42results about "Automatic control systems" patented technology

The embodiment of the invention provides a vehicle control method which comprises the steps that first road condition data and second road condition data of a preset road are obtained, the first road condition data are from a platform data source, and the second road condition data are from a vehicle-mounted data source; performing risk classification processing based on the first road condition data to obtain a target risk type of the preset road; determining a target risk level corresponding to the target risk type based on the second road condition data; based on the target risk type and the corresponding target risk level, determining a target driving strategy when driving on the preset road; and performing driving control on the vehicle based on the target driving strategy. Due to the fact that the first road condition data of the platform data source and the second road condition data of the vehicle-mounted data source are integrated, the road condition of an emergency can be obtained in advance, the corresponding driving strategy is determined, prospective vehicle control is achieved, and the response speed during vehicle control can be increased.

The disclosed technology teaches a system and method for providing driver assistance alerts to a driver using an end-to-end artificial intelligence advanced driver assistance system. The disclosed techniques further include receiving a series of environmental data of a driving state including at least video from a camera, return data from an optical sensor, and location data from a GNSS receiver, where the camera, the optical sensor, and the GNSS receiver are coupled to a processor carried by a vehicle; processing the environmental data as input to an end-to-end neural network, wherein the end-to-end neural network is trained to generate specified steering and speed control actions in response to a current driving state; analyzing hidden layer data and output data from the end-to-end neural network to estimate collision avoidance data; and presenting to the driver a user interface including a driver assistance alert based on the collision avoidance data.

A computer-implemented method for verifying a software-based behavior planner of an automated driving function. The method includes: providing a verification environment model to limit the state space of the behavior planner according to a specifiable traffic scene; providing a formal requirement as a criterion for the correctness of decisions of the behavior planner; generating a model checker representation of the behavior planner taking into account the provided verification environment model; analyzing the model checker representation using a model checking procedure with respect to the formal requirement. The verification environment model is used to determine a physically meaningful parameter interval for at least one location parameter and / or movement parameter of the participants of the given traffic scene. The model checking procedure systematically samples the parameter interval and thus checks the behavior planner for a representative selection of the possible temporal and spatial developments of the given traffic scene.

A method of coordinating road users via a server device which determines instruction data by a central model and transmits the instruction data as action instruction to respective control circuits of the road user, the central model being a virtual image of a real environment created by the server device from environment data, includes when a road user reaches the real environment a local model is created by onboard sensor data and delta data relating to the central model is determined. The delta data is transmitted to the server device by the control circuit of the road user which creates an updated central model by the delta data and the central model. The server device determines and transmits updated instruction data to the road user as readjustment of the instruction data.

An approach for operating a motor vehicle that is designed for an autonomous and / or partially autonomous driving operation in which the motor vehicle is moved along a predetermined driving trajectory. During the autonomous or partially autonomous driving operation, a driving trajectory running centrally or substantially centrally along the lane traveled is shifted to the edge of the lane on the basis of lane information describing the lane currently traveled by the motor vehicle, and on the basis of speed information describing a current speed of the motor vehicle, and on the basis of at least one piece of traffic information describing a current traffic volume in the surroundings of the motor vehicle. Alternatively, or in addition, the motor vehicle is stopped before a bottleneck or an intersection is entered on the basis of road-course information describing the bottleneck or the intersection along the road course to be traveled, and additionally on the basis of emergency vehicle information describing the presence of an emergency vehicle in the surroundings of the motor vehicle, and / or on the basis of accident information describing an accident along the road course to be traveled.

The present invention provides a vehicle driving assistance device that can prevent the vehicle's speed from temporarily falling below the legal minimum speed, even when performing driving assistance control that allows the vehicle to coast. [Solution] The vehicle driving support device 10 performs a first driving support control to drive the vehicle 100 by autonomously alternating between accelerating and coasting the vehicle so that the vehicle's speed is maintained within a range between a target upper speed and a target lower speed. The vehicle driving support device sets the target upper speed by adding a predetermined upper limit to the set vehicle speed set by the vehicle's user as the target value for the vehicle's speed, and sets the target lower speed by subtracting a predetermined lower limit from the set vehicle speed. When the first driving support control is executed, if the target lower speed is lower than the legally mandated minimum speed applicable to the vehicle, the predetermined lower limit is changed so that the target lower speed is equal to or greater than the legally mandated minimum speed.

