Patent classifications
B60W2555/00
TECHNOLOGY TO GENERALIZE SAFE DRIVING EXPERIENCES FOR AUTOMATED VEHICLE BEHAVIOR PREDICTION
Systems, apparatuses and methods may provide for technology that generates, via a first neural network such as a grid network, a first vector representing a prediction of future behavior of an autonomous vehicle based on a current vehicle position and a vehicle velocity. The technology may also generate, via a second neural network such as an obstacle network, a second vector representing a prediction of future behavior of an external obstacle based on a current obstacle position and an obstacle velocity, and determine, via a third neural network such as a place network, a future trajectory for the vehicle based on the first vector and the second vector, the future trajectory representing a sequence of planned future behaviors for the vehicle. The technology may also issue actuation commands to navigate the autonomous vehicle based on the future trajectory for the vehicle.
Driving Assist Device, Driving Assist Method, and Driving Assist System
The invention ensures a proper vehicle attitude even if a friction coefficient of a contacted road surface with respect to wheels is small. A driving assist device obtains a first moment that is a moment necessary for an subject vehicle to follow a running course, on the basis of information about a running coursed of an subject vehicle, which is obtained on the basis of external environment information of the subject vehicle, which is acquired by an external environment recognition portion, a first physical quantity associated with a motion state of the subject vehicle, which is inputted by a vehicle motion state detection sensor, and specifications of the subject vehicle, further obtains a second moment that is a moment that can be generated in the subject vehicle on the basis of a friction coefficient of a contacted road surface with respect to the wheels of the subject vehicle, which is acquired by a road surface condition acquisition portion, and a second physical quantity associated with a motion state of the subject vehicle, which is inputted by the vehicle motion state detection sensor, and outputs to a braking control device a command to implement control for making a braking force generated in rear wheels of the wheels greater than a braking force generated in front wheels when the second moment is smaller than the first moment.
Ability enhancement
- Richard T. Lord ,
- Robert W. Lord ,
- Nathan P. Myhrvold ,
- Clarence T. Tegreene ,
- Roderick A. Hyde ,
- Lowell L. Wood ,
- Muriel Y. Ishikawa ,
- Victoria Y. H. Wood ,
- Charles Whitmer ,
- Paramvir BAHL ,
- Douglas C. Burger ,
- Ranveer Chandra ,
- William H. Gates, III ,
- Pablos Holman ,
- Jordin T. Kare ,
- Craig J. Mundie ,
- Tim Paek ,
- Desney S. Tan ,
- Lin Zhong ,
- Matthew G. DYOR
Techniques for ability enhancement are described. In some embodiments, devices and systems located in a transportation network share threat information with one another, in order to enhance a user's ability to operate or function in a transportation-related context. In one embodiment, a process in a vehicle receives threat information from a remote device, the threat information based on information about objects or conditions proximate to the remote device. The process then determines that the threat information is relevant to the safe operation of the vehicle. Then, the process modifies operation of the vehicle based on the threat information, such as by presenting a message to the operator of the vehicle and/or controlling the vehicle itself.
Methods and system for operating an off-road vehicle
Systems and methods for operating a hybrid powertrain or driveline that includes an engine and an integrated starter/generator are described. In one example, engine power is adjusted based on a time averaged transmission input shaft power so that the engine may operate in a power region where its performance is enhanced to support operation in an off-road environment.
VEHICLE CONTROL SYSTEM, VEHICLE CONTROL METHOD, AND PROGRAM
A vehicle control system includes: a recognizer configured to recognize a surrounding situation of an own vehicle; a determiner configured to determine whether a condition for lane changing of the own vehicle from an own lane to an adjacent lane is satisfied based on the surrounding situation recognized by the recognizer; and a traveling controller configured to control steering and a deceleration or acceleration speed of the own vehicle and perform lane-changing control to change the own lane to the adjacent lane when the determiner determines that the condition is satisfied. The lane-changing control is inhibited when a speed of the own vehicle is equal to or less than a predetermined speed.
PARKING ASSIST SYSTEM
A parking assist system includes: a control device configured to control an autonomous parking operation to move a vehicle autonomously to a prescribed target parking position; and a vehicle state detecting device configured to detect a state of the vehicle. During control of the parking operation, when the control device determines that the state of the vehicle detected by the vehicle state detecting device is a prohibition state in which the parking operation should be prohibited, the control device executes a prohibition deceleration process to decelerate the vehicle so as to stop the vehicle. The control device is configured to set an upper limit on deceleration of the vehicle in the prohibition deceleration process to be larger than an upper limit on deceleration of the vehicle in a stop operation to stop the vehicle at the target parking position.
Automated detection of hazardous drifting vehicles by vehicle sensors
A method and device for determining an anomalous driving pattern of a neighboring vehicle using a vehicle camera and/or other sensor is described. Image data is received and if suitable lane markings are detected, a reference trajectory is derived from the detected lane markers. Otherwise, a reference trajectory is derived from a motion of the present vehicle. A trajectory of the neighboring vehicle is determined, characteristic parameters of the detected trajectory are derived, and the characteristic parameters are compared with predetermined trajectory data. Based on the comparison it is determined if the trajectory of the neighboring vehicle is an anomalous trajectory and in one case an alert signal is generated.
Driver Assistance Device, Driver Assistance Method, and Driver Assistance System
A driver assistance device, a driver assistance method, and a driver assistance system according to the present invention make it possible to: determine a distribution of a risk of a vehicle departing from a drivable width of a road on which the vehicle travels based on driving environment factors including a road curvature and a friction coefficient of a road surface of a curve approaching the vehicle; calculate an operation variable of an actuator related to a steering operation of the vehicle based on the distribution of the risk; and output the operation variable to the actuator. This enables steering control based on potential risk evaluation made by taking into account a risk that the controllability of the vehicle may decrease when the vehicle travels on a curve.
Method and system for artificial intelligence based advanced driver assistance
The present invention provides a method and system of historical reaction based driver advanced assistance. In this method, a combination of external environment to a vehicle on which the advanced driver assistance system (ADAS) is mounted fetched by forward looking cameras is combined with rear looking camera for internal environment or driver state, is generated. The generated combination is utilized to analyze is there is any critical situation that is upcoming. For providing feedback for such situation, processor within the ADAS transmits the current combination situation to a remote server that stores historical feedback and driver reactions for various combination of situations. For the current combination situation, a historical combination situation is fetched and corresponding feedbacks analyzed and an ideal feedback, that has comparatively least number of negative driver reactions, is determined.
Vehicle system and method for steep slope site avoidance
A system for operating a vehicle includes a perception sensor, vehicle controls, a controller circuit, and a leveling actuator. The perception sensor is operable to determine a slope of an area within an operable range of a vehicle. The vehicle controls are operable to control movement of the vehicle. The controller circuit is in communication with the perception sensor, the vehicle controls, and the leveling actuator. The controller circuit is configured to determine, using the perception sensor, a first slope of a first site within the area to stop the vehicle, and compare the first slope to a slope threshold. In response to a determination that the first slope is steeper than the slope threshold, the controller circuit is configured to access a digital map that indicates a plurality of slopes coinciding with a plurality of locations at least comprising a second site characterized by a second slope that is not steeper than the slope threshold. The controller circuit is also configured to operate the vehicle controls to move the vehicle to the second site, and to operate the leveling actuator to level the vehicle based on the second slope upon stopping the vehicle at the second site.