Electronic device and lane determination method

Abstract

An electronic device and a lane determination method are disclosed. The method for determining a lane, according to one embodiment, may comprise the operations of: measuring similarity between a future driving trajectory of a first vehicle and a future driving trajectory of a second vehicle that is traveling, behind the first vehicle, in a lane different from that of the first vehicle; acquiring a risk of collision associated with the first vehicle moving to the lane in which the second vehicle is traveling, on the basis of the similarity, the distance between the first vehicle and the second vehicle, and the relative speed between the first vehicle and the second vehicle; and determining, on the basis of the risk, whether the first vehicle should move to the lane in which the second vehicle is traveling. The future driving trajectory can be a driving trajectory from the current position of the vehicle to a future point in time.

Description

Electronic devices and lane determination methods

[0001] The following disclosure relates to an electronic device and a method for determining a lane.

[0002] Autonomous vehicles may need to perceive their surroundings, plan routes based on those conditions, and drive safely and efficiently. In particular, in complex driving situations such as lane changes, it may be important to assess the risks associated with lane changes so that the autonomous vehicle can change lanes safely without colliding with surrounding vehicles.

[0003] The background technology described above is possessed or acquired by the inventor in the process of deriving the content of the disclosure of the present application, and cannot necessarily be considered as prior art disclosed to the general public prior to the filing of this application.

[0004] A method for determining a lane according to one embodiment may include an operation of measuring similarity between the future driving trajectory of a first vehicle and the future driving trajectory of a second vehicle traveling in a different lane from the first vehicle behind the first vehicle. The method may include an operation of obtaining a risk of collision when the first vehicle moves into the lane in which the second vehicle is traveling, based on the similarity, the distance between the first vehicle and the second vehicle, and the relative speed between the first vehicle and the second vehicle. The method may include an operation of determining whether the first vehicle will move into the lane in which the second vehicle is traveling, based on the risk. The future driving trajectory may be a driving trajectory from the vehicle's current position to a future point in time.

[0005] The operation of measuring the similarity may include an operation of predicting the future driving trajectory of the first vehicle based on the current position of the first vehicle. The operation of measuring the similarity may include an operation of predicting the future driving trajectory of the second vehicle based on the current position of the second vehicle. The operation of measuring the similarity may include an operation of calculating the Bhattacharyya similarity between the future driving trajectory of the first vehicle and the future driving trajectory of the second vehicle.

[0006] The operation of predicting the future driving trajectory of the first vehicle may include the operation of predicting the future driving trajectory of the first vehicle through a Gaussian distribution from the current position of the first vehicle.

[0007] The operation of predicting the future driving trajectory of the second vehicle may include the operation of predicting the future driving trajectory of the second vehicle through a Gaussian distribution from the current position of the second vehicle.

[0008] The operation of obtaining the above risk level may include an operation of calculating the inverse time to collision (ITTC) between the first vehicle and the second vehicle based on the distance between the first vehicle and the second vehicle and the relative speed between the first vehicle and the second vehicle. The operation of obtaining the above risk level may include an operation of calculating the above risk level based on the similarity and the ITTC.

[0009] The operation of calculating the above risk level may include an operation of calculating a first risk level corresponding to the above similarity. The operation of calculating the above risk level may include an operation of calculating a second risk level corresponding to the above ITTC. The operation of calculating the above risk level may include an operation of calculating a total risk level by combining the first risk level and the second risk level.

[0010] The operation of determining whether the first vehicle moves into the lane in which the second vehicle is driving may include the operation of setting a threshold value of the risk level. The operation of determining whether the first vehicle moves into the lane in which the second vehicle is driving may include the operation of comparing the risk level and the threshold value to determine whether the first vehicle moves into the lane in which the second vehicle is driving.

[0011] The operation of setting the threshold of the above risk level may include the operation of setting the threshold level by modeling the risk level with respect to the speed of the first vehicle based on the ground truth of the driving data that successfully changed lanes.

[0012] The operation of determining whether the first vehicle moves into the lane where the second vehicle is driving by comparing the risk level and the threshold value may include the operation of determining that the first vehicle does not move into the lane where the second vehicle is driving if the risk level is greater than the threshold value. The operation of determining whether the first vehicle moves into the lane where the second vehicle is driving by comparing the risk level and the threshold value may include the operation of determining that the first vehicle moves into the lane where the second vehicle is driving if the risk level is less than the threshold value.

