A vehicle with autonomous navigation abilities ensures that the vehicle will remain within a safe driving region, such as the current lane, even in the case of a system failure. The vehicle's autonomous control subsystem computes driving parameters used to follow a path of the vehicle toward the current destination. These driving parameters are used to compute a safety envelope describing a region that the vehicle could reach from the present position in case of system failure before coming to a stop. The safety envelope is compared to a current safe driving region, and if the safety envelope violates the boundaries of the safe driving region, the driving parameters and corresponding safety envelopes are recomputed until the currently-computed safety envelope no longer violates the boundaries of the safe driving region.

A vehicle control device includes a first inputter, a second inputter, a mode controller configured to, when the first inputter is operated by a user, determine a driving mode of a vehicle as a first mode, and when the second inputter is operated by the user in the first mode, switch the driving mode from the first mode to a second mode, and a driving controller configured to control at least one of a steering and speed of the vehicle, and the driving controller is configured to control a steering and speed of the vehicle and prohibit change of a path of the vehicle when the driving mode is the first mode, and control a steering and speed of the vehicle and change of the path of the vehicle is allowed when the driving mode is the second mode.

A method for managing NFT-based driver data for an autonomous vehicle includes: receiving driver data including driver’s driving information, traveling information and environment information transmitted from the autonomous vehicle; determining whether an autonomous driving algorithm applied to the autonomous vehicle is improvable based on the driver data; improving the autonomous driving algorithm based on the driver data based on a determination result; generating NFT data corresponding to the driver data as the autonomous driving algorithm is improved; and registering the NFT data in an NFT market for an autonomous vehicle.

A method of sharing information about an object or a condition on a road includes receiving, by a server from a first autonomous vehicle, a message comprising a first data structure that includes information about a driving condition on a road; and transmitting, by the server to a second autonomous vehicle, a second data structure that includes information about the driving condition on the road, where the second data structure is transmitted in response to determining that a location of the driving condition is related to a trajectory on which the second autonomous vehicle is operating or is expected to drive, where the second data structure is transmitted to the second autonomous vehicle before the second autonomous vehicle reaches the location of the driving condition, and where the server is located in a fixed location outside of the first autonomous vehicle and the second autonomous vehicle.

A computer implemented method of controlling a vehicle operation of a vehicle, the vehicle comprising vehicle components operable by processing circuitry based on predicted user behaviour, the method comprising receiving, by the processing circuitry, a signal indicative of a current user behaviour for a user currently operating the vehicle; comparing, by the processing circuitry, the current user behaviour with a predicted user behaviour; and when a difference between the current user behaviour and the predicted user behaviour is above a predetermined threshold limit: forming, by the processing circuitry, new user behaviour based on the current user behaviour; and controlling, by the processing circuitry, operation of at least one of the vehicle components using the new user behaviour.

Aspects of the disclosure relate to controlling a vehicle in an autonomous driving mode. For instance, a trajectory is identified. The trajectory defines a future desired path for the vehicle and includes a control requirement having a corresponding point in time. A command for achieving the control requirement is generated. A fixed delay value corresponding to a delay caused by transmission of the command to an actuator of the vehicle is generated. A variable delay value corresponding to a delay caused by an amount of time to change a physical state of the actuator to a desired state according to the command is generated. The command is then sent to the actuator based on the fixed delay value, the variable delay value, and so that the actuator causes the vehicle to move according to the command.

In various examples, systems and methods are disclosed that accurately identify driver and passenger in-cabin activities that may indicate a biomechanical distraction that prevents a driver from being fully engaged in driving a vehicle. In particular, image data representative of an image of an occupant of a vehicle may be applied to one or more deep neural networks (DNNs). Using the DNNs, data indicative of key point locations corresponding to the occupant may be computed, a shape and/or a volume corresponding to the occupant may be reconstructed, a position and size of the occupant may be estimated, hand gesture activities may be classified, and/or body postures or poses may be classified. These determinations may be used to determine operations or settings for the vehicle to increase not only the safety of the occupants, but also of surrounding motorists, bicyclists, and pedestrians.

A method is for controlling a system for regulating a distance between a target vehicle and a following vehicle, with the regulation system being installed on the following vehicle. The method includes the implementation of a control law for regulating the distance which calculates, for a plurality of possible combinations of speeds of movement of the following vehicle and the target vehicle, potential setpoint distances, and, for a given combination of speeds of movement of the following and target vehicles, from the plurality of possible combinations, the determination of a final setpoint distance among the potential setpoint distances previously calculated by the control law.

Systems and methods are provided for navigating a host vehicle. In an embodiment, a processing device may be configured to receive a plurality of images acquired by a camera; analyze at least one of the plurality of images to identify a crosswalk in the environment of the host vehicle; analyze the at least one of the plurality of images to determine a looking direction of at least one pedestrian in a vicinity of the identified crosswalk; if the at least one pedestrian is determined to be looking in a direction of the host vehicle, determine a navigational action for the host vehicle; and cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action for the host vehicle.

Systems and methods for situational modification of autonomous vehicle operation are disclosed. According to aspects, a computing device may detect the occurrence of an emergency event and may determine a current operation of an autonomous vehicle that may be associated with the emergency event. The computing device may determine a modification to operation of the autonomous vehicle, where the modification may represent a violation of a roadway regulation that may enable effective handling of the emergency event. The computing device may generate a set of instructions for the autonomous vehicle to execute to cause the autonomous vehicle to undertake the operation modification.