1.2.2 DEFINING PREDICATES AND OPERATORS 20
3.1.2.3 DEFINING A STATE : 22
3.1.3 EXAMPLE TRACE ;
22
3.2 DOMAIN BUILDER 24
3.2.1 HIGHLEVEL WINDOW DESCRIPTION
24
3.2.1.1 MODELWINDOW 25
3.2.1.2 RELATION WINDOW 26
3.2.1.3 OPERATOR WINDOW 29
3.2.1.4 STATE WINDOW 30
3.2.1.5 PROBLEM WINDOW 32
3.2.1.6 EXAMPLE TRACE 33
3.2.2 ANIMATION ALGORITHM 34
3.2.3 PRIMITIVE ELEMENTS FOR THE DOMAIN BUILDER 38
3.3 FRAMEGRAPHICS - LOW LEVELGRAPHICS . 40
CHAPTER 4 - EMPIRICAL ANALYSIS: USER STUDIES
45
4.1 STUDY 1: COVERAGE AND USABILITY 45
4.1.1. STUDY 1: HYPOTHESIS 46
4.1.2 STUDY 1: PROCEDURE 46
4.1.3 STUDY 1: RESULTS 47
4.1.3.1 EIGHT PUZZLE DOMAIN 47
4.1.3.2 DNA MOLECULE DOMAIN.. 51
4.1.3.3 OTHER RESULTS 54
4.1.4 STUDY 1: ANALYSIS 56
4.1.5 STUDY 1: CONCLUSION 58
4.2 STUDY 2: APPRENTICE VERSUS EMACS STUDY 58
4.2.1 STUDY 2: HYPOTHESIS 58
4.2.2 STUDY 2: PROCEDURE 58
4.2.2.1 PHASE 1: DOMAIN BUILDING 59
4.2.1.1.1 PHASE 1: RESULTS 60
4.2.1.1.2 PHASE 1: ANALYSIS 61
4.2.2.2 PHASE 2: DOMAIN UNDERSTANDING 62
4.2.1.2.1 PHASE 2: RESULTS 63
4.2.1.2.2 PHASE 2: ANALYSIS 64
4.2.3 STUDY 2: ANALYSIS
65
4.2.4 STUDY 2: CONCLUSION
66
IMAGE 3
4.3 EARNING STUDY 66
4.4 STUDY 4: MEDIUM SIZE DOMAINBUILDING 66
4.4.1 STUDY 4: HYPOTHESIS 67
4.4.2 STUDY 4: PROCEDURE 67
4.4.3 STUDY 4: RESULTS. 67
4.4.4 STUDY 4: CONCLUSION 69
CHAPTER 5 - DOMAIN CHARACTERISTICS 71
5.1 POSITIVE DOMAIN CHARACTERISTICS 71
5.2 APPRENTICE LIMITATIONS 73
5.3 TECHNIQUES THATAID LARGE DOMAIN DEVELOPMENT 74
CHAPTER6 - CONCLUSION 77
6.1 SUMMARY OF FINDINGS 77
6.2 CONTRIBUTIONS OF THIS RESEARCH 77
6.3 FUTURE WORK 78
6.3.1 APPRENTICE-ASSISTED SEARCH CONTROL RULE DEVELOPMENT 79 6.3.2
SEAMLESS ENVIRONMENT: VISUAL AND TEXTUAL REPRESENTATION 81 6.3.3 SPATIAL
MULTIDIMENSIONAL RELATIONS 82
6.3.4 APPRENTICE TECHNIQUES FOR NON-VISUAL DOMAINS 82 CHAPTER7
-REFERENCES 83
APPENDIX A - RESULTS CHART FROM STUDY 1 A-L
APPENDIX B - DNA DOMAIN CODE B-L
APPENDIX C - SELECTED DOMAINS FROM STUDY 1 C-L
SUBJECT 1 C-2
SUBJECT 12 C-3
SUBJECT22 C-5
SUBJECT 24 C-6
