0.25
0.5
0.75
1.25
1.5
1.75
2
Map Building without Localization by Dimensionality Reduction Techniques
Published on Jun 23, 20077002 Views
This paper proposes a new map building framework for mobile robot named Localization-Free Mapping by Dimensionality Reduction (LFMDR). In this framework, the robot map building is interpreted as a pro
Related categories
Chapter list
Map Building without Localization by Dimensionality Reduction Techniques00:00
Motivation00:21
Purpose01:31
Map Building Problem to Consider02:13
Related Works : SLAM [Thrun 02]02:50
Related Works : Dimensionality Reduction and Mapping (1)03:43
Related Works : Dimensionality Reduction and Mapping (2)04:18
Related Works : Dimensionality Reduction and Mapping (cont.)04:46
Proposed Framework : LFMDR (1) Assumptions05:11
Proposed Framework : LFMDR (2) Interpretation as a DR Problem06:13
Proposed Framework : LFMDR (4) Procedure06:36
Features of LFMDR (1) (Comparison with SLAM)07:17
Features of LFMDR (2) (Comparison with Other DR-based Approaches)08:32
Experiment09:36
DR Methods10:21
Case 1 : Visibility-Only Mapping Description10:49
Case 1 : Visibility-Only Mapping Visibility Measurements11:36
Case 1 : Visibility-Only Mapping Maps After 2000 Time Steps12:19
Case 1 : Visibility-Only Mapping Mean Position Errors13:00
Case 1 : Visibility-Only Mapping Final Map Errors13:16
Case 2 : Bearing-Only Mapping Description13:37
Case 2 : Bearing-Only Mapping Bearing Measurements14:26
Case 2 : Bearing-Only Mapping Maps After 2000 Time Steps14:51
Case 2 : Bearing-Only Mapping Final Map Errors15:22
Conclusion16:09