[0013] An electronic device for determining a lane according to one embodiment may include a processor. The electronic device may include a memory for storing instructions. The instructions may be executed individually or collectively by the processor to enable the electronic device to measure the similarity between the future driving trajectory of a first vehicle and the future driving trajectory of a second vehicle traveling in a different lane from the first vehicle behind the first vehicle. The instructions may be executed individually or collectively by the processor to enable the electronic device to obtain a risk of collision when the first vehicle moves into the lane in which the second vehicle is traveling, based on the similarity, the distance between the first vehicle and the second vehicle, and the relative speed between the first vehicle and the second vehicle. The instructions may be executed individually or collectively by the processor to enable the electronic device to determine whether the first vehicle will move into the lane in which the second vehicle is traveling, based on the risk. The above future driving trajectory may be a driving trajectory from the vehicle's current location to a future point in time.

[0014] The above instructions may be executed individually or collectively by the processor to enable the electronic device to predict the future driving trajectory of the first vehicle based on the current location of the first vehicle. The above instructions may be executed individually or collectively by the processor to enable the electronic device to predict the future driving trajectory of the second vehicle based on the current location of the second vehicle. The above instructions may be executed individually or collectively by the processor to enable the electronic device to calculate the Bhattacharyya similarity between the future driving trajectory of the first vehicle and the future driving trajectory of the second vehicle.

[0015] The above instructions may be executed individually or collectively by the processor to enable the electronic device to predict the future driving trajectory of the first vehicle through a Gaussian distribution from the current position of the first vehicle.

[0016] The above instructions may be executed individually or collectively by the processor to enable the electronic device to predict the future driving trajectory of the second vehicle through a Gaussian distribution from the current location of the second vehicle.

[0017] The above instructions may be executed individually or collectively by the processor to enable the electronic device to calculate the inverse time to collision (ITTC) between the first vehicle and the second vehicle based on the distance between the first vehicle and the second vehicle and the relative speed between the first vehicle and the second vehicle. The above instructions may be executed individually or collectively by the processor to enable the electronic device to calculate the risk based on the similarity and the ITTC.

[0018] The above instructions may be executed individually or collectively by the processor to cause the electronic device to calculate a first risk level corresponding to the similarity. The above instructions may be executed individually or collectively by the processor to cause the electronic device to calculate a second risk level corresponding to the ITTC. The above instructions may be executed individually or collectively by the processor to cause the electronic device to calculate a total risk level by combining the first risk level and the second risk level.

[0019] The above instructions may be executed individually or collectively by the processor to enable the electronic device to set a threshold of the risk level. The above instructions may be executed individually or collectively by the processor to enable the electronic device to compare the risk level with the threshold value and determine whether the first vehicle moves into the lane in which the second vehicle is traveling.

[0020] The above instructions may be executed individually or collectively by the processor to enable the electronic device to set the threshold value by modeling the risk level with respect to the speed of the first vehicle based on the ground truth of the driving data of a successful lane change.

[0021] The above instructions may be executed individually or collectively by the processor to cause the electronic device to determine that the first vehicle does not move into the lane in which the second vehicle is traveling when the risk level is greater than the threshold value. The above instructions may be executed individually or collectively by the processor to cause the electronic device to determine that the first vehicle moves into the lane in which the second vehicle is traveling when the risk level is less than the threshold value.

[0022] FIG. 1 is a drawing for explaining an autonomous driving method according to one embodiment.

[0023] FIG. 2 is a block diagram illustrating hardware included in an autonomous driving device according to one embodiment.

[0024] FIG. 3 is an example of a lane determination system according to one embodiment.

[0025] FIG. 4 is a diagram illustrating a method for determining whether to change lanes based on the distance and relative speed to surrounding vehicles according to one embodiment.

[0026] FIG. 5 is a diagram illustrating the operation of setting a threshold value of risk according to one embodiment.

[0027] Figure 6 is a diagram illustrating a method for calculating the risk of collision with a rear vehicle when changing lanes in various scenarios.

[0028] FIG. 7 is an example of a flowchart of a method for determining a lane according to one embodiment.

[0029] FIG. 8 is an example of an electronic device according to one embodiment.

[0030] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.

[0031] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0032] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between.

[0033] The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0034] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0035] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.

[0036]

[0037] FIG. 1 is a drawing for explaining an autonomous driving method according to one embodiment.

[0038] Referring to FIG. 1, an autonomous driving device (e.g., the autonomous driving device (40) of FIG. 2) can be mounted on a vehicle to implement an autonomous driving vehicle (10). The autonomous driving vehicle (10) may be a vehicle capable of driving on its own without driver operation.

[0039] The autonomous driving device (40) mounted on the autonomous driving vehicle (10) may include various sensors for collecting surrounding situation information (e.g., sensor unit (41) of FIG. 2).

