Abstract: A method includes obtaining road patch type data associated with at least one road patch type, deriving, from the road patch type data, a set of road patch type parameters for the at least one road patch type, generating, based on the set of road patch type parameters, a set of risk metrics, each risk metric of the set of risk metrics corresponding to a respective road patch type parameter of the set of road patch type parameters, identifying, based at least in part on the set of risk metrics, a set of autonomous vehicle (AV) motion planning constraints selected for the at least one road patch type, and providing the set of AV motion planning constraints to update motion planning functionality performed by at least one component of an AV.

Abstract: Aspects of the disclosure provide for controlling an autonomous vehicle. For instance, data identifying an object may be received. A first portion of a trajectory may be generated using a first uncertainty distribution for the object. The first portion of the trajectory may enable the autonomous vehicle to make progress towards a destination of the autonomous vehicle. A fallback portion of the trajectory may be generated using a second uncertainty distribution for the object. The fallback portion may enable the autonomous vehicle to stop. The second uncertainty distribution may be different from the first uncertainty distribution, and the second uncertainty distribution may be based on a predetermined uncertainty distribution if the autonomous vehicle loses a localization improvement process. The autonomous vehicle may be controlled according to the trajectory.