An autonomous driving device is configured to switch a driving mode, and includes a destination setting type autonomous driving mode in which a vehicle is made to travel to a destination and a following road autonomous driving mode in which, when a destination is not set, the vehicle is made to travel along a road. The autonomous driving device includes a display unit and an electronic control unit. The electronic control unit is configured to, when the display unit is made to display a traveling route along a following road traveling route, make the display unit display a traveling route from a current position of the vehicle to a nearest branch road in front in a moving direction along the following road traveling route and a moving direction on the nearest branch road along the following road traveling route.

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.

Jaywalking behaviors of vulnerable road users (VRUs) such as cyclists or pedestrians can be predicted. Location data is obtained that identifies a location of a VRU within a vicinity of a vehicle. Environmental data is obtained that describes an environment of the VRU, where the environmental data identifies a set of environmental features in the environment of the VRU. The system can determine a nominal heading of the VRU, and generate a set of predictive inputs that indicate, for each of at least a subset of the set of environmental features, a physical relationship between the VRU and the environmental feature. The physical relationship can be determined with respect to the nominal heading of the VRU and the location of the VRU. The set of predictive inputs can be processed with a heading estimation model to generate a predicted heading offset (e.g., a target heading offset) for the VRU.

The embodiments of the present disclosure relate to a wireless terminal location information-based accident prevention device and method. Specifically, the wireless terminal location information-based accident prevention device according to the present disclosure may include a receiver for receiving GPS information of a wireless terminal located within a predetermined distance from a host vehicle, a sensor unit for detecting an object corresponding to the GPS information of the wireless terminal, and a controller configuring to determine a first time-to-collision with the object based on a change of the GPS information, to determine a second time-to-collision with the object based on motion information of the object detected by the sensor unit, and to control the host vehicle to prevent a collision with the object according to a predetermined criterion based on the first time-to-collision and the second time-to-collision.

A method, system and non-transitory computer readable medium for multi-stage communication between an autonomous vehicle and a road user. The autonomous vehicle uses vehicle external cameras, a LiDAR sensors and radar sensors to image the surrounding environment. Image processing circuitry is used to develop a view of the surrounding environment from the sensed images and the view is combined with stored map data. Road users, which may include pedestrians, bicyclists, motorcyclists and non-autonomous vehicles are identified on the view and it is determined whether the movement of the road user will intersect the trajectory of the autonomous vehicle. The autonomous vehicle performs a vehicle behavior modification as a first stage signal to alert the road user of its intent. If the road user does not react to the first stage signal, the autonomous vehicle activates additional external lighting as a second stage signal to alert the road user.

A driving assistance apparatus is configured to identify a target as a crossing target when a vehicle and the target are expected to collide with each other in an intersecting region, configured to decelerate the vehicle at a first deceleration from a first timing before an expected collision timing that the vehicle and the crossing target are expected to collide with each other, and configured to decelerate the vehicle at a second deceleration from a second timing when the crossing target is still present at a second timing immediately before a third timing defined such that the vehicle is not stoppable at a position immediately before entering the intersecting region in a case where the vehicle starts to decelerate from the third timing at a second deceleration having an absolute value larger than an absolute value of the first deceleration.

Provided is an apparatus for assisting driving of a host vehicle including: an obstacle detector configured to detect an obstacle using a radar sensor; and a controller configured to determine a free-space in which a host vehicle is movable based on a position of the detected obstacle, and determine an obstacle located at a boundary of the free-space as an object having a risk of collision.

A method for determining event data including: sampling a first data stream within a first time window at a first sensor of an onboard vehicle system coupled to a vehicle, extracting interior activity data from the first data stream; determining an interior event based on the interior activity data; sampling a second data stream within a second time window at a second sensor of the onboard vehicle system; extracting exterior activity data from the second image stream; determining an exterior event based on the exterior activity data; correlating the exterior event and the interior event to generate combined event data; automatically classifying the combined event data to generate an event label; and automatically labeling the first time window of the first data stream and the second time window of the second data stream with the combined event label to generate labeled event data.

An attention calling device includes a memory and a hardware processor coupled to the memory. The hardware processor is configured to: acquire information regarding obstacles around a moving object detected by a sensor included in the moving object; calculate a potential risk that is a degree to which attention needs to be paid for each of the obstacles around the moving object, based on the acquired information regarding the obstacles and a moving state of the moving object; and present, to an occupant of the moving object, information for calling attention to an obstacle having a potential risk exceeding a predetermined value, based on a calculated potential risk of each of the obstacles.

Techniques for determining a classification probability of an object in an environment are discussed herein. Techniques may include analyzing sensor data associated with an environment from a perspective, such as a top-down perspective, using multi-channel data. From this perspective, techniques may determine channels of multi-channel input data and additional feature data. Channels corresponding to spatial features may be included in the multi-channel input data and data corresponding to non-spatial features may be included in the additional feature data. The multi-channel input data may be input to a first portion of a machine-learned (ML) model, and the additional feature data may be concatenated with intermediate output data from the first portion of the ML model, and input into a second portion of the ML model for subsequent processing and to determine the classification probabilities. Additionally, techniques may be performed on a multi-resolution voxel space representing the environment.