Autonomous driving apparatus and method
Disclosed are an autonomous driving apparatus and method for an ego vehicle that autonomously travels. The autonomous driving apparatus includes a first sensor to detect a nearby vehicle nearby an ego vehicle, a memory to store map information, and a processor including a driving trajectory generator to generate a first driving trajectory of the ego vehicle and a second driving trajectory of the nearby vehicle based on the map information stored in the memory and a control processor configured to control autonomous driving of the ego vehicle based on the first and second driving trajectories generated by the driving trajectory generator.
1. An autonomous driving apparatus for an ego vehicle that autonomously travels, the autonomous driving apparatus comprising:
a first sensor to detect a vehicle nearby the ego vehicle;
a memory to store map information; and
a processor comprising a driving trajectory generator to generate a first driving trajectory of the ego vehicle and a second driving trajectory of the nearby vehicle based on the map information stored in the memory, a trajectory learner to correct the first driving trajectory of the ego vehicle generated by the driving trajectory generator, and a control processor to control autonomous driving of the ego vehicle based on the first and second driving trajectories generated by the driving trajectory generator,
wherein the driving trajectory generator is configured to:
generate an actual driving trajectory of the nearby vehicle by making cross reference to a location of the nearby vehicle detected by the first sensor and a given location in the map information stored in the memory, generate an expected driving trajectory of the nearby vehicle as a center line of a lane incorporated into the map information,
generate an actual driving trajectory of the ego vehicle by making cross reference to a location of the ego vehicle and a given location in the map information stored in the memory, and
generate an expected driving trajectory of the ego vehicle as a center line of a lane incorporated into the map information,
wherein the trajectory learner is configured to correct the actual driving trajectory of the ego vehicle by applying trajectory a lateral shift value to the actual driving trajectory of the ego vehicle, when a trajectory error between the actual driving trajectory and the expected driving trajectory of the nearby vehicle is equal to or greater than a preset threshold,
wherein the control processor is configured to:
determine whether a function of the driving trajectory generator is abnormal,
request a target nearby vehicle around the ego vehicle to transmit new map information if it is determined that the function of the driving trajectory generator is abnormal,
verify reliability of the new map information received from the target nearby vehicle,
control the autonomous driving of the ego vehicle based on the new map information and results of detection of the nearby vehicle by the first sensor if the reliability of the new map information has been verified, and
turn off an autonomous driving mode of the ego vehicle and output an alarm to notify a driver of the autonomous driving mode switching to a manual driving mode if the reliability of the new map information has not been verified,
wherein the control processor is configured to determine that the function of the driving trajectory generator is abnormal when a data value of the first driving trajectory or the second driving trajectory generated by the driving trajectory generator is out of a preset reliability range,
wherein the control processor is configured to verify the reliability of the new map information based on a location of a reference object present in the new map information received from the target nearby vehicle,
wherein the control processor is configured to determine that the reliability of the new map information has been verified, when a difference between a first location value of the reference object present in the new map information received from the target nearby vehicle and a second location value of the reference object obtained as a result of detection of the reference object by a second sensor mounted on the target nearby vehicle is equal to or less than a preset reference value,
wherein the control processor is configured to:
generate, without the driving trajectory generator, the first driving trajectory of the ego vehicle and the second driving trajectory of the nearby vehicle by fusing the new map information and the results of the detection of the nearby object by the first sensor if the reliability of the new map information has been verified, and
control the autonomous driving of the ego vehicle based on the generated first and second driving trajectories,
wherein the nearby vehicle comprises at least two surrounding vehicles.
2. An autonomous driving method for an ego vehicle comprising the steps of:
controlling autonomous driving of the ego vehicle based on a first driving trajectory of the ego vehicle and a second driving trajectory of a nearby vehicle based on map information stored in a memory, wherein the first and second driving trajectories are generated by a driving trajectory generator;
determining whether a function of the driving trajectory generator is abnormal;
requesting a target nearby vehicle around the ego vehicle to transmit new map information if it is determined that the function of the driving trajectory generator is abnormal;
verifying reliability of the new map information received from the target nearby vehicle;
controlling the autonomous driving of the ego vehicle based on the new map information and results of detection of the nearby object by a first sensor mounted on the ego vehicle if the reliability of the new map information has been verified, and
turning off an autonomous driving mode of the ego vehicle and outputting an alarm to notify a driver of the autonomous driving mode switching to a manual driving mode if the reliability of the new map information has not been verified,
wherein the method further comprises the steps of:
generating an actual driving trajectory of the nearby vehicle by making cross reference to a location of the nearby vehicle detected by the first sensor and a given location in the map information stored in the memory, generating an expected driving trajectory of the nearby vehicle as a center line of a lane incorporated into the map information,
generating an actual driving trajectory of the ego vehicle by making cross reference to a location of the ego vehicle and a given location in the map information stored in the memory,
generating an expected driving trajectory of the ego vehicle as a center line of a lane incorporated into the map information, and
correcting the actual driving trajectory of the ego vehicle by applying a trajectory lateral shift value to the actual driving trajectory of the ego vehicle, when a trajectory error between the actual driving trajectory and the expected driving trajectory of the nearby vehicle is equal to or greater than a preset threshold,
wherein the step of determining whether the driving trajectory generator is abnormal comprises the step of determining that the function of the driving trajectory generator is abnormal when a data value of the first driving trajectory or the second driving trajectory is out of a preset reliability range,
wherein the step of verifying the reliability comprises the step of verifying the reliability of the new map information based on a location of a reference object present in the new map information received from the target nearby vehicle,
wherein the step of verifying the reliability comprises the step of determining that the reliability of the new map information has been verified, when a difference between a first location value of the reference object present in the new map information received from the target nearby vehicle and a second location value of the reference object obtained as a result of detection of the reference object by a second sensor mounted on the target nearby vehicle is equal to or less than a preset reference value,
wherein the step of controlling the autonomous driving of the ego vehicle comprises the steps of:
generating the first driving trajectory of the ego vehicle and the second driving trajectory of the nearby vehicle by fusing the new map information and the results of the detection of the nearby object by the first sensor if the reliability of the new map information has been verified, and
controlling the autonomous driving of the ego vehicle based on the generated first and second driving trajectories,
wherein the nearby vehicle comprises at least two surrounding vehicles.