Abstract: A multi-core processor configured to improve processing performance in certain computing contexts is provided. The multi-core processor includes multiple processing cores that implement barrel threading to execute multiple instruction threads in parallel while ensuring that the effects of an idle instruction or thread upon the performance of the processor is minimized. The multiple cores can also share a common data cache, thereby minimizing the need for expensive and complex mechanisms to mitigate inter-cache coherency issues. The barrel-threading can minimize the latency impacts associated with a shared data cache. In some examples, the multi-core processor can also include a serial processor configured to execute single threaded programming code that may not yield satisfactory performance in a processing environment that employs barrel threading.

Abstract: Systems and methods are disclosed for navigating a host vehicle. In one implementation, at least one processor may be programmed to receive an image captured by a camera; identify an oncoming target vehicle; determine that a planned trajectory for the host vehicle includes a turn that crosses a projected trajectory of the oncoming target vehicle in a potential turn-across-path event; determine a driving jurisdiction associated with the road; determine, based on the driving jurisdiction, whether the target vehicle is approaching a road feature that negates the potential turn-across-path event; and either implement or forego implementing a remedial action based on whether the target vehicle is approaching a road feature that negates the potential turn-across-path event.

Abstract: Provided herein are system, apparatus, device, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for predicting a driver path of a vehicle. In the method, an image of a driver of the vehicle is received. Based on the image, a gaze direction of the driver is determined. Based at least in part on the gaze direction, a path of the vehicle is predicted. The vehicle is controlled based on the predicted path.

Abstract: For example, a compiler may be configured to compile a source code into a target code configured for execution by a target processor in a plurality of execution cycles including a first execution cycle, a second execution cycle after the first execution cycle, and a third execution cycle after the second execution cycle. For example, the target code may include one or more no operation (no-op) instructions configured to maintain a first variable live such that a value of the first variable is to be available in a register of the target processor at the first execution cycle and at the third execution cycle.

Abstract: A driver assistance system may also include a driver monitoring system that determines driver awareness. The driver monitoring system may include a camera that observes the driver. According to an embodiment, based on an image captured from the camera, a gaze direction of the driver may be determined. The gaze direction may be evaluated to determine whether it is directed at an object from the vehicle surroundings. If the object is within the driver trajectory, a driver assistance system may recognize that the driver is aware of the object. For that reason, the driver assistance system may delay automatic braking that would otherwise be triggered due to the object.

Abstract: A navigation system for a host vehicle is provided. The system may comprise at least one processing device programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the plurality of images to identify at least one vehicle-induced occlusion zone in an environment of the host vehicle; and cause a navigational change for the host vehicle based, at least in part, on a size of a target vehicle that induces the identified occlusion zone.

Abstract: Provided herein are system, apparatus, device, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for improving object detection based on gaze direction. In the method, a first image of surroundings of a vehicle is received. A second image of a driver of the vehicle is also received. The second image captured contemporaneously with the first image. Based on the second image, a gaze direction of the driver is determined. Based on the gaze direction, a region of the first image being viewed by the driver is determined. An object detection algorithm is applied to recognize an object in the surroundings of the vehicle at a greater level of detail within the region.

Abstract: 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.

Abstract: Embodiments here observe the driver and determine an orientation of an articulating camera based on driver gaze tracking and external object detection. A fixed camera collects image data of the vehicle's surroundings, and an articulating camera collects image data of the driver. The gaze direction is used to identify what objects in the vehicle's surroundings the driver is looking at. Based on the position of the object, an orientation of the articulating camera may be determined.

Abstract: For example, a compiler may be configured to identify a loop nest based on a source code to be compiled into a target code to be executed by a target processor, the loop nest including a plurality of loops including at least a first loop and a second loop nested in the first loop, the first loop including at least one first-loop instruction outside the second loop; and to generate Address Generation Unit (AGU) configuration code to configure an AGU of the target processor based on the first-loop instruction, wherein the AGU configuration code is to configure a first dimension of the AGU based on the first loop and a second dimension of the AGU based on the second loop to configure a memory-access operation based on the first-loop instruction, to be performed at a start of the second loop or at an end of the second loop.

Abstract: A driver assistance system may also include a driver monitoring system that determines driver awareness. The driver monitoring system may include a camera that observes the driver. Embodiments avoid unnecessary lane keeping activity based on where the driver is gazing. For example, if the driver is looking at an adjacent lane, then lane keeping activity to avoid or discourage the vehicle from moving into the adjacent lane may be disabled. And vice-versa, if the vehicle is shifting to adjacent lane in one direction and the driver is gazing at the opposite side, then the lane keeping activity, or at least warning, could be activated earlier.

