A crossing detection unit (21) detects a pedestrian who is about to cross a roadway on which a vehicle (100) travels. A behavior detection unit (22) detects a behavior of a nearby vehicle traveling around the vehicle (100). A stop determination unit (23) determines whether or not to stop the vehicle (100) in view of the detection of the pedestrian who is about to cross the roadway by the crossing detection unit (21) and the behavior of the nearby vehicle detected by the behavior detection unit (22). A vehicle control unit (24) stops the vehicle (100) before the pedestrian when the stop determination unit (23) determines to stop the vehicle.

Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. More specifically, systems, devices, and methods are configured to generate trajectories to influence navigation of autonomous vehicles. In particular, a method may include receiving path data to navigate from a first geographic location to a second geographic location, generating data representing a trajectory with which to control motion of the autonomous vehicle based on the path data, generating data representing a contingent trajectory, monitoring generation of the trajectory, and implementing the contingent trajectory subsequent to an absence of the trajectory.

A navigation system includes a processing device programmed to receive, from an image capture device, at least one image of an environment of the host vehicle; determine, based on at least one driving policy, a navigational action for accomplishing a navigational goal of the host vehicle; analyze the at least one image to identify a target vehicle; test the navigational action against at least one accident liability rule for determining potential accident liability for the host vehicle relative to the target vehicle; if the test indicates that potential accident liability exists for the host vehicle if the navigational action is taken, then cause the host vehicle not to implement the navigational action; and if the test indicates that no accident liability would result for the host vehicle if the navigational action is taken, then cause the host vehicle to implement the navigational action.

Systems and methods are provided for crowdsourcing road surface information collection. In one implementation, a method of collecting road surface information for a road segment may include receiving at least one image representative of a portion of the road segment, identifying in the at least one image at least one road surface feature along the portion of the road segment, determining a plurality of locations associated with the road surface feature according to a local coordinate system of the vehicle, and transmitting the determined plurality of locations from the vehicle to a server. The determined locations may be configured to enable determination by the server of a line representation of the road surface feature extending along the road segment.

A driving support device comprises a passing determination unit which determines whether an own vehicle is going to pass by a stopped vehicle stopped in an adjacent lane adjacent to a traveling lane on which the own vehicle is traveling; and a notification control unit which issues warning notification when it is determined that the own vehicle is going to pass by the stopped vehicle.

When a transmission condition regarding a state detected by a state detection unit (vehicle sensor, operation detection sensor, external environment sensor, or internal environment sensor) is satisfied while a travel controller performs a travel control, a vehicle control system transmits attentional state information representing a travel state, an operation state, or an environment state to a travel assist server through a communication device.

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to receive a vehicle path from a server computer and verify the vehicle path based on vehicle dynamics and vehicle constraints. The instruction can include further instructions to, when the vehicle path is verified as correct, operating the vehicle on the vehicle path and, when the vehicle path is verified as incorrect, stopping the vehicle.

When a collision avoidance target is a pedestrian or a bicycle, a driving assistance ECU performs automatic braking control. In this case, accelerator override cannot be performed. When the collision avoidance target is an automobile and when an accelerator operation amount is equal to or larger than a first operation amount threshold, the driving assistance ECU prohibits the automatic braking control. In this case, the accelerator override can be performed. When the accelerator operation amount is smaller than the first operation amount threshold, the driving assistance ECU performs the automatic braking control.

A collision detection device detects a probability of whether a vehicle will collide with a detected moving object. An ECU determines a high-risk region measured by a predetermined distance in a forward moving direction of the vehicle from a farthest feature point obtained from a farthest-located obstacle object detected on a road's shoulder. When the moving object is detected in the high-risk region, the ECU reduces a collision detection time-period within which the vehicle must detect whether the vehicle would collide with the moving object. The reduced collision detection time-period is shorter than a collision detection time-period to be used when the moving object is detected outside of the high-risk region.

A system and a method for autonomous decisioning and operation by an autonomous agent includes: collecting decisioning data including: collecting a first stream of data includes observation data obtained by onboard sensors of the autonomous agent, wherein each of the onboard sensors is physically arranged on the autonomous agent; collecting a second stream of data includes observation data obtained by offboard infrastructure devices, the offboard infrastructure devices being arranged geographically remote from and in an operating environment of the autonomous agent; implementing a decisioning data buffer that includes the first stream of data from the onboard sensors and the second stream of data from the offboard sensors; generating current state data; generating/estimating intent data for each of one or more agents within the operating environment of the autonomous agent; identifying a plurality of candidate behavioral policies; and selecting and executing at least one of the plurality of candidate behavioral policies.