Abstract: A travel control device carries out a travel control for a vehicle based on detected lane boundary lines. A first prescribed position, an absolute vehicle position and an absolute vehicle azimuth angle are stored while changing from a state where the lane boundary lines can be detected to a state where the lane boundary lines cannot be detected. A second prescribed position is stored while changing from a state in which the lane boundary lines cannot be detected to a state in which the lane boundary lines can be detected. The host vehicle is controlled to travel along a travel path connecting the first prescribed position and the second prescribed position where a current absolute position and a current absolute azimuth angle of the host vehicle do not deviate by a prescribed value or more from the stored absolute position and the stored absolute azimuth angle.

Abstract: A travel control device carries out a travel control for a vehicle based on detected lane boundary lines. A first prescribed position, an absolute vehicle position and an absolute vehicle azimuth angle are stored while changing from a state where the lane boundary lines can be detected to a state where the lane boundary lines cannot be detected. A second prescribed position is stored while changing from a state in which the lane boundary lines cannot be detected to a state in which the lane boundary lines can be detected. The host vehicle is controlled to travel along a travel path connecting the first prescribed position and the second prescribed position where a current absolute position and a current absolute azimuth angle of the host vehicle do not deviate by a prescribed value or more from the stored absolute position and the stored absolute azimuth angle.

Abstract: A vehicle behavior estimation method includes: detecting a speed of a first preceding vehicle traveling in front of a host vehicle in a first lane where the host vehicle is traveling; detecting a speed of an adjacent vehicle traveling in a second lane adjacent to the first lane; calculating a relative speed between the first preceding vehicle and the adjacent vehicle; predicting whether or not an absolute value of the relative speed will be at or below a speed threshold value within a predetermined time from a point time when a decrease in the absolute value of the relative speed starts to be detected; and estimating that the adjacent vehicle is likely to change lanes into the first lane when the absolute value of the relative speed is predicted to be at or below the speed threshold value within the predetermined time.

Abstract: A vehicle behavior estimation method includes: detecting a speed of a first preceding vehicle traveling in front of a host vehicle in a first lane where the host vehicle is traveling; detecting a speed of an adjacent vehicle traveling in a second lane adjacent to the first lane; calculating a relative speed between the first preceding vehicle and the adjacent vehicle; predicting whether or not an absolute value of the relative speed will be at or below a speed threshold value within a predetermined time from a point time when a decrease in the absolute value of the relative speed starts to be detected; and estimating that the adjacent vehicle is likely to change lanes into the first lane when the absolute value of the relative speed is predicted to be at or below the speed threshold value within the predetermined time.

Abstract: The vehicle control device sets a region including a stationary object on a road, calculates a passing position at which a host vehicle and an oncoming vehicle pass each other in accordance with a velocity of the host vehicle and a position and a velocity of the oncoming vehicle, calculates a first score that is a larger value as the velocity of the oncoming vehicle is greater, calculates a second score that is a larger value as an acceleration rate of the oncoming vehicle is greater, integrates the first score with the second score so as to calculate an integration score, and causes the host vehicle to decelerate when the integration score is greater than or equal to a predetermined value or causing the host vehicle to keep the velocity or accelerate when the integration score is smaller than the predetermined value.

Abstract: A controller causes a host vehicle to decelerate when a velocity of an oncoming vehicle corresponding to a position of the oncoming vehicle distant from a stationary object by a predetermined distance is greater than or equal to a velocity threshold corresponding to the position of the oncoming vehicle distant from the stationary object by the predetermined distance in a case in which a passing position is present within a predetermined region, and causes the host vehicle to keep the velocity or accelerate when the velocity of the oncoming vehicle corresponding to the position of the oncoming vehicle distant from the stationary object by the predetermined distance is less than the velocity threshold corresponding to the position of the oncoming vehicle distant from the stationary object by the predetermined distance in the case in which the passing position is present within the region.

Abstract: The vehicle control device sets a region including a stationary object on a road, calculates a passing position at which a host vehicle and an oncoming vehicle pass each other in accordance with a velocity of the host vehicle and a position and a velocity of the oncoming vehicle, calculates a first score that is a larger value as the velocity of the oncoming vehicle is greater, calculates a second score that is a larger value as an acceleration rate of the oncoming vehicle is greater, integrates the first score with the second score so as to calculate an integration score, and causes the host vehicle to decelerate when the integration score is greater than or equal to a predetermined value or causing the host vehicle to keep the velocity or accelerate when the integration score is smaller than the predetermined value.

Abstract: A controller causes a host vehicle to decelerate when a velocity of an oncoming vehicle corresponding to a position of the oncoming vehicle distant from a stationary object by a predetermined distance is greater than or equal to a velocity threshold corresponding to the position of the oncoming vehicle distant from the stationary object by the predetermined distance in a case in which a passing position is present within a predetermined region, and causes the host vehicle to keep the velocity or accelerate when the velocity of the oncoming vehicle corresponding to the position of the oncoming vehicle distant from the stationary object by the predetermined distance is less than the velocity threshold corresponding to the position of the oncoming vehicle distant from the stationary object by the predetermined distance in the case in which the passing position is present within the region.

