Provided are autonomous vehicles (AV), computer program products, and methods for maneuvering an AV in a roadway, including receiving forecast information associated with predicted trajectories of one or more actors in a roadway, determining a relevant trajectory of an actor based on correlating a forecast for predicted trajectories of the actor with the trajectory of the AV, regenerate a distance table for the relevant trajectory previously generated for processing constraints, generate a plurality of margins for the AV to evaluate, the margins based on a plurality of margin types for providing information about risks and effects on passenger comfort associated with a future proximity of the AV to the actor, classifying an interaction between the AV and the actor based on a plurality of margins, and generating continuous scores for each candidate trajectory that is also within the margin of the actor generated for the relevant trajectory.

The disclosure relates to a lane change method and system, a storage medium, and a vehicle. The lane change method includes the following steps: receiving consecutive frames of condition information, the condition information including velocity information of a current vehicle, state information of an adjacent vehicle, and lane information; with the condition information as an input to a neural network, processing the condition information by means of the neural network, to obtain an initial lane change strategy; and correcting the initial lane change strategy based on a predetermined rule and the condition information, to generate and output a corrected lane change strategy. According to this lane change method, intelligent, safe and efficient lane change may be achieved during an autonomous driving or driving assistance process.

Image data are input to a machine learning program. The machine learning program is trained with a virtual boundary model based on a distance between a host vehicle and a target object and a loss function based on a real-world physical model. An identification of a threat object is output from the machine learning program. A subsystem of the host vehicle is actuated based on the identification of the threat object.

The present invention obtains a processor, a processing method, a warning system, and a straddle-type vehicle capable of improving both the rider's safety and the rider's comfort. A processor (20) includes: an acquisition section that acquires surrounding environment information corresponding to output of a surrounding environment detector (11) during travel of a straddle-type vehicle (100); a determination section that determines necessity of warning operation provided to the rider and generated by the warning system (1); and a control section that makes an alarm (30) perform the warning operation in the case where the determination section determines that the warning operation is necessary. The acquisition section further acquires helmet posture direction information corresponding to output of a helmet posture direction detector (13) during the travel of the straddle-type vehicle (100). The determination section determines the necessity of the warning operation on the basis of the surrounding environment information and the helmet posture direction information.

A vehicle running control method includes: calculating, by a controller, a lateral velocity of an adjacent vehicle that travels in a lane adjacent to a traveling lane in which an autonomous vehicle travels in the road-width direction, and a longitudinal velocity of the adjacent vehicle in the direction in which the adjacent lane extends; specifying, by the controller, a predetermined road section based on the longitudinal velocity and calculating a first path on the assumption that an offset distance of the adjacent vehicle in the adjacent lane in the road-width direction is maintained within the road section; and applying, by the controller, the lateral velocity to the first path to calculate a second path corresponding to a predicted traveling path of the adjacent vehicle.

The present disclosure relates to a method and system for integrated path planning and path tracking control of an autonomous vehicle. The method includes: obtaining five input control variables and eleven system state variables of an autonomous vehicle at current time; constructing a vehicle path planning-tracking integrated state model according to the obtained variables at the current time; enveloping external contours of two autonomous vehicles using elliptical envelope curves to determine elliptical vehicle envelope curves of the two autonomous vehicles, respectively; determining time to collision (TTC) between the vehicles according to elliptical vehicle envelope curves and vehicle driving states; establishing an objective function of a model prediction controller (MPC) according to the model; and solving the objective function based on the TTC, and determining input control variables to the MPC at the next time. Autonomous vehicle collision avoidance can be achieved according to the present disclosure.

A travel assistance method and a travel assistance device for a vehicle is capable of avoiding any risk that may arise. The method includes obtaining a risk potential of an object detected by the vehicle, associating the risk potential of the object with an encounter location at which the object is encountered, accumulating the risk potential at the encounter location, and using the accumulated risk potential to obtain a primary estimated risk potential of the object predicted to be encountered at the encounter location. The primary estimated risk potential is lower than the risk potential obtained when detecting the object. The method further includes obtaining a secondary estimated risk potential using a predicted travel movement of another vehicle that avoids a risk due to the primary estimated risk potential, and when traveling at the encounter location again, autonomously controlling travel of the vehicle using the secondary estimated risk potential.

Enclosed are embodiments for navigation with drivable area detection. In an embodiment, a method comprises: receiving a point cloud from a depth sensor, receiving image data from a camera; predicting at least one label indicating a drivable area by applying machine learning to the image data; labeling the point cloud using the at least one label; obtaining odometry information; generating a drivable area by registering the labeled point cloud and odometry information to a reference coordinate system; and controlling the vehicle to drive within the drivable area.

A travel control apparatus is configured to control a travel of a vehicle so as to travel along a target path. The travel control apparatus is configured to perform: acquiring a change schedule information of a traffic light installed over each of a plurality of merge lanes that merge with a main line and configured to be able to change an indication form between a first indication form permitting the vehicle to merge with the main line and a second indication form instructing the vehicle to stop before a stop line; determining a merge lane on which the vehicle travels among the plurality of merge lanes, based on the change schedule information of a traffic light located in a travel direction of the vehicle; and generating a target path of the vehicle leading to the stop line of the merge lane.

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.