Abstract: While the cameras used by an ADAS system may provide an unobstructed view of the surroundings, a driver's view may be obstructed. For example, a driver's view could be obstructed by the construction of the vehicle. Analysis may be conducted on the images collected by the ADAS system to identify objects that are in areas where the driver's view is occluded. If the driver's view of the object is occluded, the ADAS may behave differently than it otherwise would if the driver was aware of the object. For example, the ADAS system may apply automatic braking to avoid hitting an object more quickly if the driver cannot see it due to an occlusion.

Abstract: For example, a compiler may be configured to identify a loop nest based on a source code, the loop nest including a plurality of loops, the plurality of loops including at least a first loop and second loop nested in the first loop, wherein the first loop includes at least one first-loop instruction which is outside the second loop, wherein the second loop includes one or more second-loop instructions; to transform the loop nest into a transformed loop, the transformed loop including a conditional instruction based on the first-loop instruction, the conditional instruction based on a state of a second-loop predicate, wherein the second-loop predicate is to identify a start of the second loop or an end of the second loop; and one or more transformed-loop instructions based on the one or more second-loop instructions; and to generate target code based on the transformed loop.

Abstract: For example, a compiler may be configured to identify a plurality of memory-access operations in a loop based on a source code to be compiled into a target code to be executed by a target processor, the plurality of memory-access operations may include at least a first memory-access operation and a second memory-access operation to a same memory pointer. For example, the first memory-access operation may have a first offset, and the second memory-access operation may have a second offset different from the first offset. For example, the compiler may configure Address Generation Unit (AGU) configuration code to configure the plurality of memory-access operations by a same AGU. For example, the compiler may generate the target code based on compilation of the source code. For example, the target code may be based on the AGU configuration code.

Abstract: Techniques are disclosed for performing an image sensor profiling process and accompanying architecture that facilitates performing an image quality measurement over a range of different parameters such as light levels, exposure values, contrast targets, confidence intervals, color ratios, temperature, etc. An image sensor profile may then be generated from these measurements includes an image sensor performance profile dataset. This dataset provides contrast detection probability (CDP) measurement data over a full range of operating parameters of the image sensor. The image sensor performance profile dataset may quantify the image quality and performance for a full range of operation. The image sensor performance profile dataset may be implemented to generate an image sensor model, which may be deployed in a vehicle and used to modify the functions thereof during operation.

Abstract: To receive authority certification for mass deployment of autonomous vehicles (AVs), manufacturers need to justify that their AVs operate safer than human drivers. This in turn creates the need to estimate and model the collision rate (failure rate) of an AV taking all possible errors and driving situations into account. In other words, there is the strong demand for comprehensive Mean Time between Failure (MTBF) models for AVs. The disclosure describes such a generic and scalable model that creates a link between errors in the perception system to vehicle-level failures (collisions). Using this model, requirements for the perception quality may then be derived based on the desired vehicle-level MTBF, or vice versa, to obtain an MTBF value given a certain mission profile and perception quality.

Abstract: For example, a compiler may be configured to identify a first masked memory-access operation based on a source code, wherein the first masked memory-access operation is based on a first mask expression comprising one or more mask leaves: to determine a second masked memory-access operation by reconfiguring the first masked memory-access operation based on an identified mask leaf of the one or more mask leaves, wherein the second masked memory-access operation is based on a second mask expression which is logically simplified compared to the first mask expression; and to generate target code based on compilation of the source code, wherein the target code is based on the second masked memory-access operation.

Abstract: For example, a compiler may be configured to identify a select instruction in a loop operation based on a source code, the select instruction to select between a first value and a second value according to a mask in the select instruction: to configure a masked operation in the loop operation based on the select instruction, wherein the masked operation is based on the mask in the select instruction, the masked operation including a passthrough value based on the second value; and to generate target code based on compilation of the source code, wherein the target code is based on the masked operation.

Abstract: For example, a compiler may be configured to identify a first data operation and a second data operation, which are executable in parallel according to a SIMD instruction to be executed by a single ALU of a target processor: to determine a selected compilation scheme from a first compilation scheme and a second compilation scheme based on a predefined selection criterion, wherein the first compilation scheme includes compilation of the first data operation and the second data operation into the SIMD instruction, wherein the second compilation scheme includes compilation of the first data operation into a first ALU instruction, and compilation of the second data operation into a second ALU instruction to be executed separately from the first ALU instruction; and to generate target code based on compilation of the first data operation and the second data operation according to the selected compilation scheme.

Abstract: A system for correlating drive information from multiple road segments is disclosed. In one embodiment, the system includes memory and a processor configured to receive drive information from vehicles that traversed a first road segment and vehicles that traversed a second road segment. The processor is configured to correlate the drive information from the vehicles to provide a first road model segment representative of the first road segment and a second road model segment representative of the second road segment. The processor correlates the first road model segment with the second road model segment to provide a correlated road segment model if a drivable distance between a first point associated with the first road segment and a second point associated with the second road segment is less than or equal to a predetermined distance threshold, and stores the correlated road segment model as part of a sparse navigational map.