The technology disclosed teaches a system and methods for providing driver assistance alerts to a driver using an end-to-end artificially-intelligent advanced driver assistance system. The technology disclosed further includes receiving environmental data for a sequence of driving states including at least video from a camera, returns from an optical sensor, and location data from a GNSS receiver, wherein the camera, the optical sensor, and the GNSS receiver are coupled to a processor carried by a vehicle, processing the environmental data as input to an end-to-end neural network, wherein the end-to-end neural network is trained to generate prescriptive steering and speed control actions in response to a present driving state, analyzing hidden layer data and output data from the end-to-end neural network to estimate collision avoidance data, and presenting, to the driver, a user interface including driver assistance alerts based on the collision avoidance data.

A system for providing an output signal based on a generated surroundings model of surroundings of a mobile platform is proposed. The system includes: a first subsystem, a second subsystem, wherein the second subsystem is configured to redundantly provide a functionality of the first subsystem, and a third subsystem, wherein the third subsystem is configured to redundantly provide the functionality of the first subsystem and / or of the second subsystem; a first comparison system, a second comparison system, wherein the first comparison system and / or the second comparison system are configured to detect at least one fault in the first subsystem and / or a fault in the second subsystem and / or a fault in the third subsystem and / or to identify the corresponding faulty subsystem.

Drive control device (1) for providing drive control for a hybrid vehicle by controlling a machine (2) and motor-generators (4, 5) which can be operated to output a charge of electrical power to a battery (21) and to receive a supply of electrical power from the battery (21) to supply the hybrid vehicle with a motive force obtained from the machine (2) and the motor-generators (4, 5), wherein the drive control device has a power sharing and composition system having four axes connected to each of the rotating elements of the two planetary gear sets (8, 9); wherein two motor generators (4, 5) are connected to the battery (21); wherein one of the motor generators (4, 5), the machine (2), a drive shaft (7) connected to a traction wheel (6), and the other of the motor generators (4, 5) lie on a collinear diagram, wherein the four axes of the power sharing and composition system are each connected to one motor generator (4, 5), the machine (2), the drive shaft (7), and the other motor generator (4, 5); the drive control device further comprises the following: a drive power target calculation function (42) for calculating a drive power target based on an accelerator pedal position and a vehicle speed; a charge / discharge power target calculation function (43) for calculating an electrical charge / discharge power target to / from the battery (21) based on a charge / discharge state of the battery (21); a first machine power target calculation function (44) for calculating a first machine power target based on the drive power target calculated by the drive power target calculation function (42) and the electrical charge / discharge power target calculated by the charge / The discharge power target calculation function (43) is calculated; a first machine operating point target calculation function (46) for calculating a first machine speed target and a first machine torque target, both of which correspond to the first machine power target calculated by the first machine power target calculation function (44), based on information about a machine operating point identified by a relationship between a machine speed and a machine torque; a first calculation function (47) for an upper machine speed target limit for calculating an upper limit of the first machine speed target based on the vehicle speed, wherein the upper limit of the machine speed is limited by an upper limit of the speed of one motor-generator (4, 5) and is subject to changes depending on the vehicle speed, and wherein the calculation function (47) of the upper first machine speed target limit calculates the upper limit of the first machine speed target based on the vehicle speed and the upper limit of the speed of one motor-generator (4, 5); a machine operating point target calculation function (48) to determine whether the first machine speed target calculated by the first machine operating point target calculation function (46) is greater than the upper limit, wherein the machine operating point target calculation function (48) is designed to: to set a second machine speed target to the upper limit and to calculate a second machine torque target corresponding to the second machine speed target, based on the information about the machine operating point, when it is determined that the first machine speed target calculated by the first machine operating point target calculation function (46) is greater than the upper limit; and to set the second machine speed target and the second machine torque target as the first machine speed target and as the first machine torque target if it is determined that the first machine speed target calculated by the first machine operating point target calculation function (46) is less than or equal to the upper limit; a second machine power target calculation function (49) for calculating a second machine power target based on the second machine speed target and the second machine torque target; a calculation function (50) for an electrical power target for calculating an electrical power target that specifies an amount of electrical power to be generated by driving the motor generators (4, 5) to charge the battery (21), or to be supplied from the battery (21) to the motor generators (4, 5) to drive the motor generators (4, 5), based on a difference between the drive power target calculated by the drive power target calculation function (42) and the second machine power target calculated by the second machine power target calculation function (49); a machine control (40) that is configured to to control a moment of the machine (2) based on the second machine moment target; and a motor-generator control unit (60) configured to control the motor-generators (4, 5) based on the second machine speed target, the second machine torque target, and the electrical power target.

