Autoliv Asp, Incorporated

Bei Yan

Shan Cong

Systems and methods are presented herein for improved cross-path detection between a host vehicle and a target object. In general, the cross-path angle by solving a multiple hypothesis problem characterized by independent calculations across a first plurality of time points, the multiple hypothesis problem supposing a plurality of possible cross-path angle solutions, each cross-path angle solution representing a corresponding possible trajectory for the target object. Advantageously, a cross-traffic alert or other feedback may be triggered based at least partially on whether the target object is within a region of interest, wherein the region of interest is determined at least in part based on the estimated cross-path angle. In some embodiments the cross-path angle may be determined by selecting a cross-path angle solution from the plurality of possible cross-path angle solutions which minimizes a variance between results of the independent calculations across the first plurality of time points. Other feature disclosed herein include, determining an estimate for the cross-path angle for each of a plurality of trackings of the target object, wherein each tracking is characterized by a different set of two or more time points. This may advantageously enable, determining a change in trajectory of the target object based on variance between cross-path angle estimates.

Growing community of inventors

Farmington Hills, MI, United States of America

Bei Yan