Abstract: Techniques are described for performing vehicle operation that comprises determining, by a computer located in a vehicle, a set of values of a predicted trajectory along which the vehicle is predicted to operate in a driving mode; performing a first determination that the vehicle is operable in the driving mode in response to determining that the set of values of the driving mode is within maximum and minimum values associated with another set of values of a trajectory along which the vehicle is expected to be operated; and causing, in response to the first determination, the vehicle to operate in the driving mode by sending one or more driving related instructions to a device in the vehicle to cause the device to perform cruise control related operations.

Abstract: Techniques are described for performing vehicle operation that comprises determining, by a computer located in a vehicle and for each of a first driving mode and a second driving mode, a set of values of a predicted trajectory along which the vehicle is predicted to operate in a driving mode; performing a first determination that the vehicle is not operable in the first driving mode; performing a second determination that the vehicle is operable in the second driving mode; and causing, in response to the second determination, the vehicle to operate in the second driving mode by sending one or more driving related commands to one or more apparatus in the vehicle.

Abstract: A controller for optimizing a local control policy of a system for trajectory-centric reinforcement learning is provided. The controller includes performing steps of learning a stochastic predictive model for the system using a set of data collected during trial and error experiments performed using an initial random control policy, estimating mean prediction and uncertainty associated, determining a local set of deviations of the system using the learned stochastic system model, from a nominal system state upon use of a control input at a current time-step, determining a system state with a worst-case deviation, determining a gradient of the robustness constraint, providing and solving a robust policy optimization problem using non-linear programming to obtain system trajectory and stabilizing local policy simultaneously, updating the control data according to the solved optimization problem, and output the updated control data via the interface.