To tackle the challenges of the road estimation task, many works employ a fusion of multiple sources. By that, a commonly made assumption is that the sources always are equally reliable. However, this assumption is inappropriate since each source has certain advantages and drawbacks depending on the operational scenarios. Therefore, Tuan Tran Nguyen proposes a novel concept by incorporating reliabilities into the multi-source fusion so that the road estimation task can alternately select only the most reliable sources. Thereby, the author estimates the reliability for each source online using classifiers trained with the sensor measurements, the past performance and the context. Using real data recordings, he shows via experimental results that the presented reliability-aware fusion increases the availability of automated driving up to 7 percentage points compared to the average fusion. Contents

• Reliability-Aware Fusion Framework

• Assessing and Learning Reliability for Ego-Lane Estimation

• Reliability-Based Ego-Lane Estimation Using Multiple SourcesTarget Groups

• Scientists and students in the fields of IT, fusion and automated driving

• Engineers working in industrial research and development of automated drivingAbout the AuthorTuan Tran Nguyen received the Master's degree in computer science and the Ph.D. degree from Otto-von-Guericke University Magdeburg, Germany, in 2013 and 2019, respectively. His research focuses on methods and architectures for reliability-based sensor fusion in intelligent vehicles.

Autorentext
Tuan Tran Nguyen received the Master's degree in computer science and the Ph.D. degree from Otto-von-Guericke University Magdeburg, Germany, in 2013 and 2019, respectively. His research focuses on methods and architectures for reliability-based sensor fusion in intelligent vehicles.

Inhalt
Reliability-Aware Fusion Framework.- Assessing and Learning Reliability for Ego-Lane Estimation.- Reliability-Based Ego-Lane Estimation Using Multiple Sources.