A vehicle driving assistance apparatus executes a first driving assistance control of causing a host vehicle to travel by autonomously repeating powering and coasting of the host vehicle alternately such that a traveling speed of the host vehicle is maintained within a range between target upper and lower limit speeds. The apparatus sets a speed obtained by adding a predetermined upper limit variation amount to a set vehicle speed as the target upper limit speed, and sets a speed obtained by subtracting a predetermined lower limit variation amount from the set vehicle speed as the target lower limit speed. When the target lower limit speed is lower than a legal minimum speed during execution of the first driving assistance control, the apparatus changes the predetermined lower limit variation amount such that the target lower limit speed is equal to or higher than the legal minimum speed.

The embodiment of the invention provides an intelligent driving control method, electronic equipment, a storage medium and a program product. The method comprises the following steps: determining a current driving scene of a vehicle according to running state data, environment sensing data and navigation data of the vehicle; under the condition that the current driving scene meets the scene switching condition, target configuration parameters of the intelligent driving function are determined based on the current driving scene; the target configuration parameters comprise state parameters and target control parameters; and according to the state parameters and the target control parameters, current configuration parameters of the intelligent driving function are adjusted. The method is used for flexibly distributing the computing power based on the driving scene, and the effect of improving the response efficiency of intelligent driving under the condition of avoiding the waste of the computing power is achieved.

Provided is a vehicle driving assistance device that can prevent the driving speed of a host vehicle from temporarily falling below a legal minimum speed while performing driving assistance control for inertial running of the host vehicle. A vehicle driving assistance device (10) performs first driving assistance control for causing a host vehicle (100) to run by autonomously alternately repeating powered running and inertial running of the host vehicle in such a way as to maintain the running speed of the host vehicle within a range between an upper target speed and a lower target speed. The vehicle driving assistance device sets, as the upper target speed, a speed obtained by adding a predetermined upper limit amplitude to a set speed set as a target value for the running speed of the host vehicle by a user of the host vehicle, and sets, as the lower target speed, a speed obtained by subtracting a predetermined lower limit amplitude from the set speed, and changes the predetermined lower limit amplitude so that the lower target speed is equal to or higher than a legal minimum speed applied to the host vehicle when the lower target speed is lower than the legal minimum speed applied to the host vehicle while the first driving assistance control is being performed.

An object recognition apparatus may include a sensor, configured to obtain a point cloud associated with an object, and a processor. The processor may be configured to divide, based on a size of the point cloud, a specified space into a plurality of subspaces. The point cloud may be projected into the specified space. The specified space may include a plurality of voxels included in the plurality of subspaces. The processor may be further configured to identify, among the plurality of voxels and based on sequentially exploring the plurality of voxels, one or more valid voxels that include at least a part of the point cloud; assign, to the one or more valid voxels, at least one index; recognize, based on the one or more valid voxels and the at least one index, the object; and control, based on the recognized object, an operation of a vehicle.

This document describes techniques and systems for associating measurement points to spline points in determining a free space boundary for a vehicle assistance system. An exemplified method includes obtaining a set of measurement points that define a subset of a free space boundary near a host vehicle. A parametric curve that approximates spatial information representing the free space boundary is also obtained. The parametric curve includes a plurality of spline samples. The method then includes determining, for each respective spline point of the plurality of spline samples, a respective measurement point of the set of measurement points that corresponds to the respective spline point. In this way, a more efficient technique is disclosed for a vehicle assistance system to associate measurement points to spline points that make up a parametric-curve representation of the free space boundary.

A system (10) for operating an autonomous vehicle includes a passenger-detector (18) and a controller-circuit (32). The passenger-detector (18) is operable to determine a passenger-count (20) of passengers (22) present in a host-vehicle (12). The controller-circuit (32) is in communication with the passenger-detector (18) and vehicle-controls (26) of the host-vehicle (12). The controller-circuit (32) is configured to operate the host-vehicle (12) in an autonomous-mode (14) and in accordance with a parameter (40). The parameter (40) is set to an empty-value (46) when passenger-count (20) is equal to zero, and the parameter (40) is set to an occupied-value (48) different from the empty-value (46) when the passenger (22) count is greater than zero.

