Multisensor Fusion: A Minimal Representation FrameworkThe fusion of information from sensors with different physical characteristics, such as sight, touch, sound, etc., enhances the understanding of our surroundings and provides the basis for planning, decision-making, and control of autonomous and intelligent machines. The minimal representation approach to multisensor fusion is based on the use of an information measure as a universal yardstick for fusion. Using models of sensor uncertainty, the representation size guides the integration of widely varying types of data and maximizes the information contributed to a consistent interpretation. In this book, the general theory of minimal representation multisensor fusion is developed and applied in a series of experimental studies of sensor-based robot manipulation. A novel application of differential evolutionary computation is introduced to achieve practical and effective solutions to this difficult computational problem. |
Contents
Preface | 1 |
1 | 17 |
Multisensor Fusion in Object Recognition | 43 |
Minimal Representation | 57 |
Environment and Sensor Models | 75 |
Minimal Representation Multisensor Fusion | 91 |
Multisensor Data Fusion | 125 |
Applying the Abstract Framework to Concrete | 151 |
Discussion of Experimental Results | 225 |
Conclusion | 237 |
Appendix A List of Symbols | 247 |
Error Residuals | 257 |
Appendix E Properties of Mixture Representation Size | 263 |
TTTT | 269 |
Appendix H Quaternion Algebra | 275 |
78 | 287 |
Multisensor Object Recognition in Three Dimen | 173 |
75 | 202 |
Laboratory Experiments | 203 |
43 | 208 |
45 | 214 |
291 | |
297 | |
306 | |
313 | |
Other editions - View all
Multisensor Fusion: A Minimal Representation Framework Rajive Joshi,Arthur C Sanderson Limited preview - 1999 |
Common terms and phrases
ê accuracy and precision bits needed CDFS computed constraint equation contact points convergence coordinate frame correspondence model data feature representation data fusion differential evolution ellipsoidal encoding scheme environment model library environment model parameters error residuals evolution program evolutionary algorithms framework fusion and model given interpretation j₁ Kolmogorov complexity log₂ Lwedge measurement space minimal representation minimal representation size model class model features model selection modeled data features multisensor data multisensor fusion number of bits number of data number of vision observation errors observed data features outliers Pªja Pªjs parameter resolution polynomial pose parameters pose transform quaternion reference pose robot rotation search algorithms sensor accuracy sensor data sensor models sensor precision sensor resolution shape model shown in Figure specified surface normal tactile sensor three-dimensional tion touch data features two-dimensional two-part encoding uncertainty model uncertainty region unmodeled vector vertex features vision data features vision sensor