Systems and methods for interaction-based trajectory prediction

A computing system for an autonomous vehicle, the computing system comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable medium storing instructions for execution by the one or more processors to cause the computing system to perform operations, the operations comprising:
• obtaining graph data associated with a first node indicative of a first object in an environment of the autonomous vehicle and a second node indicative of a traffic element in the environment of the autonomous vehicle, the graph data further comprising an edge between the first node and the second node indicative of a relationship between the first object and the traffic element;
• determining a distance between the first object and the traffic element;
• in response to determining the distance between the first object and the traffic element to be less than a predefined distance, processing the graph data to predict an interaction type for the edge between the first node and the second node, wherein the interaction type is predicted from a predetermined set of discrete interaction types;
• processing the interaction type between the first node and the second node to predict a trajectory of the first object;
• and
• controlling motion of the autonomous vehicle based on a motion plan determined based on the trajectory of the first object.

An autonomous vehicle comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable medium storing instructions for execution by the one or more processors to cause the one or more processors to perform operations, the operations comprising:
• obtaining graph data associated with a first node indicative of a first object in an environment of the autonomous vehicle and a second node indicative of a traffic element in the environment of the autonomous vehicle, the graph data further comprising an edge between the first node and the second node indicative of a relationship between the first object and the traffic element;
• determining a distance between the first object and the traffic element;
• in response to determining the distance between the first object and the traffic element to be less than a predefined distance, processing the graph data to predict an interaction type for the edge between the first node and the second node, wherein the interaction type is predicted from a predetermined set of discrete interaction types;
• processing the interaction type between the first node and the second node to predict a trajectory of the first object;
• and
• controlling motion of the autonomous vehicle based on a motion plan determined based on the trajectory of the first object.