Systems and Methods for Simulating Dynamic Objects Based on Real World Data
Systems and methods for generating simulation data based on real-world dynamic objects are provided. A method includes obtaining two- and three-dimensional data descriptive of a dynamic object in the real world. The two- and three-dimensional information can be provided as an input to a machine-learned model to receive object model parameters descriptive of a pose and shape modification with respect to a three-dimensional template object model. The parameters can represent a three-dimensional dynamic object model indicative of an object pose and an object shape for the dynamic object. The method can be repeated on sequential two- and three-dimensional information to generate a sequence of object model parameters over time. Portions of a sequence of parameters can be stored as simulation data descriptive of a simulated trajectory of a unique dynamic object. The parameters can be evaluated by an objective function to refine the parameters and train the machine-learned model.
1 . A computing system comprising:
one or more processors; and
one or more non-transitory computer-readable medium storing instructions that are executable by the one or more processors to perform operations, the operations comprising:
providing input data descriptive of a dynamic object as an input to a machine-learned object parameter estimation model;
receiving as an output of the machine-learned object parameter estimation model, a plurality of object model parameters;
determining a sequence of object model parameters descriptive of a respective object pose for the dynamic object, wherein the sequence of object model parameters is indicative of a trajectory of the dynamic object; and
generating at least a portion of simulation data based on the sequence of object model parameters, wherein generating at least the portion of the simulation data comprises generating one or more single action sequences from the sequence of object model parameters based on the sequence of object model parameters.
2 . The computing system of claim 1 , wherein the input data comprises sequential data, the sequential data indicative of the dynamic object at a plurality of time steps.
3 . The computing system of claim 2 , wherein the operations further comprise:
determining the plurality of object model parameters corresponds to at least a first step of the plurality of time steps.
4 . The computing system of claim 1 , wherein the one or more single action sequences comprise a portion of the sequence of object model parameters corresponding to an action of the dynamic object.
5 . The computing system of claim 1 , wherein the input data comprises at least one of two dimensional data or three dimensional data.
6 . The computing system of claim 1 , wherein the dynamic object comprises a pedestrian.
7 . The computing system of claim 1 , wherein the operations further comprise:
determining a prior consistency measure for the plurality of object model parameters; and
modifying the plurality of object model parameters based on the prior consistency measure.
8 . A computer-implemented method comprising:
providing input data descriptive of a dynamic object as an input to a machine-learned object parameter estimation model;
receiving as an output of the machine-learned object parameter estimation model, a plurality of object model parameters;
determining a sequence of object model parameters descriptive of a respective object pose for the dynamic object, wherein the sequence of object model parameters is indicative of a trajectory of the dynamic object; and
generating at least a portion of simulation data based on the sequence of object model parameters, wherein generating at least the portion of the simulation data comprises generating one or more single action sequences from the sequence of object model parameters based on the sequence of object model parameters.
9 . The computer-implemented method of claim 8 , wherein the input data comprises sequential data, the sequential data indicative of the dynamic object at a plurality of time steps.
10 . The computer-implemented method of claim 9 , further comprising:
determining the plurality of object model parameters corresponds to at least a first step of the plurality of time steps.
11 . The computer-implemented method of claim 8 , wherein the one or more single action sequences comprise a portion of the sequence of object model parameters corresponding to an action of the dynamic object.
12 . The computer-implemented method of claim 8 , wherein the input data comprises at least one of two dimensional data or three dimensional data.
13 . The computer-implemented method of claim 8 , wherein the dynamic object comprises a pedestrian.
14 . The computer-implemented method of claim 8 , further comprising:
determining a prior consistency measure for the plurality of object model parameters; and
modifying the plurality of object model parameters based on the prior consistency measure.
15 . One or more non-transitory computer-readable media storing instructions that are executable by one or more processors cause one or more processors to perform operations comprising:
providing input data descriptive of a dynamic object as an input to a machine-learned object parameter estimation model;
receiving as an output of the machine-learned object parameter estimation model, a plurality of object model parameters;
determining a sequence of object model parameters descriptive of a respective object pose for the dynamic object, wherein the sequence of object model parameters is indicative of a trajectory of the dynamic object; and
generating at least a portion of simulation data based on the sequence of object model parameters, wherein generating at least the portion of the simulation data comprises generating one or more single action sequences from the sequence of object model parameters based on the sequence of object model parameters.
16 . The one or more non-transitory computer-readable media of claim 15 , wherein the input data comprises sequential data, the sequential data indicative of the dynamic object at a plurality of time steps.
17 . The one or more non-transitory computer-readable media of claim 16 , wherein the operations further comprise:
determining the plurality of object model parameters corresponds to at least a first step of the plurality of time steps.
18 . The one or more non-transitory computer-readable media of claim 15 , wherein the one or more single action sequences comprise a portion of the sequence of object model parameters corresponding to an action of the dynamic object.
19 . The one or more non-transitory computer-readable media of claim 15 , wherein the input data comprises at least one of two dimensional data or three dimensional data.
20 . The one or more non-transitory computer-readable media of claim 15 , wherein the dynamic object comprises a pedestrian.