[0040] The autonomous driving device (40) can detect the movement of a preceding vehicle (20) operating in front through an image sensor and / or event sensor mounted on the front of the autonomous driving vehicle (10). The autonomous driving device (40) may further include sensors to detect other vehicles (30) operating in the adjacent lane as well as pedestrians around the autonomous driving vehicle (10), in addition to the front of the autonomous driving vehicle (10).

[0041] At least one of the sensors for collecting situational information around the autonomous vehicle (10) may have a predetermined field of view (FoV) as shown in FIG. 1. When a sensor mounted on the front of the autonomous vehicle (10) has a field of view (FoV) as shown in FIG. 1, information detected at the center of the sensor may have relatively high importance. This may be because the information detected at the center of the sensor contains most of the information corresponding to the movement of the preceding vehicle (20).

[0042] The autonomous driving device (40) processes information collected by the sensors of the autonomous driving vehicle (10) in real time to control the movement of the autonomous driving vehicle (10), while at least some of the information collected by the sensors can be stored in a memory device (e.g., memory system (47) of FIG. 2).

[0043]

[0044] FIG. 2 is a block diagram illustrating hardware included in an autonomous driving device according to one embodiment.

[0045] Referring to FIG. 2, the autonomous driving device (40) may include a sensor unit (41), a processor (46), a memory system (47), and a vehicle body control module (48), etc.

[0046] The sensor unit (41) may include a plurality of sensors (42-45). The plurality of sensors (42-45) may include an image sensor, an event sensor, an illuminance sensor, a GPS device, an accelerometer, etc. Data collected by the sensors (42-45) may be transmitted to a processor (46).

[0047] The processor (46) can store data collected by the sensors (42-45) in the memory system (47). The processor (46) can determine the movement of the vehicle by controlling the vehicle body control module (48) based on the data collected by the sensors (42-45).

[0048] The memory system (47) may include two or more memory devices and a system controller for controlling the memory devices. Each of the memory devices may be provided as a single semiconductor chip. In addition to the system controller of the memory system (47), each of the memory devices included in the memory system (47) may include a memory controller. The memory controller may include an artificial intelligence (AI) computation circuit, such as a neural network. The memory controller may generate computation data by assigning a predetermined weight to data received from the sensors (42-45) or the processor (46), and may store the computation data in the memory chip.

[0049] The vehicle body control module (48) can control the movement of the vehicle by receiving commands from the processor (46).

[0050]

[0051] FIG. 3 is an example of a lane determination system according to one embodiment.

[0052] Referring to FIG. 3, a lane decision system (300) may include a vehicle (310), a lane decision device (330), and a control server (350). However, FIG. 3 is merely an example for explaining the present invention and should not be interpreted as limiting the scope of the present invention. For example, the lane decision device (330) may perform a lane decision method independently without a control server (350).

[0053] A vehicle (310) may mean a person and / or a means of transport for transporting a person. The vehicle (310) may be an autonomous vehicle (10) shown in FIG. 1 or may include an autonomous driving device (40) shown in FIG. 2. The vehicle (310) may include, for example, a means of transport such as an automobile, a train, a ship, a boat, an aircraft, a kickboard and / or a bicycle.

[0054] The lane determination device (330) may be mounted inside the vehicle (310) or implemented outside the vehicle (310) (e.g., on a server (350)).

[0055] The lane determination device (330) can determine the lane in which the vehicle (310) will drive. In particular, the lane determination device (330) can determine whether the vehicle (310) will change lanes. In determining whether to change lanes, it may be important to determine the risk of collision with surrounding vehicles so that the vehicle (310) can change lanes without colliding with surrounding vehicles. If the interaction between the vehicle (310) and surrounding vehicles is not properly reflected in determining whether to collide, the risk of collision may be underestimated or overestimated.

[0056] The lane determination device (330) can predict the future trajectory of the vehicle (310) and surrounding vehicles, as well as determine the risk of collision using the relative speed and / or distance between the vehicle (310) and surrounding vehicles, in order to appropriately reflect the interaction between the vehicle (310) and surrounding vehicles. This will be explained in detail with reference to FIGS. 4 to 8.

[0057] The server (350) may be a server that controls and manages the vehicle (310) and / or the lane determination device (330). The server (350) may be a server that monitors the vehicle (330) in real time and manages the vehicle (330). The server (350) may perform remote control of the vehicle (330).

