Trajectory prediction method and device

A trajectory prediction method, comprising:

• acquiring current trajectory data and current map data, wherein the current trajectory data comprises a plurality of trajectory points of a moving subject and one or more other moving objects in current environment in a past predetermined time period, each of the plurality of trajectory points comprises a spatial position at a corresponding time point, and the current map data comprises spatial positions of a plurality of map points of a road element in the current environment in the predetermined time period;
• expressing the current trajectory data and the current map data as a current trajectory point set and a current map point set in a high-dimensional space;
• extracting a global scene feature according to the current trajectory point set and the current map point set;
• and
• predicting and outputting a plurality of prediction trajectory point sets of the moving subject and a probability corresponding to each of the plurality of prediction trajectory point sets according to the global scene feature.

A trajectory prediction device, comprising at least one processor and at least one memory, wherein at least one machine-executable instruction is stored in the at least one memory, and the processor executes the at least one machine-executable instruction to implement operations comprising:

• acquiring current trajectory data and current map data, wherein the current trajectory data comprises a plurality of trajectory points of a moving subject and one or more other moving objects in current environment in a past predetermined time period, each of the plurality of trajectory points comprises a spatial position at a corresponding time point, and the current map data comprises spatial positions of a plurality of map points of a road element in the current environment in the predetermined time period;
• expressing the current trajectory data and the current map data as a current trajectory point set and a current map point set in a high-dimensional space;
• extracting a global scene feature according to the current trajectory point set and the current map point set;
• and
• predicting and outputting a plurality of prediction trajectory point sets of the moving subject and a probability corresponding to each of the plurality of prediction trajectory point sets according to the global scene feature.

A non-transitory storage medium, configured to store at least one machine-executable instruction, wherein a processor executes the at least one machine-executable instruction to implement operations comprising:

• acquiring current trajectory data and current map data, wherein the current trajectory data comprises a plurality of trajectory points of a moving subject and one or more other moving objects in current environment in a past predetermined time period, each of the plurality of trajectory points comprises a spatial position at a corresponding time point, and the current map data comprises spatial positions of a plurality of map points of a road element in the current environment in the predetermined time period;
• expressing the current trajectory data and the current map data as a current trajectory point set and a current map point set in a high-dimensional space;
• extracting a global scene feature according to the current trajectory point set and the current map point set;
• and
• predicting and outputting a plurality of prediction trajectory point sets of the moving subject and a probability corresponding to each of the plurality of prediction trajectory point sets according to the global scene feature.