18495071. DECISION MAKING METHOD AND APPARATUS, AND VEHICLE simplified abstract (Huawei Technologies Co., Ltd.)
DECISION MAKING METHOD AND APPARATUS, AND VEHICLE
Organization Name
Inventor(s)
DECISION MAKING METHOD AND APPARATUS, AND VEHICLE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18495071 titled 'DECISION MAKING METHOD AND APPARATUS, AND VEHICLE
Simplified Explanation
The abstract describes a method for decision making in autonomous vehicles by predicting moving tracks of the ego vehicle and obstacles, determining game objects, constructing sampling game spaces, and calculating policy costs.
- Predicted moving tracks of ego vehicle and obstacles are obtained
- Game objects are determined based on predicted moving tracks and distance from ego vehicle
- Sampling game spaces are constructed for each game object
- Game spaces include game policies based on vehicle, obstacle, and road condition information
- Policy costs of each game policy are calculated
Potential Applications
- Autonomous driving systems - Collision avoidance systems - Traffic management systems
Problems Solved
- Improving decision-making processes in autonomous vehicles - Enhancing safety on the road - Optimizing traffic flow and efficiency
Benefits
- Increased safety for passengers and pedestrians - Reduced accidents and collisions - Improved traffic flow and reduced congestion
Original Abstract Submitted
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.