[0058] The vehicle (310), lane determination device (330), and server (350) can communicate using a network (not shown). For example, the network may include a Local Area Network (LAN), a Wide Area Network (WAN), a Value Added Network (VAN), a mobile radio communication network, a satellite communication network, and combinations thereof. The network is a comprehensive data communication network that enables the vehicle (310), lane determination device (330), and server (350) to communicate smoothly with each other, and may include wired internet, wireless internet, and mobile wireless communication networks. Additionally, the wireless communication network may include, for example, Wi-Fi, Bluetooth, Bluetooth Low Energy, Zigbee, Wi-Fi Direct (WFD), Ultra-Wideband (UWB), Infrared Data Association (IrDA), Near Field Communication (NFC), but is not limited thereto.

[0059]

[0060] FIG. 4 is a diagram illustrating a method for determining whether to change lanes based on the distance and relative speed to surrounding vehicles according to one embodiment.

[0061] Referring to FIG. 4, the time-series driving trajectory of the first vehicle (430) (e.g., 430-0 to 430-N) and the time-series driving trajectory of the second vehicle (440) (e.g., 440-0 to 440-N) can be observed. The first vehicle (430) may be driving in the first lane (410), and the second vehicle (440) may be driving in the second lane (420). At this time, a method for determining the risk of collision between the first vehicle (430) and the second vehicle (440) when the first vehicle (430) attempts to change to the second lane (420) will be explained below.

[0062] A lane determination device (e.g., lane determination device (330) of FIG. 3) can predict the future driving trajectory of the first vehicle (430) based on the current position of the first vehicle (430) (e.g., position at the current time point). The lane determination device (330) can predict the future driving trajectory of the first vehicle (430) through a Gaussian distribution from the current position of the first vehicle (430). For example, the lane determination device (330) can adjust the lateral direction of the first vehicle (430) to reflect a situation where the first vehicle (430) attempts to change into the second lane (420). The lane determination device (330) can predict the position over time through the current position of the first vehicle (430) (e.g., position at t=0 (430-0)) and the adjusted direction, assuming that the first vehicle (430) is moving at a constant velocity. The lane determination device (330) can predict a future position (e.g., a position at a future point in time) (e.g., a position from t=1 to t=N (430-1 to 430-N)) from a position (430-0) when the first vehicle (430) moves at a constant speed from t=0 to t=N. The future driving trajectory may refer to a trajectory (or path) connecting the current position to the predicted future position. The lane determination device (330) can model (or reflect) uncertainty through a Gaussian distribution on the future driving trajectory calculated in this way (e.g., a trajectory calculated assuming the first vehicle (430) moves at a constant speed). That is, the lane determination device (330) can predict the future driving trajectory in the form of a probability distribution with the trajectory calculated assuming the first vehicle (430) moves at a constant speed as the average. The future driving trajectory in the form of a probability distribution can be expressed in the form of a Gaussian distribution as shown in Equation 1 below.

[0063]

[0064] In mathematical formula 1, N represents a Gaussian distribution, and represents the average of the future driving trajectory of the first vehicle (430) (e.g., a trajectory calculated assuming the first vehicle (430) moves at a constant speed), and represents the standard deviation of the future driving trajectory of the first vehicle (430).

[0065] The lane determination device (330) can predict the future driving trajectory of the second vehicle (440) based on the current position of the second vehicle (440) (e.g., position at t=0 (440-0)) through substantially the same method as predicting the future trajectory of the first vehicle (430).

[0066] The lane determination device (330) can calculate the bhattacharyya similarity between the future driving trajectory of the first vehicle (430) and the future driving trajectory of the second vehicle (440). The lane determination device (330) can calculate the bhattacharyya similarity between the future driving trajectory of the first vehicle (430) and the future driving trajectory of the second vehicle (440) based on the longitudinal direction and / or the lateral direction. When the lane determination device (330) is based on the longitudinal direction and / or the lateral direction, it can use the standard deviations in the longitudinal and / or lateral directions of the future driving trajectory of the first vehicle (430) and the future driving trajectory of the second vehicle (440). The lane determination device (330) can calculate the final bhattacharyya similarity by summing the bhattacharyya similarities based on the longitudinal and / or lateral directions. For example, the lane determination device (330) can calculate the risk level according to each direction by calculating the bataratiya similarity based on the longitudinal and / or transverse directions through the following mathematical formulas 2 and 3. The lane determination device (330) can calculate the final bataratiya similarity through mathematical formula 4.

