A cruise control system is provided with the ability to inhibit operation of a cruise control resume function which returns a vehicle to a target vehicle speed. The resume inhibition is inhibited when values of vehicle parameters exceed threshold values, such as a road wheel angle being greater than a threshold angle, detection of an object such as another vehicle adjacent to the vehicle, and/or a vehicle speed being lower than a threshold speed. The ability to inhibit the cruise control resume function enhances safety by avoiding unexpected or otherwise undesired vehicle acceleration when the steering wheels turned at a large angle and an adjacent object is present, thereby minimizing the chances of the turning vehicle colliding with the adjacent object.

A work vehicle includes a first detection unit that detects an optical beam emitted from a beam projector disposed at one end of a reference travel path, a first position deviation calculation section that calculates position deviation by a vehicle body from the reference travel path based on a detection signal from the first detection unit, a second detection unit that detects a work boundary line that occurs due to work travel, a second position deviation calculation section that calculates position deviation of the vehicle body traveling along successive travel paths from the work boundary line based on a detection signal from the second detection unit, and a steering information generation section that, based on the position deviation calculated by the first position deviation calculation section and the second position deviation calculation section, generates steering information for correcting the position deviation.

The present disclosure provides a method, an apparatus, a device and a readable storage medium for planning a pass path. The method includes: acquiring current road environment information in front of a vehicle; setting pass candidate points according to the current road environment information and a driving strategy; and determining a current optimal passable path according to the pass candidate points. Since the pass candidate points are set according to the current road environment information and the driving strategy, and the current optimal passable path is determined according to the pass candidate points, thereby effectively decreasing the calculation amount of the impassable path calculation in prior art due to direct setting of pass candidate points in all areas in front of an unmanned vehicle.

An in-vehicle data collection and processing device receives real-time data from a plurality of sensors relating to at least one of a current vehicle condition and a current driver condition. The device then predicts, by processing at least a portion of the real-time data through a pre-trained pattern recognition algorithm, a likelihood of occurrence of at least one of a plurality of incidents involving the vehicle. In response, the device outputs one or more types of warnings and/or conducts a vehicle evasive maneuver if the likelihood is predicted to be above one or more thresholds.

A method is provided for danger prediction. The method includes generating fully-annotated simulated training data for a machine learning model responsive to receiving a set of computer-selected simulator-adjusting parameters. The method further includes training the machine learning model using reinforcement learning on the fully-annotated simulated training data. The method also includes measuring an accuracy of the trained machine learning model relative to learning a discriminative function for a given task. The discriminative function predicts a given label for a given image from the fully-annotated simulated training data. The method additionally includes adjusting the computer-selected simulator-adjusting parameters and repeating said training and measuring steps responsive to the accuracy being below a threshold accuracy. The method further includes predicting a dangerous condition relative to a motor vehicle and providing a warning to an entity regarding the dangerous condition by applying the trained machine learning model to actual unlabeled data for the vehicle.

A method for detecting an obstacle along a known path of a machine can include relating the location of the machine with a map. The map can include a worksite with a known path or known paths that the machine can travel on. The stopping distance of the machine can be determined and based on these identified known path and its characteristics along with a traveling speed and a weight of the machine. A LIDAR region of interest can be determined based on the stopping distance, the position and orientation of the machine, and characteristics of the known path. The machine can include a LIDAR system that can be configured to be oriented with respect to the LIDAR region of interest. A concentrated LIDAR scan can be performed to detect if an obstacle is present within the LIDAR region of interest.

A control device (100) can communicate with a first sensor (300) for detecting an object around a first vehicle and is equipped on the first vehicle (500). The control device (100) includes a first acquisition unit, a second acquisition unit, a detection unit, and a determination unit. The first acquisition unit acquires a sensing result being a result of detecting an object around the first vehicle (500) from the first sensor (300) equipped on the first vehicle (500). The second acquisition unit acquires positional information of a specified object being an object for performance measurement of the first sensor (300). The detection unit detects the specified object existing within a reference distance from the first vehicle (500), by use of positional information of the first vehicle (500) and positional information of the specified object. The determination unit determines performance of the first sensor (300), based on the sensing result of the specified object by the first sensor (300).

The present teaching relates to method, system, and medium, for operating a vehicle. The method includes the steps of receiving Real-time data related to the vehicle are received. A current mode of operation of the vehicle is determined. A first risk associated with the current mode of operation of the vehicle is evaluated based on the real-time data in accordance with a risk model. If the first risk satisfies a first criterion, a second risk associated with switching the current mode to a different mode of operation of the vehicle is determined. The vehicle is switched from the current mode to the different mode if the second risk satisfies a second criterion.

Systems and methods for providing illumination-based object tracking information within a host vehicle. In some embodiments, the system may comprise a remote object detection module and an illumination display pattern within the vehicle comprising one or more light sources defining a pattern. The illumination display pattern may be configured to dynamically change in accordance with one or more objects being detected and/or tracked by the remote object detection module to convey visible information to vehicle occupants regarding such object(s).

A vehicle computer comprises a processor and a memory. The memory stores instructions executable by the processor to detect debris flying above a roadway, to input vehicle sensor data to a first classifier that outputs a source of the debris, and based on the source of the debris, to compare sensor data representing the debris to stored reference data to determine a type of physical material included in the debris. The memory stores instruction to input the type of physical material and an environmental condition to a second classifier that outputs a risk assessment, and to actuate the vehicle based on the risk assessment.