SUBJECT 29 C-8
APPENDIX D - INFORMATION GIVEN TO SUBJECTS IN STUDY 2 PHASE 1 D-L
PRODIGY ANDDOMAIN DESCRIPTION D-2
EMACS/PRODIGY EXAMPLE DOMAIN D-4
APPRENTICE DESCRIPTION D-7
STRIPS WORLD DESCRIPTION D-10
LOGISTIC WORLD DESCRIPTION D-L 1
APPENDIX E - QUESTIONS FROM STUDY 2 PHASE 2 E-L
APPENDIX F - CODE FOR MEDIUM SIZE DOMAIN E-L
APPENDIX G - LEARNING STUDY DOMAINS E-L
HIKING WORLD DESCRIPTION E-3
ROBOT PICKING TULIP DESCRIPTION E-4
IMAGE 4
LIST OF FIGURES
FIGURE 1.1 SEVERAL OBJECTS THAT ARE IN A MACHINING DOMAIN 2
FIGURE 1.2 SOME RELATIONS BETWEEN OBJECTSIN THE MACHININGDOMAIN 2
FIGURE 1.3 STATE IN THE MACHINING DOMAIN 3
FIGURE 1.4 THE PUT-PART-IN-VISE OPERATOR IN THE MACWNING DOMAIN. 3
FIGURE 1.5 OTHER OPERATORS IN THE NRACHINING DOMAIN 4
FIGURE 1.6 SEQUENCE OF OPERATORS IN THE IRACHINING DOMAIN TO DRILL A
HOLE IN A PART 5
FIGURE 1.7 DIAGRAM OF TYPICAL KNOWLEDGE ACQUISITION PROCESS 6
FIGURE 2.1 TABLEOF DIFFERENCES AMONG KNOWLEDGE ACQUISITION SYSTEMS 15
FIGURE 3.1 DIAGRAM OF THE APPRENTICE SYSTEM. 17
FIGURE 3.2 FUNCTIONAL VIEW OF PRODIGY. 19
FIGURE 3.3 IS-A DEFINITIONS FOR THE BLOCKSWORLD. 20
FIGURE 3.4 OPERATOR FORMAT . . 21
FIGURE 3.5 OPERATORS FOR THE BLOCKS WORLD 22
FIGURE 3.6 PROBLEM DEFINITION FOR THE BLOCKS WORLD 22
FIGURE 3.7 PARTIAL SOLUTION TRACEIN PRODIGY FOR THE BLOCKS EXAMPLE
DOMAIN 23
FIGURE 3.8 MODEL WINDOW: EDITING THE BLOCK-MODEL OBJECT 26
FIGURE 3.9 RELATION WINDOW: DEVELOPING THE ON-TABLE RELATION 27
FIGURE 3.10 RELATION WINDOW: SHOWING A NEGATED CONNECTION 28
FIGURE 3.11 RELATION WINDOW: SHOWING A NON-CONNECTION DEFINITION 28
FIGURE 3.12 PICKUP OPERATOR BEFORE CODE IS GENERATED 30
FIGURE 3.13 OPERATOR WINDOW SHOWING THE PICKUP OPERATOR WITH
AUTOMATICALLY
GENERATED PRODIGY CODE 30
FIGURE 3.14 STATE WINDOW: DEFINING INITIAL-STATE-1 31
FIGURE 3.15 STATE WINDOW: DEFINING GOAL-STATE-1 32
IMAGE 5
FIGURE 3.16 PROBLEM WINDOW: DISPLAYING THE INITIAL AND GOAL STATE
DEFINITIONS 33
FIGURE 3.17 VISUAL ANIMATION SHOWING BLOCKS WORLD PROBLEM BEING SOLVED.