[0067]

[0068] In mathematical formulas 2 to 4, represents the Bataratsia similarity based on the longitudinal direction, represents the Bataratsia similarity based on the lateral direction, represents the final Bataratsia similarity, represents the longitudinal position in the future driving trajectory of the first vehicle (430), and represents the longitudinal position in the future driving trajectory of the second vehicle (440), and represents the lateral position in the future driving trajectory of the second vehicle (440), and represents the longitudinal standard deviation of the future driving trajectory of the first vehicle (430), and represents the longitudinal standard deviation of the future driving trajectory of the second vehicle (440), and represents the standard deviation in the lateral direction of the future driving trajectory of the first vehicle (430), and represents the standard deviation in the lateral direction of the future driving trajectory of the second vehicle (440).

[0069]

[0070] The lane determination device (330) can calculate a risk level (e.g., a first risk level) corresponding to the Bataratiya similarity. In predicting a future driving trajectory, the uncertainty of the prediction may be greater as time passes. To compensate for such uncertainty of the prediction over time, the lane determination device (330) can calculate a first risk level by applying a time-dependent weight. For example, the lane determination device (330) can calculate a first risk level using the following mathematical formula 5.

[0071]

[0072] In mathematical formula 5, represents the first risk level, and decay_rate represents a weight over time (e.g., to reduce the uncertainty of the prediction over time) (e.g., negative). The descriptions of the parameters described in Equations 1 through 4 can be practically applied in the same way to Equation 5.

[0073] The first risk level is a risk level calculated through the similarity of the future driving trajectories of the first vehicle (430) and the second vehicle (440), and may not adequately reflect the interaction between the first vehicle (430) and the second vehicle (440). Accordingly, the lane determination device (330) may use the following second risk level to adequately reflect the interaction in determining whether there is a collision between the first vehicle (430) and the second vehicle (440). The method for calculating the second risk level will be explained below.

[0074] The lane determination device (330) can calculate the inverse time to collision (ITTC) between the first vehicle (430) and the second vehicle (440) based on the distance between the first vehicle (430) and the second vehicle (440) and the relative speed between the first vehicle (430) and the second vehicle (440). ITTC is the inverse of TTC, and TTC can represent the time taken to collision assuming that the first vehicle (430) and the second vehicle (440) are moving at a constant speed and / or acceleration. The lane determination device (330) can calculate the ITTC at the current time (e.g., t=0).

[0075] The lane determination device (330) can calculate a second risk level corresponding to the ITTC. The lane determination device (330) can calculate a total risk level by combining the first risk level and the second risk level. For example, the second risk level and / or total risk level can be calculated as shown in Equation 6 and / or Equation 7 below.

[0076]

[0077] In mathematical formulas 6 and 7, represents the relative speed between the first vehicle (430) and the second vehicle (440), and D represents the distance between the first vehicle (430) and the second vehicle (440). represents the second risk level, and risk represents the total risk level. The description of the parameters listed in Equation 5 can be practically applied in the same way to Equations 6 and 7.

[0078] As described above, the lane determination device (330) can calculate the risk of collision with the second vehicle (440) in a situation where the first vehicle (430) attempts to change to the second lane (420) based on the interaction and future driving of the first vehicle (430) and the second vehicle (440). Based on the risk, the lane determination device (330) can determine whether the first vehicle (430) will move to the lane (e.g., the second lane (420)) where the second vehicle (440) is driving. This will be explained in detail with reference to FIG. 5.

[0079]

[0080] FIG. 5 is a diagram illustrating the operation of setting a threshold value of risk according to one embodiment.

[0081] Referring to FIG. 5, the lane determination device (330) can determine whether the first vehicle (e.g., the first vehicle (430) of FIG. 4) will move into the lane (e.g., the second lane (420) of FIG. 4) where the second vehicle (e.g., the second vehicle (440) of FIG. 4) is driving, based on the risk level.

[0082] The lane determination device (330) can set a threshold value for risk. The lane determination device (330) can set a threshold value by modeling the risk level with respect to the speed of the first vehicle (430) based on ground truth values. Ground truth values ​​may include actual driving data where a lane change was successful. For example, the lane determination device (330) can store the speed and risk level of the first vehicle (430) at the moment a lane change was successful through ground truth values. The lane determination device (330) can analyze at what risk level a lane change was successful depending on the speed of the first vehicle (430). The lane determination device (330) can repeat the above process to model a data-driven threshold value for risk based on the speed of the first vehicle (430). Through this, the lane determination device (330) can determine whether a lane change was human-like. Below, a method for setting a data-driven threshold value for risk will be described in detail.

