A system and method for reliably determining lanes of a roadway includes an optical sensing arrangement for sensing metallic striping from photoelectric effect. The location of the striping that defines a border of a traffic lane is determined and the location of the striping is displayed on a graphical user interface. The location can be used to provide lane control to ensure the vehicle maintains proper position in a traffic lane, lane warning assistance, collision avoidance, parking control, and guidance for autonomous driving.

The described techniques relate to modifying a trajectory of a vehicle, such as an autonomous vehicle, based on a latency associated with one or more systems of the vehicle. In examples, a planning system of the vehicle may predict a future latency (e.g., based on an interval between receipt of sensor data and/or object predictions), and use the future latency to determine a time at which to predict object behavior. Additionally, in some cases, the described techniques may include associating a predetermined acceleration with a predicted future location of the object to create a safety distance around the object, where the predetermined acceleration may be based on a maximum expected acceleration of the object. The safety distance may account for the object potentially accelerating in one or more directions at the future time.

An in-vehicle sensing module for monitoring a vehicle is disclosed, which is advantageous for use in the context of a shared vehicle service, such as a car rental service, an autonomous taxi service, or a ride sharing service. The in-vehicle sensing module at least includes a controller, a cellular transceiver, and one or more integrated sensors configured to monitor a status of the vehicle. The in-vehicle sensing module utilizes appropriate algorithms, models, or thresholds to interpret sensor data and enrich the data with metadata and event detection. The in-vehicle sensing module uploads relevant sensor data, event data, or other metadata to a cloud storage backend, which is made accessible by authorized third-parties.

A display control device comprising: a depression acquisition part acquiring a current amount of depression of an accelerator pedal; a suitable range calculation part calculating, as a suitable depression range, a range of an amount of accelerator depression required for a following distance of a preceding vehicle and an ego vehicle to become a predetermined target following distance, based on the following distance; and a display control part displaying the current amount of depression and the suitable depression range at a display device able to be viewed by a driver.

A vehicle control device recognizes a second self-position, which is obtained by correcting a first self-position, and an orientation of a vehicle on a road, on which the vehicle is traveling, based on a situation around the vehicle, the first self-position, and map information, determines a steering control mode and a speed control mode of the vehicle based on the second self-position and the orientation of the vehicle, and performs automated driving by controlling the vehicle based on the determined control modes. When the vehicle is scheduled to advance from a first lane to a second lane and it is not possible to recognize a target associated with a road indicating an end point of a merging section, a determiner determines a steering angle control mode for searching for the target based on the second self-position and the orientation of the vehicle.

Disclosed herein is a technique for generating and providing an indication to an autonomous vehicle regarding the confidence level for the accuracy or quality of the map data in which the indication is determined from observation data received from other vehicles.

A driving control method and apparatus are provided. The method may be applied to the intelligent vehicle field such as intelligent driving/automatic driving. The driving control method includes, after calculating a conventional path in a conventional map, the driving control apparatus searches a high-definition map for a high-definition path that matches the conventional path, and if yes, performs real-time navigation broadcast by using the conventional path, and performs automatic driving by using the found high-definition path. The driving control method and apparatus use advantages of the conventional map, for example, rich road sections and updated real-time traffic information, a more proper calculated conventional path, and a better effect of real-time navigation broadcast, and implement automatic vehicle driving by using a high-definition path, to reduce user operations, thereby improving user experience.

A method for traffic light auto-labeling includes aggregating vehicle-to-infrastructure (V2I) traffic light signals at an intersection to determine transition states of each driving lane at the intersection during operation of an ego vehicle. The method also includes automatically labeling image training data to form auto-labeled image training data for a traffic light recognition model within the ego vehicle according to the determined transition states of each driving lane at the intersection. The method further includes planning a trajectory of the ego vehicle to comply with a right-of-way according to the determined transition states of each driving lane at the intersection according to a trained traffic light detection model. A federated learning module may train the traffic light recognition model using the auto-labeled image training data during the operation of the ego vehicle.

Vehicle center of gravity (CoG) height and mass estimation techniques utilize a light detection and ranging (LIDAR) sensor configured to emit light pulses and capture reflected light pulses that collectively form LIDAR point cloud data and a controller configured to estimate the CoG height and the mass of the vehicle during a steady-state operating condition of the vehicle by processing the LIDAR point cloud data to identify a ground plane, identifying a height difference between (i) a nominal distance from the LIDAR sensor to the ground plane and (ii) an estimated distance from the LIDAR sensor to the ground plane using the processed LIDAR point cloud data, estimating the vehicle CoG height as a difference between (i) a nominal vehicle CoG height and the height difference, and estimating the vehicle mass based on one of (i) vehicle CoG metrics and (ii) dampening metrics of a suspension of the vehicle.

A system and methods are provided for determining a vehicle action during a phantom projection attack, including processing a received image to identify a traffic object, and creating from the received image multiple processed images that are applied to respective neural network (NN) models. Latent representations of the multiple processed images from each of the NN models are then fed to a combiner model trained to determine whether the latent representations indicate a phantom projection attack, and, responsively to a determination of a phantom projection attack, issuing a phantom projection indicator.