THESE ARE SEVERAL SNAPSHOT VIEWS OF STATE CHANGES WITH APPLIED OPERATOR
OR BACKTRACK COMMAND. 34
FIGURE 3.18 ANIMATION DIAGRAM. 35
FIGURE 3.19 THE RELATION WINDOW WITH THE ON RELATION 36
FIGURE 3.20 ADDING THE ON RELATION TO A STATE. THE RELATIVE DISTANCE
BETWEEN THE TWO OBJECTS IN THE RELATION IS USED TO DETERMINE OBJECT
PLACEMENT 36
FIGURE 3.21 FRAMEGRAPHICS DIAGRAM. 41
FIGURE 4.1 ILLUSTRATION OF EIGHT PUZZLE GAME: INITIAL AND FINAL STATE
ALONG WITH INTERMEDIATE MOVES 48
FIGURE 4.2 SQUARE AND TILE OBJECTS FOR THE EIGHTPUZZLE DOMAIN 48
FIGURE 4.3 RELATIONSFOR ME EIGHTPUZZLE DOMAIN 48
FIGURE 4.4 APPRENTICE DEFINITION OF THE MOVE OPERATOR FOR THE EIGHT
PUZZLE DOMAIN 49
FIGURE 4.5 AUTOMATICALLY GENERATED PRODIGY CODE FROM THE GRAPHICALLY 49
FIGURE 4.6 AN INITIAL STATEFOR THE THREE-PUZZLE IN APPRENTICE AND IN
PRODIGY 50
FIGURE 4.7 A GOAL STATE FOR THE THREE-PUZZLE IN APPRENTICE AND IN
PRODIGY 50
FIGURE 4.8 STEPS FOR SOLVINGTHE 3-PUZZLE 51
FIGURE 4.9 OBJECTS IN THE DNA MOLECULE DOMAIN 51
FIGURE 4.10 RELATIONS IN THE DNA MOLECULE DOMAIN 52
FIGURE 4.11 OPERATORS IN THE DNA MOLECULE DOMAIN 53
FIGURE 4.12 INITIAL PROBLEM STATE IN THE DNA MOLECULE DOMAIN 54
FIGURE 4.13 GOAL PROBLEM STATE IN THE DNA MOLECULE DOMAIN 54
FIGURE 4.14 STATISTICS FOR 32 AND 29 SUBJECTS IN STUDY 1 56
FIGURE 4.15 PLOT OF SUBJECTS VERSUS DOMAIN DEVELOPMENT TIMES FROM STUDY
1 57
FIGURE 4.16 COMPARISON PLOT OF STUDY 1 DOMAIN ELEMENTS WITH THE 29
SUBJECTS 57
IMAGE 6
FIGURE 4.17 PHASE 1 DOMAIN BUILDING TIME. THE CHART SHOWS FASTER
DEVELOPMENT TIME FOR APPRENTICE THAN EMACS FOR ALL BUT THE SEASONED
PRODIGY EXPERT 61
FIGURE 4.18 RATIO OF DOMAIN BUILDING TIME (EM/AP) 61
FIGURE 4.19 GRAPHICAL REPRESENTATIONS WITH A MULTIPLE-CHOICE QUESTION 62
FIGURE 4.20 TEXTUAL REPRESENTATIONS WITH A MULTIPLE-CHOICE QUESTION 63
FIGURE 4.21 RESULTS OF PHASE 2, SHOWING MUCH BETTER UNDERSTANDING (FEWER
ERRORS) FOR APPRENTICE THAN EMACS 64
FIGURE 4,22 QUESTION 6 REPRESENTING THE MOVE-BLOCK OPERATOR 65
FIGURE 4.23 TABLE OF SUBJECT 2 S DOMAIN BUILDING TIME. THE DOMAINS WERE
BUILT IN ORDER FROM LEFT TO RIGHT 66
FIGURE 4.24TABLE OF THE ELEMENTS THAT ARE IMPACTED WHEN AN ELEMENT IS
CHANGED 68
FIGURE 5.1 OPERATOR WINDOW: MACHINING DOMAIN ORGANIZED AT BOTTOM OF
WINDOW 76
FIGURE 6.1 EXAMPLE OF A STRIPS WORLD TYPE DOMAIN 80
FIGURE 6.2 EXAMPLE OF POSSIBLE CONTROL RULE BUILT WITH SYSTEM ASSISTANCE
81
FIGURE 6.3 CURRENTLY APPRENTICE PROVIDES FULL DATA FLOW FROM THE
GRAPHICAL INTERFACE TO EMACS, BUT ONLY LIMITED DATA FLOW FROM EMACS TO
THE
GRAPHICAL INTERFACE 81
TABLE A.L STUDY 1 SUBJECTS A-2
|
| any_adam_object | 1 |
| author | Joseph, Robert L. |
| author_facet | Joseph, Robert L. |
| author_role | aut |
| author_sort | Joseph, Robert L. |
| author_variant | r l j rl rlj |
| building | Verbundindex |
| bvnumber | BV010171781 |
| classification_tum | DAT 760d DAT 703d |
| ctrlnum | (OCoLC)27308295 (DE-599)BVBBV010171781 |
| dewey-full | 510.7808 |
| dewey-hundreds | 500 - Natural sciences and mathematics |
| dewey-ones | 510 - Mathematics |
| dewey-raw | 510.7808 |
| dewey-search | 510.7808 |
| dewey-sort | 3510.7808 |
| dewey-tens | 510 - Mathematics |
| discipline | Informatik Mathematik |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03416nam a2200469 cb4500</leader><controlfield tag="001">BV010171781</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20010102 </controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">950509s1992 d||| m||| 00||| eng d</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)27308295</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV010171781</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">510.7808</subfield><subfield code="b">C28r 92-188</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 760d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">DAT 703d</subfield><subfield code="2">stub</subfield></datafield><datafield tag="088" ind1=" " ind2=" "><subfield code="a">CMU CS 92 188</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Joseph, Robert L.