[0083] The lane determination device (330) can check the risk graph (500) upon successful lane change according to the speed of the first vehicle (430) through actual values. The lane determination device (330) can remove risks on the graph (500) where the magnitude of the risk is 0.9 (e.g., 90%) or greater. Risks where the magnitude of the risk is 0.9 (e.g., 90%) or greater are actual values ​​generated by a person dangerously changing lanes, and this may be for the purpose of filtering them out. The lane determination device (330) can obtain a linear graph (520) by linearly interpolating the actual risk (original risk) (510) on the graph (500). The lane determination device (330) can set the upper envelope (530) and lower envelope (540) by adding or subtracting a preset value (e.g., set by the user and / or lane determination device (330)) (e.g., 0.025) from the linear graph (520). The lane determination device (330) can set the upper envelope (530) and lower envelope (540) to threshold values ​​of risk.

[0084] The lane determination device (330) can determine whether the first vehicle (430) moves into the lane where the second vehicle (440) is driving (e.g., the second lane (420)) by comparing the risk level with a threshold value. The lane determination device (330) can determine whether to change lanes by comparing whether the risk level is included in the envelope region (550). The lane determination device (330) can determine that the first vehicle (430) does not move into the lane where the second vehicle (440) is driving if the risk level is greater than the threshold value (e.g., the upper envelope (530)). The lane determination device (330) can determine that the first vehicle (430) moves into the lane where the second vehicle (440) is driving if the risk level is less than the threshold value (e.g., the lower envelope (540)). For example, the lane determination device (330) may determine that the current lane change is dangerous when the risk level is contained within the envelope area (550) (e.g., when it is smaller than the upper envelope (530)) and then crosses the upper envelope (530). If the lane determination device (330) determines that the lane change is dangerous, it may determine that the first vehicle (430) does not move to the second lane (420). As another example, the lane determination device (330) may determine that the current lane change is not dangerous when the risk level is located above the envelope area (550) (e.g., when the risk level is larger than the upper envelope (530)) and then becomes smaller than the lower envelope (540). If the lane determination device (330) determines that the lane change is not dangerous, it may determine that the first vehicle (430) moves to the second lane (420).

[0085]

[0086] Figure 6 is a diagram illustrating a method for calculating the risk of collision with a rear vehicle when changing lanes in various scenarios.

[0087] Referring to FIG. 6, scenario (610) may represent a scenario in which the second vehicle (620) (e.g., the second vehicle (440) in FIG. 4) is traveling at a speed of 5 m / s and the first vehicle (630) (e.g., the first vehicle (430) in FIG. 4) is stationary and the second vehicle (620) changes into the lane in which the second vehicle (620) is traveling. Scenario (640) may represent a scenario in which the second vehicle (660) (e.g., the second vehicle (440) in FIG. 4) is traveling at a speed of 10 m / s and the first vehicle (650) (e.g., the first vehicle (430) in FIG. 4) is stationary and the second vehicle (660) changes into the lane in which the second vehicle (660) is traveling.

[0088] When calculating the risk, the lane determination device (e.g., the lane determination device (330) of FIG. 3) considers the interaction between the first vehicle (630, 650) and the second vehicle (620, 660), so the value of the risk may be calculated differently depending on the speed of the second vehicle (620, 660). For example, in scenario (640), the speed of the second vehicle (660) is faster than in scenario (610), so the risk of collision may be greater when the first vehicle (650) changes lanes. Accordingly, since the relative speed between the first vehicle (650) and the second vehicle (660) is greater, the second risk (e.g., corresponding to ITTC) may be calculated to be greater. That is, the lane determination device (330) may calculate the risk to be greater in scenario (640) than in scenario (610).

[0089]

[0090] FIG. 7 is an example of a flowchart of a method for determining a lane according to one embodiment.

[0091] Operations 710 and 730 may be performed sequentially, but are not limited thereto. For example, the two operations may be performed in parallel. Operations 710 and 730 may be substantially identical to the operation of the lane determination device (e.g., lane determination device (330) of FIG. 3) described with reference to FIG. 1 through 6. Accordingly, a detailed description is omitted.

[0092] In operation 710, the lane determination device (330) can measure the similarity between the future driving trajectory of the first vehicle (e.g., vehicle (310) of FIG. 3 and / or vehicle (430) of FIG. 4) and the future driving trajectory of the second vehicle (e.g., vehicle (440) of FIG. 4). The lane determination device (330) can calculate the Bhattacharyya similarity between the future driving trajectory of the first vehicle (430) and the future driving trajectory of the second vehicle (440). However, the method of calculating similarity is not limited to this, and various similarity calculation methods may be used.

