Abstract: A prediction accuracy evaluation method is executed by a computer. The prediction accuracy evaluation method includes a process of acquiring detection information. The detection information indicates a detected position, a detected velocity, an error range of the detected position, and an error range of the detected velocity of an obstacle detected by using a sensor mounted on a moving body. The prediction accuracy evaluation method further includes: a predicted distribution generation process that generates a predicted distribution of a position of the obstacle at a second time later than a first time, based on first detection information that is the detection information at the first time; and a prediction abnormality determination process that determines whether or not the predicted distribution is abnormal based on the predicted distribution and a second detected position that is the detected position of the obstacle at the second time.

Abstract: A vehicle control system generates a target trajectory and controls a vehicle to follow the target trajectory. Blind spot information indicates a blind spot region present in front of the vehicle. Under assumption that a first object appears at a first position in front of the vehicle, decelerating the vehicle with a first deceleration cannot avoid a collision between the first object and the vehicle. A deceleration map, which is prepared in advance, indicates at least a collision region consisting of the first position. The vehicle control system recognizes, based on the deceleration map, the collision region under assumption that the vehicle reaches a future position on the target trajectory. When the collision region and the blind spot region overlap each other, the vehicle control system modifies the target trajectory so that the collision region and the blind spot region do not overlap each other.

Abstract: A vehicle control system for controlling a vehicle is configured to perform automated driving by switching between a plurality of automated driving modes. The plurality of automated driving modes include: a first automated driving mode that does not require a driving operation by a human; and a second automated driving mode that requests an operation or monitoring by a human as necessary. In the first automated driving mode, the vehicle control system determines that there is human intervention when an operation state of an operating member operable by a human satisfies a first condition. In the second automated driving mode, the vehicle control system determines that there is human intervention when the operation state of the operating member satisfies a second condition. The first condition is less likely to be satisfied than the second condition.

Abstract: A vehicle control system includes one or more processors configured to execute automated driving control that controls automated driving of a vehicle. The automated driving control includes risk avoidance control that avoids a collision with a target around the vehicle. When a notification representing a risk level around the vehicle is received from an operator during the automated driving control, the one or more processors are configured to relax an activation condition of the risk avoidance control or increase a control amount in the risk avoidance control as the risk level becomes higher.

Abstract: The vehicle controller of the present disclosure acquires a preset operation route, and causes the vehicle to travel along the preset operation route in one of an autonomous driving mode and a manual driving mode. The autonomous driving mode is a mode in which the vehicle is operated by autonomous driving. The manual driving mode is a mode in which the vehicle is operated by manual driving in which at least steering is manually performed. The vehicle controller of the present disclosure generates steering torque in a direction of returning the vehicle to the preset operation route in response to detection of steering toward a road deviating from the preset operation route during operation in the manual driving mode.

Abstract: A route search device includes a memory and a processor. The processor performs search processing for a route from a current position to a destination of a ride-sharing vehicle based on data stored in the memory. A standard route with the shortest requested time from the current position to the destination is calculated in the search processing. A high-frequency route with a frequency of encountering a pedestrian between the current position and the destination that is higher than the standard route is also calculated in the search processing. A recognition level is compared with a reference level in the search processing. When the recognition level is equal to or less than the reference level, the standard route is selected as a final route. When the recognition level is higher than the reference level, the high-frequency route is selected as the final route.

Abstract: A traveling trajectory estimation system obtains traveling record information indicating a past traveling record of a vehicle, and characteristic object position information indicating the installation position of a characteristic object, and performs a vehicle position estimation process to estimate an object vehicle position at an object time, based on the traveling record information and the characteristic object position information. In the vehicle position estimation process, not only a time previous to the object time, but also a time subsequent to the object time, is used as a reference time. The traveling trajectory estimation system sets each of a plurality of successive times as the object time, and performs the vehicle position estimation process, to estimate the object vehicle positions at the respective times, and determines a collection of the estimated object vehicle positions as a traveling trajectory of the vehicle.

Abstract: An autonomous driving system configured to make an abnormality determination for an in-vehicle device at an abnormality determination point while an autonomous vehicle is driving autonomously includes: a route search unit configured to search for a travel route from a departure point to a destination point; a route determination unit configured to determine a determination route for making the abnormality determination for the in-vehicle device from the searched travel route, based on necessity of making the abnormality determination for the in-vehicle device and the number of the abnormality determination points on the travel route; and an abnormality determination unit configured to make the abnormality determination for the in-vehicle device at the abnormality determination point while the autonomous vehicle is driving along the determination route.

Abstract: A self-position estimation accuracy verification method includes a step of moving a mobile object to a first check point, a step of acquiring first check information, a step of starting a self-position estimation using the first check information as an initial value, a step of moving the mobile object to a second check point while continuing the self-position estimation, a step of acquiring second check information, and a step of calculating a deviation between a position and a posture of the mobile object on the map estimated by the self-position estimation at the second check point and a position and a posture of the mobile object on the map indicated in the second check information, and verifying the accuracy of the self-position estimation based on the deviation.

