Design of emergency braking algorithm for pedestrian protection based on multi-sensor fusion
Globally, safety has become an increasingly important issue in the automotive industry. In an attempt to reduce traffic fatalities, UNECE launched a new EU Road Safety Program which aims to decrease the number of road deaths by half by 2020. AEB (Autonomous Emergency Braking) is a very effective active safety system intended to reduce fatalities. This study involves the design of a multi-sensor data fusion strategy and decision-making algorithm for AEB pedestrian. Possible collision avoidance scenarios according to the EuroNCAP protocol are analyzed and a robust pedestrian tracking strategy is proposed. The performance of the AEB system is enhanced by using a braking model to predict the collision avoidance time and by designing the system activation zone according to the relative speed and possible distance required to stop for pedestrians. The AEB activation threshold requires careful consideration. The test results confirm the advantages of the proposed algorithm, the performance of which is described in this paper.
Key wordsEmergency braking AEBS Pedestrian Sensor fusion Decision making Target tracking
Unable to display preview. Download preview PDF.
- Chavez-Garcia, R. O., Burlet, J., Vu, T. D. and Aycard, O. (2012). Frontal object perception using radar and monovision. IEEE Intelligent Vehicle Symp., 159–164.Google Scholar
- Cho, H. G., Seo, Y. W., Kumar, B. V. K. V. and Rajakumar, R. (2014). A multi-sensor fusion system for moving object detection and tracking in urban driving environments. Robotics and Automation (ICRA), IEEE Int. Conf., 1836–1843.Google Scholar
- Eckert, A., Hohm, A. and Lueke, S. (2013). An integrated ADAS solution for pedestrian collision avoidance. Int. Technical Conf. Enhanced Safety of Vehicles (ESV).Google Scholar
- EuroNCAP (2014). Euro NCAP 2020 Roadmap.Google Scholar
- IRTAD (2016). International Traffic Safety Data and Analysis Group. Road Safety Annual Report 2016.Google Scholar
- KoROAD (2015). Road Traffic Safety Authority Korea. Traffic Accident Analysis.Google Scholar
- Seiniger, P., Bartels, O., Kunert, M. and Schaller, T. (2014). Assessment Methodologies for Forward Looking Integrated Pedestrian and Further Extension to Cyclist Safety. IDIADA, ASPECSS D2.5.Google Scholar
- Themann, P., Kotte, J., Raudszus, D. and Eckstein, L. (2015). Impact of positioning uncertainty of vulnerable road users on risk minimization in collision avoidance systems. IEEE Intelligent Vehicles Symp. IV), 1201–1206.Google Scholar
- Tiemann, N., Branz, W. and Schramm, D. (2009). Predictive pedestrian protection-sensor requirements and risk assessment. Proc. Int. Technical Conf. Enhanced Safety Vehicles.Google Scholar
- Westhofen, D., Grundler, C., Doll, K., Brunsmann, U. and Zecha, S. (2012). Transponder and camera-based advanced driver assistance system. IEEE Intelligent Vehicles Symp. IV), 293–298.Google Scholar
- Wiest, J., Hö ffken, M., Kreßel, U. and Dietmayer, K. (2012). Probabilistic trajectory prediction with Gaussian mixture models. IEEE Intelligent Vehicles Symp. IV), 141–146.Google Scholar
- WHO (2013). Pedestrian Safety: A Road Safety Manual for Decision-makers and Practitioners.Google Scholar