A method and system include receiving a request for autonomous parking of a vehicle; upon receiving the request, obtaining information as to a plurality of potential parking spots, including as to their respective effects on a temperature of the vehicle; selecting, via a processor of the vehicle, one of the plurality of potential parking spots as a selected parking spot for the vehicle, based on the information, including the respective effects on the temperature of the vehicle; and autonomously parking the vehicle in the selected parking spot, in accordance with instructions provided by the processor.

Techniques are disclosed for performing hybrid simulation operations with an autonomous vehicle. A method of testing autonomous vehicle operations includes receiving, by a computer, a pre-configured scenario that includes one or more simulation parameters and one or more initial condition parameters, sending, to the autonomous vehicle and based on the one or more initial condition parameters, control signals that instruct the autonomous vehicle to operate at an operative condition, and in response to determining that the autonomous vehicle is operating at the operative condition, performing a simulation with the one or more simulated objects and the autonomous vehicle to test a response of the autonomous vehicle.

An autonomous or semi-autonomous vehicle (104) may improve the overall safety of other vehicles by determining an action of a proximate vehicle (102) based on sensor data and determining one or more expected visual cues associated with the determined action. One or more images of the proximate vehicle may then be used to detect a difference between expected visual cues and the captured images. Detected differences may be used to notify one or more entities (116) that can then take corrective actions.

The invention discloses a vision-language-action model-based complex road semantic event-driven intelligent chassis pre-adjustment control method, system and device and a storage medium, and belongs to the technical field of automatic driving vehicle control and intelligent chassis cooperative control. The method comprises the following steps: acquiring vehicle-related information; performing multi-modal fusion coding on the information obtained in the step S1; generating a chassis pre-adjusting intention; a dynamic advance model is constructed, and whether chassis pre-adjustment is triggered or not is judged; after chassis pre-adjustment is triggered, a chassis pre-adjustment target is generated; executing chassis parameter presetting, mode pre-switching and actuator pre-loading; the chassis control process enters an event period active control stage; and the chassis control process enters a recovery and strategy updating stage. According to the method, vision-language-action driven semantic reasoning and chassis active pre-adjustment of a complex road semantic event are realized, and the comfort, the handling stability and the safety of an automatic driving vehicle in a complex road environment are improved.

A vehicular multi-sensor sensing system includes a plurality of sensors disposed at an equipped vehicle and sensing forward of the vehicle. Data based at least in part on processing of sensor data captured by at least one of the sensors is wirelessly transmitted from the equipped vehicle to a remote server. The wirelessly transmitted data is conjuncted to a current geographic location of the equipped vehicle along a road being travelled by the equipped vehicle. The remote server merges data wirelessly transmitted from the equipped vehicle to the remote server with data wirelessly transmitted from a plurality of other vehicles traveling along the road along which the equipped vehicle is traveling, and processes the merged data to determine at least one characteristic along the road being travelled by the equipped vehicle.

An example method includes (a) obtaining sensor data descriptive of an environment of an autonomous vehicle; (b) obtaining a plurality of travel way markers from map data descriptive of the environment; (c) determining, using a machine-learned object detection model and based on the sensor data, an association between one or more travel way markers of the plurality of travel way markers and an object in the environment; and (d) generating, using the machine-learned object detection model, an offset with respect to the one or more travel way markers of a spatial region of the environment associated with the object.

An exemplary aspect of the present disclosure relates to an exemplary computer-implemented method for predicting the intentions of actors in an environment. The exemplary method includes obtaining state data related to a plurality of actors in the environment and map data representing a plurality of lanes in the environment. The method includes determining a plurality of potential goals for each actor based on the state data and the map data. The method includes processing the state data, the map data, and the plurality of potential goals with a machine learning predictive model to determine (i) predicted goals for each actor of the plurality of actors, (ii) predicted interactions between each actor of the plurality of actors and other actors based on the predicted goals, and (iii) continuous trajectories for each actor based on the predicted goals.

The invention concerns a method for controlling a vehicle which can determine if the vehicle is located on a railway crossing and depending on the vehicle's speed or driving direction generate actions. The method comprises the steps to determine if the vehicle is located on a railway crossing; determine if the vehicle speed is below a threshold or if the vehicle is reversing; based on the combined outcome of the determinations, generate a vehicle control signal and / or generate a user information output. The invention further concerns a vehicle control system and an advanced driver assistance system.