Abstract: The vehicle position estimation apparatus that estimates the position of the host vehicle includes: a laser light irradiation unit configured to illuminate laser light; a light reception element configured to receive reflection light of the laser light and reflection light of ambient light which is light other than the laser light and be able to detect an intensity of each of the received reflection light; and a host position estimation unit configured to estimate the position of the host vehicle, based on a result of light reception of the reflection light of the laser light received by the light reception element and a result of light reception of the reflection light of the ambient light.

Abstract: An automated drive device that automatically stops a vehicle in a pick-up and drop-off area in which a passenger gets and off the vehicle includes at least one processor and at least one memory that stores a program and information to be read by the at least one processor. The processor is configured to acquire the type of the passenger before the vehicle reaches the pick-up and drop-off area as a first process. The processor is configured to change a behavior for stopping the vehicle in the pick-up and drop-off area in accordance with the type of the passenger as a second process.

Abstract: A route search device includes a memory and a processor. The processor performs search processing for a route from a current position to a destination of a ride-sharing vehicle based on data stored in the memory. A standard route with the shortest requested time from the current position to the destination is calculated in the search processing. A high-frequency route with a frequency of encountering a pedestrian between the current position and the destination that is higher than the standard route is also calculated in the search processing. A recognition level is compared with a reference level in the search processing. When the recognition level is equal to or less than the reference level, the standard route is selected as a final route. When the recognition level is higher than the reference level, the high-frequency route is selected as the final route.

Abstract: A traveling trajectory estimation system obtains traveling record information indicating a past traveling record of a vehicle, and characteristic object position information indicating the installation position of a characteristic object, and performs a vehicle position estimation process to estimate an object vehicle position at an object time, based on the traveling record information and the characteristic object position information. In the vehicle position estimation process, not only a time previous to the object time, but also a time subsequent to the object time, is used as a reference time. The traveling trajectory estimation system sets each of a plurality of successive times as the object time, and performs the vehicle position estimation process, to estimate the object vehicle positions at the respective times, and determines a collection of the estimated object vehicle positions as a traveling trajectory of the vehicle.

Abstract: A self-position estimation accuracy verification method includes a step of moving a mobile object to a first check point, a step of acquiring first check information, a step of starting a self-position estimation using the first check information as an initial value, a step of moving the mobile object to a second check point while continuing the self-position estimation, a step of acquiring second check information, and a step of calculating a deviation between a position and a posture of the mobile object on the map estimated by the self-position estimation at the second check point and a position and a posture of the mobile object on the map indicated in the second check information, and verifying the accuracy of the self-position estimation based on the deviation.

Abstract: An automated drive device that automatically stops a vehicle in a pick-up and drop-off area in which a passenger gets and off the vehicle includes at least one processor and at least one memory that stores a program and information to be read by the at least one processor. The processor is configured to acquire the type of the passenger before the vehicle reaches the pick-up and drop-off area as a first process. The processor is configured to change a behavior for stopping the vehicle in the pick-up and drop-off area in accordance with the type of the passenger as a second process.

Abstract: An autonomous driving system configured to make an abnormality determination for an in-vehicle device at an abnormality determination point while an autonomous vehicle is driving autonomously includes: a route search unit configured to search for a travel route from a departure point to a destination point; a route determination unit configured to determine a determination route for making the abnormality determination for the in-vehicle device from the searched travel route, based on necessity of making the abnormality determination for the in-vehicle device and the number of the abnormality determination points on the travel route; and an abnormality determination unit configured to make the abnormality determination for the in-vehicle device at the abnormality determination point while the autonomous vehicle is driving along the determination route.

Abstract: The vehicle position estimation apparatus that estimates the position of the host vehicle includes: a laser light irradiation unit configured to illuminate laser light; a light reception element configured to receive reflection light of the laser light and reflection light of ambient light which is light other than the laser light and be able to detect an intensity of each of the received reflection light; and a host position estimation unit configured to estimate the position of the host vehicle, based on a result of light reception of the reflection light of the laser light received by the light reception element and a result of light reception of the reflection light of the ambient light.

Abstract: An object detection apparatus includes: a laser light irradiation unit; a light reception element configured to detect reflection light of the laser light and reflection light of ambient light which is light other than the laser light; a camera; an information correction unit configured to generate corrected ambient light information by correcting ambient light information, which is information about the reflection light of the ambient light detected by the light reception element, based on a camera image; an object detection unit configured to detect an object target, based on the corrected ambient light information and laser light information received by the light reception element.

Abstract: The object detection apparatus detects an object target by using the LIDAR and the camera. The object detection apparatus includes a calibration processing unit that is configured to perform calibration of the LIDAR and the camera. The LIDAR includes a light reception element configured to receive reflection light of irradiated laser light and reflection light of ambient light which is light other than the laser light and to detect an intensity of the received reflection light of the ambient light. The calibration processing unit is configured to perform the calibration, based on a result of light reception of the received reflection light of the ambient light and the camera image captured by the camera.

Abstract: The object detection apparatus includes: a laser light irradiation unit; a light reception element configured to detect a laser light intensity of reflection light of laser light and an ambient light intensity of reflection light of ambient light; a correlation information generation unit configured to generate correlation information indicating a correlation relationship between the laser light intensity and the ambient light intensity; an image correction unit configured to correct the camera image captured by the camera based on the correlation information and generate a corrected camera image; and an object detection unit configured to detect an object target based on the corrected camera image.