The present invention relates to methods of predicting risk of collision depending on the behavior of a pedestrian adjacent to a driving vehicle and controlling the vehicle for preventing collision. According to an embodiment of the present invention, a method of controlling a vehicle comprises identifying a pedestrian adjacent to a driving road of the vehicle, determining a first recognition value of the pedestrian for the vehicle based on a behavior feature of the pedestrian, outputting a warning signal based on the first recognition value, determining a second recognition value of the pedestrian after outputting the warning signal, and controlling the vehicle based on the second recognition value.

A method for improving pedestrian safety is provided. The method includes determining operating conditions of a vehicle using a plurality of vehicle sensors. A path of the vehicle is predicted based on the determined operating conditions. Pedestrian parameters for a pedestrian in a vicinity of the vehicle are acquired using the plurality of vehicle sensors. The pedestrian parameters include at least one of a position, a speed of the pedestrian, gait, body posture and a level of distractedness. A determination is made whether a notification of the pedestrian is necessary based on the determined vehicle operating conditions and the acquired pedestrian parameters. A mode of notification of the pedestrian is selected from a plurality of modes of notification, in response to determining that the notification of the pedestrian is necessary. The pedestrian is notified using the selected mode of notification.

Methods, systems, and apparatus for generating trajectory predictions for one or more agents. In one aspect, a system comprises one or more computers configured to obtain scene context data characterizing a scene in an environment at a current time point, where the scene includes multiple agents. The one or more computers process the scene context data using a marginal trajectory prediction neural network to generate a respective marginal trajectory prediction for each of the plurality of agents that defines multiple possible trajectories for the agent after the current time point and a respective likelihood score for each of the multiple possible future trajectories. The one or more computers can generate graph data based on the respective marginal trajectory predictions, and the one or more computers can process the graph data using a graph neural network to generate a joint trajectory prediction output for the multiple agents in the scene.

Apparatuses, systems, and methods are provided for the utilization of vehicle control systems to cause a vehicle to take preventative action responsive to the detection of a near short term adverse driving scenario. A vehicle control system may receive information corresponding to vehicle operation data and ancillary data. Based on the received vehicle operation data and the received ancillary data, a multi-dimension risk score module may calculate risk scores associated with the received vehicle operation data and the received ancillary data. Subsequently, the vehicle control systems may cause the vehicle to perform at least one of a close call detection action and a close call detection alert to lessen the risk associated with the received vehicle operation data and the received ancillary data.

Control commands in a system and method for autonomously driving a vehicle or partially autonomously driving a vehicle are generated on the basis of an environment representation, which is generated from sensor signal of a sensing means. The environment representation where ambiguous objects are identified is such that information obtained from the driver of the vehicle are added. The system generates an information request. Additional information is extracted and accumulated in the environment representation map. Traffic is then determined and suitable control signals for the vehicles are generated. In case no ambiguous objects are included in the environment representation but the system is not capable of deciding on traffic, the driver is asked to disambiguate the situation or to instruct on dealing with the traffic.

An image processing device applied to a driving assistance system, which includes: a driving assistance device that detects a relative position of a lane marking with respect to a vehicle and assists a driving of the vehicle based on a detected positional information; and a head-up display device that projects a display image on a projection area arranged on the vehicle to visually recognize a virtual image of the display image, includes: an acquisition device that acquires the positional information; and a generation device that generates the display image including a predetermined display element. The generation device generates the display image to visually recognize the display element at a position associated with the positional information and to visually recognize the display element as a shape inclined toward the vehicle from the lane marking.

Methods and systems for autonomous vehicle recharging or refueling are disclosed. Autonomous electric vehicles may be automatically recharged by routing the vehicles to available charging stations when not in operation, according to methods described herein. A charge level of the battery of an autonomous electric vehicle may be monitored until it reaches a recharging threshold, at which point an on-board computer may generate a predicted use profile for the vehicle. Based upon the predicted use profile, a time and location for the vehicle to recharge may be determined. In some embodiments, the vehicle may be controlled to automatically travel to a charging station, recharge the battery, and return to its starting location in order to recharge when not in use.

Disclosed is a detection system and a detection method for detecting external environment information of a vehicle. The detection system includes at least two groups of vehicle-mounted modules (200) arranged on different vehicles, wherein each of the vehicle-mounted modules (200) includes: at least one sensor (201), configured to acquire distance information between the vehicle and a target; a processing unit (202), configured to establish a reference coordinate system by taking the vehicle as a center and perform calculation according to a detection direction of the sensor (201) and the distance information to obtain coordinates of the target in the reference coordinate system; a communication unit (203), configured to receive target positioning information of other vehicles transmitted by a communication unit (203) of at least one of other vehicle-mounted modules (200); and the processing unit (202) generates the external environment information of the vehicle in combination with target positioning information of the vehicle and the target positioning information of at least one of other vehicles. The system overcomes the limitation that a single vehicle independently acquires the external environment information, thereby accurately detecting the external environment information of the vehicle.

A driving control apparatus for a vehicle is disclosed. The driving control apparatus includes: an object detection device configured to detect objects in the vicinity of the vehicle and generate information on the objects; a sensing unit configured to detect a state of the vehicle and generate vehicle state information; and a processor configured to: based on the vehicle state information and the information on the objects, generate information on collision with a first object out of the objects, and based on the information on the collision, generate a control signal for at least one of steering, partial braking, and partial driving of the vehicle and provide the generated control signal so as to control operation of the vehicle after the collision through at least one of a steering control action, a partial braking control action, and a partial driving control action.

An object detection device detects an object moving in the area surrounding an own object. The object detection device includes: an information obtainment unit which obtains an object speed value that is at least one of a speed and an acceleration of the object in a lateral direction which is orthogonal to a predetermined direction of the area surrounding the own object; and an upper limit setting unit which sets an upper limit of the object speed value on the basis of angle information that is the relationship indicating an angle of a moving direction of the object with respect to the predetermined direction.