Search papers, labs, and topics across Lattice.
3
0
6
5
A framework that fuses the output of Trajectron++, a neural network-based trajectory predictor, with extended Kalman filter (EKF)-based multiple trajectory candidates at a late stage indicates that EKF-based trajectory candidates can effectively complement neural trajectory prediction through learned fusion.
Early lane-change intentions can be recognized with remarkable accuracy up to 3 seconds in advance, thanks to a novel dual neural calibration approach.
