AUTONOMOUS VEHICLE SIMULATION SYSTEM FOR ANALYZING MOTION PLANNERS
An autonomous vehicle simulation system for analyzing motion planners is disclosed. A particular embodiment includes: receiving map data corresponding to a real world driving environment; obtaining perception data and configuration data including pre-defined parameters and executables defining a specific driving behavior for each of a plurality of simulated dynamic vehicles; generating simulated perception data for each of the plurality of simulated dynamic vehicles based on the map data, the perception data, and the configuration data; receiving vehicle control messages from an autonomous vehicle control system; and simulating the operation and behavior of a real world autonomous vehicle based on the vehicle control messages received from the autonomous vehicle control system.
1 . A vehicle simulation system, comprising:
a processor configured to:
obtain perception data that includes data related to a first vehicle detected by sensors located on a second vehicle;
generate, using the perception data, a simulated perception data comprising a simulated vehicle corresponding to the first vehicle;
generate, based on the perception data, a simulation of the simulated vehicle with a driving behavior;
generate a plurality of trajectories from a current position of the simulated vehicle to a target position of the simulated vehicle;
select, from the plurality of trajectories, a trajectory on which the simulated vehicle is to be transitioned from the current position to the target position; and
send the trajectory and the simulated perception data of the simulated vehicle to an autonomous vehicle system.
2 . The system of claim 1 , wherein the trajectory is selected from the plurality of trajectories based on a presence of obstacles.
3 . The system of claim 1 , wherein the processor is further configured to:
generate multiple acceleration profiles with which the simulated vehicle is transitioned from a current speed of the simulated vehicle to a target speed of the simulated vehicle; and
select, from the multiple acceleration profiles, an acceleration profile with which the simulated vehicle is transitioned from the current speed to the target speed.
4 . The system of claim 3 , wherein the trajectory is selected from the plurality of trajectories based on fuel-efficiency.
5 . The system of claim 1 ,
wherein the plurality of trajectories for the simulated vehicle are represented as waypoints, and
wherein each waypoint has a corresponding position, a corresponding speed, a corresponding acceleration, and a corresponding time.
6 . The system of claim 1 , wherein the processor is further configured to:
generate attributes for the simulated vehicle at specific points in time based on the perception data.
7 . The system of claim 6 , wherein the attributes include a position, a speed and a heading for the simulated vehicle at the specific points in time.
8 . The system of claim 1 , wherein the driving behavior of the simulated vehicle is aggressive corresponding to the simulated vehicle frequently changing lanes.
9 . The system of claim 1 , wherein the driving behavior of the simulated vehicle is conservative corresponding to the simulated vehicle maintaining a distance from neighboring vehicles.
10 . A method, comprising:
obtaining perception data that includes data related to a first vehicle detected by sensors located on a second vehicle;
generating, using the perception data, a simulated perception data comprising a simulated vehicle corresponding to the first vehicle;
generating, based on the perception data, a simulation of the simulated vehicle with a driving behavior;
generating a plurality of trajectories from a current position of the simulated vehicle to a target position of the simulated vehicle;
selecting, from the plurality of trajectories, a trajectory on which the simulated vehicle is to be transitioned from the current position to the target position; and
sending the trajectory and the simulated perception data of the simulated vehicle to an autonomous vehicle system.
11 . The method of claim 10 , wherein the trajectory is selected from the plurality of trajectories based on a presence of obstacles.
12 . The method of claim 10 , further comprising:
generating multiple acceleration profiles with which the simulated vehicle is transitioned from a current speed of the simulated vehicle to a target speed of the simulated vehicle; and
selecting, from the multiple acceleration profiles, an acceleration profile with which the simulated vehicle is transitioned from the current speed to the target speed.
13 . The method of claim 12 , wherein the trajectory is selected from the plurality of trajectories based on fuel-efficiency.
14 . The method of claim 10 ,
wherein the plurality of trajectories for the simulated vehicle are represented as waypoints, and
wherein each waypoint has a corresponding position, a corresponding speed, a corresponding acceleration, and a corresponding time.
15 . The method of claim 10 , further comprising:
generating attributes for the simulated vehicle at specific points in time based on the perception data.
16 . The method of claim 15 , wherein the attributes include a position, a speed and a heading for the simulated vehicle at the specific points in time.
17 . The method of claim 10 , wherein the driving behavior of the simulated vehicle is aggressive corresponding to the simulated vehicle frequently changing lanes.
18 . A non-transitory computer readable program storage medium having code stored thereon, the code, when executed by one or more processors, causing an apparatus to implement a method, comprising:
obtaining perception data that includes data related to a first vehicle detected by sensors located on a second vehicle;
generating, using the perception data, a simulated perception data comprising a simulated vehicle corresponding to the first vehicle;
generating, based on the perception data, a simulation of the simulated vehicle with a driving behavior;
generating a plurality of trajectories from a current position of the simulated vehicle to a target position of the simulated vehicle;
selecting, from the plurality of trajectories, a trajectory on which the simulated vehicle is to be transitioned from the current position to the target position; and
sending the trajectory and the simulated perception data of the simulated vehicle to an autonomous vehicle system.
19 . The non-transitory computer readable program storage medium of claim 18 , wherein the trajectory is selected from the plurality of trajectories based on a presence of obstacles.
20 . The non-transitory computer readable program storage medium of claim 18 , wherein the method further comprises:
generating multiple acceleration profiles with which the simulated vehicle is transitioned from a current speed of the simulated vehicle to a target speed of the simulated vehicle; and
selecting, from the multiple acceleration profiles, an acceleration profile with which the simulated vehicle is transitioned from the current speed to the target speed.