Abstract--Understanding traffic scenes requires considering heterogeneous information about dynamic agents and the static infrastructure. Task-specific decoders can be applied to predict desired attributes of the scene. To this end, the vehicle needs to correctly estimate which sensory information is reliable I. NDERSTANDING traffic scenes is important for an autonomous vehicle such that it may develop a safe, agents is conveyed by the perception systems of autonomous effective and efficient plan of how to move forward. We raise the hypothesis that considering additional instance, whether a stationary car is parked or just temporarily heterogeneous entities in a traffic scene might add valuable stopped determines whether the autonomous vehicle should information. In particular, reasoning should also involve wait or overtake. Understanding of traffic scenes requires knowledge about static infrastructure, which may either be reasoning about dynamic agents and static infrastructure in perceived or in our case is provided by a High Definition order to predict the intents of nearby dynamic agents (e.g., (HD) map.

Recurrent neural networks are capable of learning the dynamics of an unknown nonlinear system purely from input-output measurements. However, the resulting models do not provide any stability guarantees on the input-output mapping. In this work, we represent a recurrent neural network as a linear time-invariant system with nonlinear disturbances. By introducing constraints on the parameters, we can guarantee finite gain stability and incremental finite gain stability. We apply this identification method to learn the motion of a four-degrees-of-freedom ship that is moving in open water and compare it against other purely learning-based approaches with unconstrained parameters. Our analysis shows that the constrained recurrent neural network has a lower prediction accuracy on the test set, but it achieves comparable results on an out-of-distribution set and respects stability conditions.