Abstract: An other-vehicle action prediction method predicts that another vehicle traveling in an adjacent lane adjacent to an own lane in which a host vehicle is traveling makes a lane change from the adjacent lane to the own lane in front of the host vehicle in accordance with the behavior of the other vehicle. The other-vehicle action prediction method acquires traffic regulation information on a traffic regulation regarding the adjacent lane, predicts a predicted traveling state of the other vehicle when traveling according to the traffic regulation, calculates a recognition possibility that the other vehicle recognizes the traffic regulation, and predicts that the other vehicle makes a lane change in accordance with the recognition possibility, the predicted traveling state, and the actual traveling state.

Abstract: A motion prediction method of other vehicle computes, based on a behavior of a second vehicle running in an adjacent lane, a lane change probability indicating a probability of the second vehicle conducting a lane change in front of an own vehicle from the adjacent lane into an own lane in which the own vehicle is running and, with use of the lane change probability and a threshold value, predicts the lane change to be conducted by the second vehicle.

Abstract: A travel assistance method selects a merging destination vehicle that will travel in front or behind a host vehicle when the host vehicle merges into an adjacent lane, based on a history of whether other vehicles traveling in the adjacent lane allowed merging of a first preceding vehicle traveling in front of the host vehicle on a host lane and locations of the other vehicles traveling in the adjacent lane in a lane direction within a section in which the merging into the adjacent lane from the host lane is possible.

Abstract: A travel assistance method selects a merging destination vehicle that will travel in front or behind a host vehicle when the host vehicle merges into an adjacent lane, based on a history of whether other vehicles traveling in the adjacent lane allowed merging of a first preceding vehicle traveling in front of the host vehicle on a host lane and locations of the other vehicles traveling in the adjacent lane in a lane direction within a section in which the merging into the adjacent lane from the host lane is possible.

Abstract: An other-vehicle action prediction method predicts that another vehicle traveling in an adjacent lane adjacent to an own lane in which a host vehicle is traveling makes a lane change from the adjacent lane to the own lane in front of the host vehicle in accordance with the behavior of the other vehicle. The other-vehicle action prediction method acquires traffic regulation information on a traffic regulation regarding the adjacent lane, predicts a predicted traveling state of the other vehicle when traveling according to the traffic regulation, calculates a recognition possibility that the other vehicle recognizes the traffic regulation, and predicts that the other vehicle makes a lane change in accordance with the recognition possibility, the predicted traveling state, and the actual traveling state.

Abstract: A traveling assistance method acquires driving characteristics of another vehicle around a host vehicle, determines whether the other vehicle is in an autonomous driving mode depending on the driving characteristics of the other vehicle, and detects an action of the other vehicle in accordance with the determination result of whether the other vehicle is in the autonomous driving mode.

Abstract: An action prediction method for predicting an action of another vehicle around a host vehicle, acquires information on conditions of a road surface around the other vehicle, and predicts the action of the other vehicle in accordance with the information on the conditions of the road surface.

Abstract: A traveling assistance method acquires driving characteristics of another vehicle around a host vehicle, determines whether the other vehicle is in an autonomous driving mode depending on the driving characteristics of the other vehicle, and detects an action of the other vehicle in accordance with the determination result of whether the other vehicle is in the autonomous driving mode.

Abstract: A carrier for carrying an object includes a fork that is vertically movable to carry the object and that is able to be inserted into an opening of a flat portion of the object, a sensor that obtains actual measured values at a plurality of points on the flat portion of the object, and an object state identification device that identifies, based on the actual measured values, an object state including at least one of a position and a posture of the object with respect to the sensor.

Abstract: An object state identification method of identifying a position and a posture of an object by obtaining actual measured values at a plurality of points on a flat portion including an opening on a surface of the object by a sensor includes generating a model value group that is a set of model values indicating the positions of a plurality of points present on surfaces of a corner model, calculating a model feature value based on at least one model value included in the model value group, calculating an actual feature value by the same method used to calculate the model feature value, extracting a corresponding point value indicating a position of an edge of the opening based on the actual feature value that matches the model feature value, and identifying the position and posture of the object based on the corresponding point value.

Abstract: An object state identification method of identifying a position and a posture of an object by obtaining actual measured values, which are three-dimensional data, at points on a flat portion including an opening on a surface of the object by a sensor includes extracting a corresponding point value indicating the position of an edge of the opening based on a predetermined feature value, calculating a plane equation indicating a plane including the flat portion based on the corresponding point value to determine a virtual plane, extracting, as a stable point, an actual measured value that is in the virtual plane, and identifying the position, posture, etc., of the object based on the stable point.

Abstract: An object state identification method of identifying a position and a posture of an object by obtaining actual measured values at a plurality of points on a flat portion including an opening on a surface of the object by a sensor includes generating a model value group that is a set of model values indicating the positions of a plurality of points present on surfaces of a corner model, calculating a model feature value based on at least one model value included in the model value group, calculating an actual feature value by the same method used to calculate the model feature value, extracting a corresponding point value indicating a position of an edge of the opening based on the actual feature value that matches the model feature value, and identifying the position and posture of the object based on the corresponding point value.