REDA: A New Methodology to Validate Sensor Systems for Person Detection under Variable Environmental Conditions.

Perception of the environment by sensor systems in variable environmental conditions is very complex due to the interference influences. In the field of autonomous machines or autonomous vehicles, environmental conditions play a decisive role in safe person detection. A uniform test and validation method can support the manufacturers of sensor systems during development and simultaneously provide proof of functionality. The authors have developed a concept of a novel test method, "REDA", for this purpose. In this article, the concept is applied and measurement data are presented. The results show the versatile potential of this test method, through the manifold interpretation options of the measurement data. Using this method, the strengths and weaknesses of sensor systems have been identified with an unprecedented level of detail, flexibility, and variance to test and compare the detection capability of sensor systems. The comparison was possible regardless of the measuring principle of the sensor system used. Sensor systems have been tested and compared with each other with regard to the influence of environmental conditions themselves. The first results presented highlight the potential of the new test method. For future applications, the test method offers possibilities to test and compare manifold sensing principles, sensor system parameters, or evaluation algorithms, including, e.g., artificial intelligence.

The performance of phenomic selection depends on the genetic architecture of the target trait.

KEY MESSAGE: The phenomic predictive ability depends on the genetic architecture of the target trait, being high for complex traits and low for traits with major QTL. Genomic selection is a powerful tool to assist breeding of complex traits, but a limitation is the costs required for genotyping. Recently, phenomic selection has been suggested, which uses spectral data instead of molecular markers as predictors. It was shown to be competitive with genomic prediction, as it achieved predictive abilities as high or even higher than its genomic counterpart. The objective of this study was to evaluate the performance of phenomic prediction for triticale and the dependency of the predictive ability on the genetic architecture of the target trait. We found that for traits with a complex genetic architecture, like grain yield, phenomic prediction with NIRS data as predictors achieved high predictive abilities and performed better than genomic prediction. By contrast, for mono- or oligogenic traits, for example, yellow rust, marker-based approaches achieved high predictive abilities, while those of phenomic prediction were very low. Compared with molecular markers, the predictive ability obtained using NIRS data was more robust to varying degrees of genetic relatedness between the training and prediction set. Moreover, for grain yield, smaller training sets were required to achieve a similar predictive ability for phenomic prediction than for genomic prediction. In addition, our results illustrate the potential of using field-based spectral data for phenomic prediction. Overall, our result confirmed phenomic prediction as an efficient approach to improve the selection gain for complex traits in plant breeding.