A method includes receiving sensor data associated with one or more inputs associated with a road portion, determining a level of risk associated with each of the one or more inputs, determining an estimated amount of computing resources that each of a plurality of candidate computing methods will consume, and selecting one or more computing methods from the plurality of candidate computing methods to associate with the one or more inputs based on the levels of risk associated with the one or more inputs and the estimated amount of computing resources that the candidate computing methods will consume.

An apparatus for controlling a vehicle capable of performing autonomous driving is provided. The apparatus includes an autonomous driving device that executes the autonomous driving and generates a transition demand when it is impossible to execute the autonomous driving. A driving controller performs a minimum risk maneuver (MRM) of applying a deceleration pattern differently depending on a driving environment of the vehicle, when the transition demand is generated, but when driving manipulation by a driver does not occur. A subsequent safety ensuring function is performed according to the MRM for the driver to recognize the MRM, and a drive mode of the vehicle is changed to a drive mode with a rapid response speed to acceleration or steering.

Monitoring driving safety information before a vehicle enters a curve or when the vehicle has entered the curve; obtaining a position of the vehicle in response to the driving safety information; obtaining curve information, where the curve information includes at least one of a position of a start point of the curve and a position of an end point of the curve; and controlling, based on the position of the vehicle and the curve information, the vehicle to stop at a position outside the curve.

A method of adjusting a driving strategy for a driverless vehicle is provided, which relates to a field of artificial intelligence, in particular to autonomous driving, cloud computing, NLP, computer vision and other fields, and may be applied to an interaction scene between a driverless vehicle and a pedestrian. A specific implementation solution includes: detecting an emotion of at least one pedestrian in response to the at least one pedestrian being detected within a preset range in front of the driverless vehicle; and adjusting a current driving strategy for the driverless vehicle based on a specified emotion in response to detecting that the at least one pedestrian includes a target pedestrian exhibiting the specified emotion.

A method for communication between autonomous vehicles and personnel can include receiving a signal from a remote computing system, the signal based upon a position of an autonomous vehicle and a first position of a mobile device, wherein the signal identifies that the mobile device is located in a path of the autonomous vehicle, responsive to receipt of the signal from the remote computing system, stopping the autonomous vehicle, receiving an updated signal from the remote computing system, the updated signal based upon a second position of the mobile device, the second position effective to facilitate a determination that the mobile device is no longer within the path of the autonomous vehicle, and responsive to receiving the updated position of the mobile device, resuming operation of the autonomous vehicle along the path. An autonomous vehicle and non-transitory computer-readable medium is also provided.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that determine yield behavior for an autonomous vehicle, and can include identifying an agent that is in a vicinity of an autonomous vehicle navigating through a scene at a current time point. Scene features can be obtained and can include features of (i) the agent and (ii) the autonomous vehicle. An input that can include the scene features can be processed using a first machine learning model that is configured to generate (i) a crossing intent prediction that includes a crossing intent score that represents a likelihood that the agent intends to cross a roadway in a future time window after the current time, and (ii) a crossing action prediction that includes a crossing action score that represents a likelihood that the agent will cross the roadway in the future time window after the current time.

Embodiments is disclosed to detect a locked heading direction of a pedestrian and to predict a path for the pedestrian using the locked heading direction. According to one embodiment, a system perceives an environment of an autonomous driving vehicle (ADV) using one or more image capturing devices. The system detects a pedestrian in the perceived environment. The system determines a facing direction of the pedestrian relative to the ADV as one of left/right side, front, or back. If the facing direction of the pedestrian is determined to be front or back facing, the system determines a lane nearest to the pedestrian. The system projects the pedestrian onto the nearest lane to determine a lane direction at the projection. The system determines a heading direction for the pedestrian locking to the lane direction of the nearest lane based on a predetermined condition.

A driver assistance system plans movement for a motor vehicle, wherein a safe state of the motor vehicle is a state of the motor vehicle in a first time step from which the motor vehicle can be transferred, as a function of a movement capability of the motor vehicle in at least one second time step which follows the first time step, into a further safe state without colliding with a road user. The driver assistance system is configured to determine for at least one future time step starting from a current state of the motor vehicle, at least one possible future state of the motor vehicle and of the road user, and to select safe future states of the motor vehicle from the possible future states of the motor vehicle and of the road user, and to plan a movement for the motor vehicle as a function of the safe future states.

A recognition processing apparatus includes a video acquisition unit configured to acquire first captured image data of surroundings of a host vehicle captured by a far-infrared camera, an other vehicle detection unit configured to detect another vehicle parked or stopped in the surroundings of the host vehicle, a heat detection unit configured to detect radiated heat associated with an operation of the other vehicle based on a thermal distribution in a region corresponding to the other vehicle in the first captured image data, and a person detection unit configured to, when the radiated heat has been detected, preferentially execute person recognition in a vicinity of the other vehicle to detect a person. The recognition processing apparatus can ascertain the possibility that a person gets out of a detected vehicle and promptly detect such a person.

Disclosed embodiments include technologies related to Maneuver Coordination Services (MCS) in vehicular networks. Embodiments include Emergency Group Maneuver Coordination (EGMC) for detected unexpected safety-critical situations (USCS) on the road. EGMC provides cooperative maneuver coordination among a group of vehicles to ensure safer collective actions in the case of USCS. Embodiments include Maneuver Coordination Message (MCM) format and structure, details of contents of MCM message, and procedures for Generation and Transmission of MCM with reduced communication overhead. Other embodiments are described and/or claimed.