Abstract: A method includes: when there is a possibility of collision between a target vehicle and a target object, classifying the target vehicle and the target object into an active party and a passive party, where the active party has a passage priority relative to the passive party; obtaining a first strategy set that is feasible for the active party; determining a second traveling strategy of the passive party corresponding to each first traveling strategy in the first strategy set based on the first strategy set, to obtain a second strategy set; analyzing execution costs of feasible strategies obtained based on the first strategy set and the second strategy set, to obtain a first cost set; and controlling the target vehicle according to a traveling strategy corresponding to a lowest execution cost in the first cost set.

Abstract: In this application, when an intent of the object is indeterminate, the intent probability of the intent-indeterminate object is inferred by using observed information, and indeterminate interactive game decision-making is performed based on the intent probability, to work out an optimal action of the ego vehicle. In this way, the ego vehicle can properly respond to a jump of an intent of a dynamic object, to reduce improper pulsating brakes and unwanted grab, thereby improving comfort, safety, and trafficability of the ego vehicle.

Abstract: The present disclosure relates to methods and apparatuses for decision making. An example method includes obtaining a predicted moving track of an ego vehicle and predicted moving tracks of obstacles around the ego vehicle. The method further includes determining a game object. The game object is an obstacle that is in the obstacles around the ego vehicle and whose predicted moving track intersects the predicted moving track of the ego vehicle or whose distance from the ego vehicle is less than a specified threshold. The method further includes constructing one sampling game space for each game object based on vehicle information of the ego vehicle, obstacle information of the game object, and road condition information that are collected by a sensor system. Each sampling game space includes one or more game policies. The method further includes calculating a policy cost of each game policy.