An object detection system may generate regions of interest (ROIs) from an input image that can be processed by a wide range of object detectors. According to the techniques described herein, an image is processed by a light-weight neural network (e.g., a heatmap network) that outputs object center and object scale heat-maps. The heatmaps are processed to define ROIs that are likely to include objects. Overlapping ROIs are then merged to reduce the aggregate size of the ROIs, and merged ROIs are downscaled to a reduced set of pre-defined resolutions. Fully-convolutional, high-accuracy object detectors may then operate on the downscaled ROIs to output accurate detections at a fraction of the computations by operating on a reduced image. For example, fully-convolutional, high-accuracy object detectors may operate on a subset of the entire image (e.g., cropped images based on ROIs) thus reducing computations otherwise performed over the entire image.

Systems and methods use cameras to provide autonomous navigation features. In one implementation, a driver-assist object detection system is provided for a vehicle. One or more processing devices associated with the system receive at least two images from a plurality of captured images via a data interface. The device(s) analyze the first image and at least a second image to determine a reference plane corresponding to the roadway the vehicle is traveling on. The processing device(s) locate a target object in the first two images, and determine a difference in a size of at least one dimension of the target object between the two images. The system may use the difference in size to determine a height of the object. Further, the system may cause a change in at least a directional course of the vehicle if the determined height exceeds a predetermined threshold.

The present disclosure relates to a driving control apparatus, a driving control method, and a program that can resolve a conflict between a deliberate action and a reflex action during determination of a next action in autonomous driving. During autonomous driving, a reflex action is determined as a simplified action on the basis of detection results detected by a variety of sensors provided in a vehicle, and a deliberate action ranked higher than a reflex action is determined through elaborate processing. A plurality of resolution modes are made available to deal with a possible conflict between the reflex action and the deliberate action, and by which of the resolution modes the conflict is resolved is specified in advance so that the conflict is resolved by the specified resolution mode. The present disclosure is applicable to motor vehicles that drive autonomously.

A method for operating a partially autonomous motor vehicle, wherein in a non-parked state of the motor vehicle, sensor data of a sensor device, which detects at least one person in the surroundings of the motor vehicle, are analyzed with respect to a behavior of the person disadvantageously impairing the further driving operation of the motor vehicle and at least one action counteracting the behavior of the person is triggered in dependence on the analysis result.

A vehicular parking system includes a plurality of exterior viewing cameras, at least one receiver and a control. The control, when the vehicle is located at an entrance of a parking structure, controls the vehicle to autonomously drive the vehicle from the entrance of the parking structure toward a parking location in the parking structure. The parking structure includes a positioning system having a plurality of short range communication devices at known locations at the parking structure. Responsive to communication signals generated by the devices, the control determines the location of the vehicle relative to the known locations and drives the vehicle from the entrance of the parking structure toward the parking location in the parking structure. With the vehicle positioned at the parking location, and responsive at least to image processing by the image processor of captured image data, the control parks the vehicle in the parking location.

An accident liability tracking system includes a processing device programmed to receive, from an image capture device, an image representative of an environment of the host vehicle, to analyze the image to identify a target vehicle in the environment of the host vehicle, and determine one or more characteristics of a navigational state of the target vehicle. The device is further programmed to compare the characteristics of the navigational state of the target vehicle to at least one accident liability rule, store one or more values indicative of potential accident liability on the part of the identified target vehicle based on the comparison of the characteristics of the navigational state of the identified target vehicle to the at least one accident liability rule, and output the one or more values, after an accident between the host vehicle and a target vehicle, for determining liability for the accident.

A surrounding environment of an autonomous vehicle is perceived to identify one or more vehicles nearby. For each of the identified vehicles, based on a current location of the identified vehicle, vehicle-independent information is obtained to determine context surrounding the identified vehicle, where the vehicle-independent information includes vehicle surrounding information that defines physical constraints imposed on the identified vehicle. For each of the identified vehicles, one or more trajectories for the identified vehicle are predicted based at least in part on the vehicle-independent information associated with the identified vehicle. The autonomous vehicle is controlled based on the one or more predicted trajectories of the one or more identified vehicles.

A real-world vehicle includes multiple data sources that generate sensor data that is spatially-mapped to a real-world region; a data fusion system is configured to fuse or integrate (i) the spatially-mapped sensor data with (ii) virtual data, that has been generated outside of the vehicle or generated independently of the operation of the vehicle, and is spatially-mapped to a virtual world. This enables a fusion of the real and virtual worlds which enables a self-driving car to interact not only with the physical world but also to virtual objects introduced into the path of the car (e.g. by a test or development engineer) to test how well the car and its autonomous driving systems cope with the virtual object.

A collision-avoidance system for use with an autonomous-capable vehicle can continuously receive image frames captured of the roadway to determine drivable space in a forward direction of the vehicle. The system can determine, for each image frame, whether individual regions of the image frame depict drivable space. The system can do so using machine-learned image recognition algorithms such as convolutional neural networks generated using extensive training data. Using such techniques, the system can label regions of the image frames as corresponding to drivable space or non-drivable space. By analyzing the labeled image frames, the system can determine whether the vehicle is likely to impact a region of non-drivable space. And, in response to such a determination, the system can generate control signals that override other control systems or human operator input to control the brakes, the steering, or other sub-systems of the vehicle to avoid the collision.

The invention relates to a method for recognizing a potential collision of a vehicle with a living creature, wherein at least one operating state is monitored of a functional unit in a parking garage in which the vehicle is located, wherein when such a characteristic operating state of the functional unit is recognized by a monitoring device that characterizes a direct, potential appearance of a living creature in the parking garage, a notice is transmitted to the vehicle, and/or an operating mode of the vehicle is changed. The invention also relates to a parking garage management system.