Summary
1. the state vector that represents the current state of a car includes {Position, Heading, Speed, Yaw rate, the number of lanes to the left, the number of lanes to the right}
2. the state vector of the target as well as those of its six neighbors are used for input
3. 4 LSTMs are used and the network structure is determined based on factor model
1. Input
. i-th vehicle's state vector includes {Position, Heading, Speed, Yaw rate, the number of lanes to the left, the number of lanes to the right}
. the observed state vectors are used for input
. the target veh. as well as its neighbors are considered
2. Network structure
. three RNNs represent three factor functions of the following equations.
. red factor function (corresponds to the upper RNN in the network structure figure) presents the relations between the target and the neighbors in the left lane
. green and blue, respectively, present the relations to the same lane and the right lane
3. Results
