US 12,051,249 B2 · Behavior prediction of surrounding agents

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting occupancies of agents. One of the methods includes obtaining scene data characterizing a current scene in an environment; and processing a neural network input comprising the scene data using a neural network to generate a neural network output, wherein: the neural network output comprises respective occupancy outputs corresponding to a plurality of agent types at one or more future time points; the occupancy output for each agent type at a first future time point comprises respective occupancy probabilities for a plurality of locations in the environment; and in the occupancy output for each agent type at the first future time point, the respective occupancy probability for each location characterizes a likelihood that an agent of the agent type will occupy the location at the first future time point.

Claims20

Dependent claims

A method comprising:

obtaining scene data characterizing a current scene in an environment being navigated through by a vehicle;
processing a neural network input comprising the scene data using a neural network to generate a neural network output, wherein:
the neural network output comprises one or more occupancy outputs corresponding to each of a plurality of future time points;
each occupancy output corresponding to each of the plurality of future time points comprises respective occupancy scores for a plurality of cells, each cell corresponding to a respective one of a plurality of locations in the environment;
and
in each occupancy output corresponding to each future time point, the respective occupancy scores for the cells represent predicted occupancies of one or more agents at the future time point;
and
providing the neural network output as input to one or more systems located on-board the vehicle for use in controlling navigation of the vehicle.

5 more elements

One or more non-transitory storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

obtaining scene data characterizing a current scene in an environment being navigated through by a vehicle;
processing a neural network input comprising the scene data using a neural network to generate a neural network output, wherein:
the neural network output comprises one or more occupancy outputs corresponding to each of a plurality of future time points;
each occupancy output corresponding to each of the plurality of future time points comprises respective occupancy scores for a plurality of cells, each cell corresponding to a respective one of a plurality of locations in the environment;
and
in each occupancy output corresponding to each future time point, the respective occupancy scores for the cells represent predicted occupancies of one or more agents at the future time point;
and
providing the neural network output as input to one or more systems located on-board the vehicle for use in controlling navigation of the vehicle.

5 more elements

Dependencies are inferred from the claim text.

Behavior prediction of surrounding agents

Life of this patent

Behavior prediction of surrounding agents

Life of this patent

Abstract

Claims20