Centralized prediction and planning for improving lane platooning and intersection vehicle behavior
This application is directed to a centralized system for predicting vehicle trajectory. A computer system associated with a fixed installation having one or more first sensors obtains, from the first sensors, information of a plurality of vehicles that are traveling within a zone of interest of a road. The computer system generates a first travel trajectory for a first vehicle of the plurality of vehicles based on the information obtained from the one or more first sensors. The computer system sends, to the first vehicle, the first travel trajectory such that the first vehicle is configured to at least partially autonomously drive the first vehicle based on the first travel trajectory of the first vehicle.
1 . A method for predicting vehicle trajectory, comprising:
at a computer system associated with a fixed installation situated at a stationary position along a road and having one or more first sensors, the computer system including one or more processors and memory:
obtaining, from the one or more first sensors, information of a plurality of vehicles that are traveling within a zone of interest of the road;
determining, for a respective vehicle of the plurality of vehicles, a probability of the respective vehicle changing lanes within a predefined time period;
generating a first travel trajectory for a first vehicle of the plurality of vehicles based on the information obtained from the one or more first sensors and the determined probability for the respective vehicle; and
sending, to the first vehicle, the first travel trajectory such that the first vehicle is configured to at least partially autonomously drive the first vehicle based on the first travel trajectory of the first vehicle.
2 . The method of claim 1 , wherein the information of the plurality of vehicles includes one of more of:
location information of a respective vehicle of the plurality of vehicles;
a speed of the respective vehicle; and
an acceleration of the respective vehicle.
3 . The method of claim 1 , further comprising:
predicting a vehicle action of a respective vehicle of the plurality of vehicles according to the obtained information,
wherein generating the first travel trajectory for the first vehicle is further based on the predicted vehicle action.
4 . The method of claim 1 , further comprising:
receiving vehicle status information from at least a subset of the plurality of vehicles that are traveling within the zone of interest,
wherein generating the first travel trajectory for the first vehicle is further based on the received vehicle status information.
5 . The method of claim 1 , wherein:
the first vehicle includes one or more second sensors for acquiring data in a vicinity of the first vehicle; and
the first vehicle is configured to apply the first travel trajectory in combination with the data acquired by the one or more second sensors.
6 . The method of claim 1 , further comprising:
controlling the first vehicle to at least partially autonomously drive the first vehicle to track the first travel trajectory.
7 . The method of claim 1 , wherein the first vehicle is configured to abort executing the first travel trajectory in accordance with a determination that the first vehicle cannot execute the first travel trajectory.
8 . A computer system associated with a fixed installation situated at a stationary position along a road and having one or first more sensors, the computer system comprising:
one or more processors; and
memory coupled to the one or more processors, the memory storing one or more programs configured for execution by the one or more processors, the one or more programs including instructions for:
obtaining, from the one or more first sensors, information of a plurality of vehicles that are traveling within a zone of interest of the road;
determining, for a respective vehicle of the plurality of vehicles, a probability of the respective vehicle changing lanes within a predefined time period;
generating a first travel trajectory for a first vehicle of the plurality of vehicles based on the information obtained from the one or more first sensors and the determined probability for the respective vehicle; and
sending, to the first vehicle, the first travel trajectory such that the first vehicle is configured to at least partially autonomously drive the first vehicle based on the first travel trajectory of the first vehicle.
9 . The computer system of claim 8 , wherein the one or more first sensors include: one or more light detection and ranging (LiDAR) scanners, one or more cameras, or a radio detection and ranging (RADAR) sensor.
10 . The computer system of claim 8 , the one or more programs further including instructions for:
generating an aerial view of the zone of interest.
11 . The computer system of claim 10 , wherein the instructions for generating the first travel trajectory for the first vehicle include instructions for generating the first travel trajectory further based on the aerial view of the zone of interest.
12 . The computer system of claim 10 , the one or more programs further including instructions for:
sending, to the first vehicle, the aerial view of the zone of interest,
wherein the first vehicle is configured to apply the first travel trajectory in combination with the aerial view of the zone of interest.
13 . The computer system of claim 10 , wherein the perception model executes locally at the fixed installation.
14 . The computer system of claim 10 , wherein the instructions for generating the aerial view of the zone of interest include instructions for applying a perception model to generate the aerial view of the zone of interest.
15 . The computer system of claim 8 , the one or more programs further including instructions for:
receiving vehicle status information from at least a subset of the plurality of vehicles that are traveling within the zone of interest,
wherein generating the first travel trajectory for the first vehicle is further based on the received vehicle status information.
16 . A non-transitory computer-readable storage medium storing one or more programs configured for execution by one or more processors of a computer system that is associated with a fixed installation situated at a stationary position along a road and having one or first more sensors, the one or more programs comprising instructions for:
obtaining, from the one or more first sensors, information of a plurality of vehicles that are traveling within a zone of interest of the road;
determining, for a respective vehicle of the plurality of vehicles, a probability of the respective vehicle changing lanes within a predefined time period;
generating a first travel trajectory for a first vehicle of the plurality of vehicles based on the information obtained from the one or more first sensors and the determined probability for the respective vehicle; and
sending, to the first vehicle, the first travel trajectory such that the first vehicle is configured to at least partially autonomously drive the first vehicle based on the first travel trajectory of the first vehicle.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein:
the zone of interest of the road comprises an intersection of the road; and
the one or more programs further include instructions for:
sending, to the first vehicle, perception information of the intersection of the road generated by the computer system, wherein the first vehicle is configured to apply the first travel trajectory in combination with the perception information.
18 . The non-transitory computer-readable storage medium of claim 17 , the one or more programs further comprising instructions for:
generating the perception information by applying a perception model, the perception information including one or more of:
a type corresponding to the intersection;
location information of the intersection;
a respective mode of at least a subset of the plurality of vehicles at the intersection; and
a priority level of the at least the subset of the plurality of vehicles arriving at the intersection, including the first vehicle.
19 . The non-transitory computer-readable storage medium of claim 16 , wherein:
the zone of interest comprises a merging zone on the road;
the one or more programs include instructions for sending, to the first vehicle, perception information of the merging zone generated by the computer system; and
the first vehicle is configured to apply the first travel trajectory in combination with the perception information.
20 . The non-transitory computer-readable storage medium of claim 19 , the one or more programs further comprising instructions for:
generating the perception information by applying a perception model, the perception information including one or more of:
a speed of a respective vehicle of the plurality of vehicles at the merging zone;
a probability of the respective vehicle cutting into a lane in the merging zone; and
a probability of the respective vehicle merging into the lane in the merging zone.