[0093] In operation 730, the lane determination device (330) may obtain a risk of collision when the first vehicle (430) moves into the lane in which the second vehicle (440) is traveling, based on similarity, distance between the first vehicle (430) and the second vehicle (440), and relative speed between the first vehicle (430) and the second vehicle (440). The risk may include a first risk corresponding to similarity between future trajectories and / or a second risk corresponding to ITTC. Since the first risk corresponds to similarity between future trajectories, it may not reflect the interaction and / or non-linear behavior between the first vehicle (430) and the second vehicle (440). The lane determination device (330) may use the second risk to determine whether there is a risk of collision when changing lanes by considering the interaction between the first vehicle (430) and the second vehicle (440).

[0094] In operation 750, the lane determination device (330) can determine whether the first vehicle (430) moves into the lane where the second vehicle (440) is driving based on the risk level. The lane determination device (330) can set a threshold value for the risk level and determine whether the first vehicle (430) changes lanes by comparing the risk level with the threshold value.

[0095]

[0096] FIG. 8 is an example of an electronic device according to one embodiment.

[0097] Referring to FIG. 8, the electronic device (800) may include a memory (810) and a processor (830). The description with reference to FIG. 1 through 7 may be applied in the same way to FIG. 8. For example, the difference determination device (330) of FIG. 3 may be the electronic device (800).

[0098] Memory (810) can store instructions (e.g., programs) executable by the processor (830). For example, the instructions may include instructions for executing the operation of the processor (830) and / or the operation of each component of the processor (830).

[0099] The memory (810) can be implemented as a volatile memory device or a non-volatile memory device.

[0100] Volatile memory devices can be implemented as DRAM (dynamic random access memory), SRAM (static random access memory), T-RAM (thyristor RAM), Z-RAM (zero capacitor RAM), or TTRAM (Twin Transistor RAM).

[0101] Non-volatile memory devices can be implemented as EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, MRAM (Magnetic RAM), Spin-Transfer Torque (STT)-MRAM, Conductive Bridging RAM (CBRAM), FeRAM (Ferroelectric RAM), PRAM (Phase change RAM), Resistive RAM (RRAM), Nanotube RRAM, Polymer RAM (PoRAM), Nano Floating Gate Memory (NFGM), holographic memory, Molecular Electronic Memory Device, or Insulator Resistance Change Memory.

[0102] The processor (830) can process data stored in memory (810). The processor (830) can execute computer-readable code (e.g., software) stored in memory (810) and instructions triggered by the processor (830).

[0103] The processor (830) may be a data processing device implemented in hardware having a circuit having a physical structure for executing desired operations. For example, the desired operations may include code or instructions included in a program.

[0104] For example, a data processing device implemented in hardware may include a microprocessor, a central processing unit, a processor core, a multi-core processor, a multiprocessor, an Application-Specific Integrated Circuit (ASIC), and a Field Programmable Gate Array (FPGA).

[0105] The processor (830) can cause the electronic device (800) to perform one or more operations by executing code and / or instructions stored in memory (810). The operations performed by the electronic device (800) may be substantially the same as the operations performed by the difference determination device (330) described with reference to FIGS. 1 through 7. Such redundant descriptions are omitted.

[0106]

[0107] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0108] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on computer-readable recording media.

[0109] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may store program instructions, data files, data structures, etc., either individually or in combination, and the program instructions recorded on the medium may be those specifically designed and configured for the embodiment or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0110] The hardware device described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0111] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based thereon. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0112] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

1. Regarding the method of determining the lane, An operation to measure the similarity between the future driving trajectory of a first vehicle and the future driving trajectory of a second vehicle traveling in a different lane from the first vehicle behind the first vehicle; An operation to acquire a risk of collision when the first vehicle moves into the lane in which the second vehicle is traveling, based on the similarity, the distance between the first vehicle and the second vehicle, and the relative speed between the first vehicle and the second vehicle; and Based on the above risk, an operation to determine whether the first vehicle moves into the lane where the second vehicle is driving. including The above future driving trajectory is, A method for the driving trajectory of a vehicle from its current location to a future point in time.

