Confidence fusion [sensor fusion]

The field of sensor fusion is well developed, but approaches to describing the confidence one ought to have in the fused result as a function of the confidence one has in the individual measurements is not. This speculative paper is intended to stimulate discussion in the robotics and instrumentation communities regarding how to approach "confidence fusion" in a way that can be practically applied in robotics applications and is intuitively satisfying with respect our feelings regarding how confidence in measurements ought to propagate. Preliminary ideas are developed in the context of a scenario wherein two one-bit-output sensors in which we have different confidence are used together. The results are compared with numerical experiments simulating a real-life experiment that we have described in the field of sensor fusion for context-aware computing.

[1]  Jie Yang,et al.  Sensor Fusion Using Dempster-Shafer Theory , 2002 .

[2]  Mel Siegel,et al.  Sensor fusion for context understanding , 2002, IMTC/2002. Proceedings of the 19th IEEE Instrumentation and Measurement Technology Conference (IEEE Cat. No.00CH37276).

[3]  Mel Siegel,et al.  Sensor fusion using Dempster-Shafer theory II: static weighting and Kalman filter-like dynamic weighting , 2003, Proceedings of the 20th IEEE Instrumentation Technology Conference (Cat. No.03CH37412).

[4]  Mel Siegel,et al.  Objective evaluation of subjective decisions , 2003, IEEE International Workshop on Soft Computing Techniques in Instrumentation, Measurement and Related Applications, 2003. SCIMA 2003..

[5]  Mel Siegel,et al.  Sensor data fusion for context-aware computing using dempster-shafer theory , 2004 .