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Knowledge acquisition for visually oriented planning</subfield><subfield code="c">Robert Leonard Joseph</subfield></datafield><datafield tag="246" ind1="1" ind2="3"><subfield code="a">CMU CS 92 188</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Pittsburgh, PA</subfield><subfield code="b">School of Computer Science, Carnegie Mellon Univ.</subfield><subfield code="c">1992</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">Getr. Zählung</subfield><subfield code="b">graph. Darst.</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">School of Computer Science <Pittsburgh, Pa.>: CMU-CS</subfield><subfield code="v">1992,188</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Zugl.: Pittsburgh, Pa., Univ., Diss., 1992</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "Many planning tasks can be represented using mental models in which an expert manipulates objects from one state to another (delivery route planning -- trucks, buildings, packages, routes, etc.; part machining -- parts, drill, mill, drill-bit, etc.). This suggests a highly graphical knowledge acquisition tool where the expert is able to capture the visual intuition of the problem solving to facilitate the encoding of a domain knowledge base. By exploring knowledge acquisition for object manipulation domains, insight will be gained in how knowledge is acquired and represented for such visually oriented tasks. This thesis addresses graphical knowledge acquisition in visually oriented domains in the context of Prodigy, a general problem solving and planning architecture</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">The prototype system, called APPRENTICE, demonstrates the main ideas in the thesis. This system establishes the feasibility of a graphical interface to enhance the ability of the expert to develop factual domain knowledge (objects, relations, and operators) in multiple domains. The system has been evaluated in four studies. In the first study, 32 AI students used the system to build their own domains. In the second study, domains developed by different types of users were completed faster using graphical input than using textual input. The third study was a learning study in which a subject developed several domains in APPRENTICE</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Finally, the fourth study demonstrated the ability to develop a larger domain in the system. APPRENTICE and its techniques proved to be usable, flexible and extendable.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Knowledge acquisition (Expert systems)</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Sehen</subfield><subfield code="0">(DE-588)4129594-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Wissenserwerb</subfield><subfield code="0">(DE-588)4241169-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Wissenserwerb</subfield><subfield code="0">(DE-588)4241169-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Maschinelles Sehen</subfield><subfield code="0">(DE-588)4129594-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="830" ind1=" " ind2="0"><subfield code="a">School of Computer Science <Pittsburgh, Pa.>: CMU-CS</subfield><subfield code="v">1992,188</subfield><subfield code="w">(DE-604)BV006187264</subfield><subfield code="9">1992,188</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="m">GBV Datenaustausch</subfield><subfield code="q">application/pdf</subfield><subfield code="u">http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=006756174&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA</subfield><subfield code="3">Inhaltsverzeichnis</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-006756174</subfield></datafield></record></collection> |
| genre | (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV010171781 |
| illustrated | Illustrated |
| indexdate | 2024-07-09T17:47:45Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-006756174 |
| oclc_num | 27308295 |
| open_access_boolean | |
| owner | DE-91 DE-BY-TUM |
| owner_facet | DE-91 DE-BY-TUM |
| physical | Getr. Zählung graph. Darst. |
| publishDate | 1992 |
| publishDateSearch | 1992 |
| publishDateSort | 1992 |
| publisher | School of Computer Science, Carnegie Mellon Univ. |
| record_format | marc |