Driving assistance device (10) which is mounted in a vehicle (1) to assist a driver during a journey of the vehicle (1) by detecting a state of the driver, wherein the vehicle (1) is between a manual driving mode in which driving operations for acceleration, braking and steering are performed manually by the driver, and an automated driving state in which at least one of the driving operations is carried out automatically, is interchangeable, wherein the driving assistance device (10) comprises: a driver state monitoring unit (120) that detects whether the driver's state is an inattentive state; an alarm unit (140) which, when the driver's inattentive state is detected, alerts the driver; a driving unit (500) operated by the driver to carry out the driving operations; and a driving state change unit (130) which, when the driver operation of the driving operation unit (500) is detected during the automated driving state of the vehicle (1), changes at least one of the driving operations in the automated driving state to the manual driving state, where when at least one of the driving modes in the automated driving state is switched to the manual driving state by the driving state change unit (130), the driver state detection unit (120) detects whether the driver's state is an agitated state; and If the driver's agitated state is detected, the alerting unit (140) will alert the driver.

In a vehicle control device 100, a rough-road travel unit 1008 determines whether or not there is a rough road within a predetermined range in front of a vehicle based on a position of the vehicle estimated by a position estimation unit 1001 and a position of a rough road acquired by a map information acquisition unit 1011, and determines whether or not the rough road has been detected based on road surface information acquired by an outside environment information acquisition unit 1002. When it is determined that there is the rough road within the predetermined range in front of the vehicle based on the position of the vehicle estimated by the position estimation unit 1001 and the position of the rough road acquired by the map information acquisition unit 1011, and it is determined that the rough road is not detected based on the road surface information acquired by the outside environment information acquisition unit 1002, a rough-road detection-omission determination unit 1006 determines whether or not rough-road detection is omitted based on the position of the rough road and a detectable section of a stereo camera 200.

An electronic instrument includes a first distance information acquisition unit acquiring first distance information corresponding to an object included in an image signal, at least one of a second distance information acquisition unit acquiring second distance information on the basis of at least one of information of an end position of the object included in the image signal and a third distance information acquisition unit configured to acquire third distance information based on information of a size of the object included in the image signal, and a distance information integration unit generating integrated distance information by combining and integrating at least two of the first distance information, the second distance information, and the third distance information.

The invention discloses an intelligent chassis unified control method, system and device based on a vision-language-action model and dynamic feasible region projection and a storage medium, and belongs to the technical field of automatic driving and vehicle intelligent control. The method comprises the steps of S1, scene and chassis state acquisition; s2, unified semantic representation generation; s3, outputting high-level chassis behavior semantics; s4, generating an intermediate action description; s5, generating a dynamic feasible region; s6, correcting the reference projection of the target chassis; s7, unified control and control distribution; and S8, outputting cooperation and closed-loop updating. According to the method, an intermediate action description and dynamic feasible region projection mechanism is introduced between the VLA high-level semantic decision and the intelligent chassis low-level control, so that the control implementability, safety, stability, interpretability and multi-actuator cooperative control capability of the automatic driving vehicle in a complex scene are improved.

An exemplary aspect of the present disclosure relates to an exemplary computer-implemented method for predicting the intentions of actors in an environment. The exemplary method includes obtaining state data related to a plurality of actors in the environment and map data representing a plurality of lanes in the environment. The method includes determining a plurality of potential goals for each actor based on the state data and the map data. The method includes processing the state data, the map data, and the plurality of potential goals with a machine learning predictive model to determine (i) predicted goals for each actor of the plurality of actors, (ii) predicted interactions between each actor of the plurality of actors and other actors based on the predicted goals, and (iii) continuous trajectories for each actor based on the predicted goals.

The invention relates to an apparatus for recognizing an object and a method thereof. The object recognition device may include: a sensor configured to obtain a point cloud associated with an object; and a processor. The processor may be configured to divide a specified space into a plurality of subspaces based on a size of the point cloud. The point cloud may be projected into a specified space. The specified space may include a plurality of voxels included in the plurality of subspaces. The processor may also be configured to: identify, among the plurality of voxels and based on sequentially exploring the plurality of voxels, one or more active voxels including at least a portion of the point cloud; assigning at least one index to the one or more active voxels; identifying an object based on the one or more valid voxels and the at least one index; and controlling an operation of the vehicle based on the identified object.