2. In Paragraph 1, The operation of measuring the above similarity is, An operation to predict the future driving trajectory of the first vehicle based on the current position of the first vehicle; An operation to predict the future driving trajectory of the second vehicle based on the current position of the second vehicle; and The operation of calculating the Bhattacharyya similarity between the future driving trajectory of the first vehicle and the future driving trajectory of the second vehicle. A method including 3. In Paragraph 2, The operation of predicting the future driving trajectory of the first vehicle is, Operation of predicting the future driving trajectory of the first vehicle from the current position of the first vehicle through a Gaussian distribution. A method including 4. In Paragraph 2, The operation of predicting the future driving trajectory of the second vehicle is, Operation of predicting the future driving trajectory of the second vehicle from the current position of the second vehicle through a Gaussian distribution A method including 5. In Paragraph 1, The operation of acquiring the above risk level is, An operation to calculate the inverse time to collision (ITTC) between the first vehicle and the second vehicle based on the distance between the first vehicle and the second vehicle and the relative speed between the first vehicle and the second vehicle; and Operation of calculating the risk level based on the above similarity and the above ITTC A method including 6. In Paragraph 5, The operation of calculating the above risk level is, An operation to calculate a first risk level corresponding to the above similarity; An operation to calculate a second risk level corresponding to the above ITTC; and The operation of calculating the total risk level by combining the first risk level and the second risk level. A method including 7. In Paragraph 1, The operation of determining whether the first vehicle moves into the lane in which the second vehicle is driving is, The operation of setting the threshold value of the above risk level; An operation to determine whether the first vehicle moves into the lane where the second vehicle is driving by comparing the above risk level and the above threshold value. A method including 8. In Paragraph 7, The operation of setting the threshold value of the above risk level is, Operation of setting the threshold value by modeling the risk level with respect to the speed of the first vehicle based on the ground truth of driving data where the lane change was successful. A method including 9. In Paragraph 7, The operation of determining whether the first vehicle moves into the lane in which the second vehicle is driving by comparing the above risk level and the above threshold value is, An action of determining that the first vehicle does not move to the lane in which the second vehicle is traveling when the above risk level is greater than the above threshold value; and When the above risk level is smaller than the above threshold value, the operation of determining that the first vehicle moves to the lane in which the second vehicle is driving. A method including 10. In an electronic device for determining a lane, processor; and Memory that stores instructions Includes, The above instructions are executed individually or collectively by the processor, causing the electronic device, Measuring the similarity between the future driving trajectory of a first vehicle and the future driving trajectory of a second vehicle traveling in a different lane from the first vehicle behind the first vehicle, and Based on the above similarity, the distance between the first vehicle and the second vehicle, and the relative speed between the first vehicle and the second vehicle, a risk of collision is obtained when the first vehicle moves into the lane in which the second vehicle is traveling, and Based on the above risk, determine whether the first vehicle will move into the lane in which the second vehicle is driving, and The above future driving trajectory is, An electronic device that is the driving trajectory of a vehicle from its current location to a future point in time.

11. In Paragraph 10, The above instructions are executed individually or collectively by the processor, causing the electronic device, Based on the current location of the first vehicle, predict the future driving trajectory of the first vehicle, and Based on the current location of the second vehicle, predict the future driving trajectory of the second vehicle, and An electronic device for calculating the Bhattacharyya similarity between the future driving trajectory of the first vehicle and the future driving trajectory of the second vehicle.

12. In Paragraph 11, The above instructions are executed individually or collectively by the processor, causing the electronic device, An electronic device that predicts the future driving trajectory of the first vehicle from the current position of the first vehicle through a Gaussian distribution.

13. In Paragraph 11, The above instructions are executed individually or collectively by the processor, causing the electronic device, An electronic device that predicts the future driving trajectory of the second vehicle through a Gaussian distribution from the current position of the second vehicle.

14. In Paragraph 10, The above instructions are executed individually or collectively by the processor, causing the electronic device, Based on the distance between the first vehicle and the second vehicle and the relative speed between the first vehicle and the second vehicle, the inverse time to collision (ITTC) between the first vehicle and the second vehicle is calculated, and An electronic device that calculates the risk level based on the above similarity and the above ITTC.

15. In Paragraph 14, The above instructions are executed individually or collectively by the processor, causing the electronic device, Calculate a first risk level corresponding to the above similarity, and Calculate the second risk level corresponding to the above ITTC, and An electronic device that calculates a total risk by combining the first risk level and the second risk level.

16. In Paragraph 10, The above instructions are executed individually or collectively by the processor, causing the electronic device, Set the threshold value of the above risk level, and An electronic device that compares the above risk level and the above threshold value to determine whether the first vehicle moves into the lane where the second vehicle is driving.

17. In Paragraph 16, The above instructions are executed individually or collectively by the processor, causing the electronic device, An electronic device that sets the threshold value by modeling the risk level with respect to the speed of the first vehicle based on the ground truth of driving data that successfully changed lanes.

18. In Paragraph 16, The above instructions are executed individually or collectively by the processor, causing the electronic device, If the above risk level is greater than the above threshold value, it is determined that the first vehicle does not move into the lane in which the second vehicle is driving, and An electronic device that determines that the first vehicle moves to the lane in which the second vehicle is traveling when the above risk level is less than the above threshold value.

Images