| series | School of Computer Science <Pittsburgh, Pa.>: CMU-CS |
| series2 | School of Computer Science <Pittsburgh, Pa.>: CMU-CS |
| spelling | Joseph, Robert L. Verfasser aut Knowledge acquisition for visually oriented planning Robert Leonard Joseph CMU CS 92 188 Pittsburgh, PA School of Computer Science, Carnegie Mellon Univ. 1992 Getr. Zählung graph. Darst. txt rdacontent n rdamedia nc rdacarrier School of Computer Science <Pittsburgh, Pa.>: CMU-CS 1992,188 Zugl.: Pittsburgh, Pa., Univ., Diss., 1992 Abstract: "Many planning tasks can be represented using mental models in which an expert manipulates objects from one state to another (delivery route planning -- trucks, buildings, packages, routes, etc.; part machining -- parts, drill, mill, drill-bit, etc.). This suggests a highly graphical knowledge acquisition tool where the expert is able to capture the visual intuition of the problem solving to facilitate the encoding of a domain knowledge base. By exploring knowledge acquisition for object manipulation domains, insight will be gained in how knowledge is acquired and represented for such visually oriented tasks. This thesis addresses graphical knowledge acquisition in visually oriented domains in the context of Prodigy, a general problem solving and planning architecture The prototype system, called APPRENTICE, demonstrates the main ideas in the thesis. This system establishes the feasibility of a graphical interface to enhance the ability of the expert to develop factual domain knowledge (objects, relations, and operators) in multiple domains. The system has been evaluated in four studies. In the first study, 32 AI students used the system to build their own domains. In the second study, domains developed by different types of users were completed faster using graphical input than using textual input. The third study was a learning study in which a subject developed several domains in APPRENTICE Finally, the fourth study demonstrated the ability to develop a larger domain in the system. APPRENTICE and its techniques proved to be usable, flexible and extendable. Knowledge acquisition (Expert systems) Maschinelles Sehen (DE-588)4129594-8 gnd rswk-swf Wissenserwerb (DE-588)4241169-5 gnd rswk-swf (DE-588)4113937-9 Hochschulschrift gnd-content Wissenserwerb (DE-588)4241169-5 s Maschinelles Sehen (DE-588)4129594-8 s DE-604 School of Computer Science <Pittsburgh, Pa.>: CMU-CS 1992,188 (DE-604)BV006187264 1992,188 GBV Datenaustausch application/pdf http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=006756174&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA Inhaltsverzeichnis |
| spellingShingle | Joseph, Robert L. Knowledge acquisition for visually oriented planning School of Computer Science <Pittsburgh, Pa.>: CMU-CS Knowledge acquisition (Expert systems) Maschinelles Sehen (DE-588)4129594-8 gnd Wissenserwerb (DE-588)4241169-5 gnd |
| subject_GND | (DE-588)4129594-8 (DE-588)4241169-5 (DE-588)4113937-9 |
| title | Knowledge acquisition for visually oriented planning |
| title_alt | CMU CS 92 188 |
| title_auth | Knowledge acquisition for visually oriented planning |
| title_exact_search | Knowledge acquisition for visually oriented planning |
| title_full | Knowledge acquisition for visually oriented planning Robert Leonard Joseph |
| title_fullStr | Knowledge acquisition for visually oriented planning Robert Leonard Joseph |
| title_full_unstemmed | Knowledge acquisition for visually oriented planning Robert Leonard Joseph |
| title_short | Knowledge acquisition for visually oriented planning |
| title_sort | knowledge acquisition for visually oriented planning |
| topic | Knowledge acquisition (Expert systems) Maschinelles Sehen (DE-588)4129594-8 gnd Wissenserwerb (DE-588)4241169-5 gnd |
| topic_facet | Knowledge acquisition (Expert systems) Maschinelles Sehen Wissenserwerb Hochschulschrift |
| url | http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=006756174&sequence=000001&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA |
| volume_link | (DE-604)BV006187264 |
| work_keys_str_mv | AT josephrobertl knowledgeacquisitionforvisuallyorientedplanning AT josephrobertl cmucs92188 |