In one embodiment, a speed planning system receives speed limit information for an autonomous driving vehicle (ADV), where the speed limit information includes a change in road speed limit for a current road of the ADV. The system determines a tapered speed limit corresponding to the current road based on the speed limit information, where the tapered speed limit correspond to a gradual speed reduction from a first road speed limit to a second road speed limit. The system determines a cost function based on the tapered speed limit and the first and second road speed limits. The system generates a number of trajectory candidates based on the cost function. The system selects a trajectory based on the trajectory candidates to control the ADV using the selected trajectory.

The technology relates to articulated autonomous vehicles that can potentially jackknife. To avoid or mitigate such hazardous conditions, the current state of the vehicle is evaluated against the vehicle's planned trajectory, for instance as it drives along a freeway or surface streets. When the evaluation indicates a likelihood of jackknifing, an automated braking approach is implemented using elective braking to stabilize the vehicle. The braking approach can depend on whether the situation involves tractor jackknifing or trailer jackknifing, and one or more different braking mechanisms can be employed for a selective modulation of the braking profile to address actual jackknifing or to prevent the vehicle from entering a jackknifing situation.

A vehicle safety system within an autonomous or semi-autonomous vehicle may predict and avoid collisions between the vehicle and other moving objects in the environment. The vehicle safety system may determine one or more perturbed trajectories for another object in the environment, for example, by perturbing the state parameters of a perceived trajectory associated with the object. Each perturbed trajectory may be evaluated to determine whether it intersects or potentially collides the planned trajectory of the vehicle. In some examples, the vehicle safety system may aggregate the results of analyses of multiple perturbed trajectories to determine a collision probability and/or additional weights or adjustment factors associated with the collision prediction, and may determine actions for the vehicle to take based on the collision predictions and probabilities.

A driving support method supports driving of a host-vehicle in a traveling scene in which a host-vehicle track on which the host-vehicle travels and a first other vehicle track on which a first other vehicle travels intersect with each other at an intersecting point. Whether the host-vehicle can enter the intersecting point is determined based on a shielding time during which a second other vehicle shields the first other vehicle track to the intersecting point and a required entry time from when the host-vehicle starts entering the intersecting point to when the host-vehicle finishes entering the intersecting point.

This document describes techniques, apparatuses, and systems for sensor fusion for object-avoidance detection, including stationary-object height estimation. A sensor fusion system may include a two-stage pipeline. In the first stage, time-series radar data passes through a detection model to produce radar range detections. In the second stage, based on the radar range detections and camera detections, an estimation model detects an over-drivable condition associated with stationary objects in a travel path of a vehicle. By projecting radar range detections onto pixels of an image, a histogram tracker can be used to discern pixel-based dimensions of stationary objects and track them across frames. With depth information, a highly accurate pixel-based width and height estimation can be made, which after applying over-drivability thresholds to these estimations, a vehicle can quickly and safely make over-drivability decisions about objects in a road.

Systems and methods for assigning a lane to an object in an environment of an autonomous vehicle are disclosed. The methods include assigning an instantaneous probability to each of a plurality of lanes in the environment based on a current state of the object, generating a transition matrix for each of the plurality of lanes, and identifying the lane in which the object is moving at the current time t based on the instantaneous probability and the transition matrix. The instantaneous probability is a measure of likelihood that the object is in that lane at a current time. The transition matrix encodes one or more probabilities that the object transitioned either into that lane or out of that lane at the current time.

Disclosed herein are systems, methods, and computer program products for operating a robotic system. For example, the method includes: obtaining a first cuboid generated based on an image, a second cuboid generated based on a lidar dataset and/or a third cuboid generated by a heuristic algorithm using the lidar dataset; using a machine learning model to generate a heading for an object in proximity to the robotic system based on the first cuboid, second cuboid and/or third cuboid; generating a bounding box geometry and a bounding box location based on the second cuboid or third cuboid; and generating a fourth cuboid using the bounding box geometry, the bounding box location, and the heading generated using the machine learning model.

A method and apparatus for controlling a vehicle is disclosed. The method may include: determining center points of at least two frames of point clouds collected for an identified obstacle during travelling of the vehicle; performing curve fitting based on the determined center points to obtain a fitted curve; determining a moving velocity of the obstacle based on the fitted curve; predicting whether the vehicle is to be collided with the obstacle when the vehicle continues travelling at a current velocity, based on the moving velocity of the obstacle, the traveling velocity of the vehicle, and a distance between the obstacle and the vehicle; and sending control information to the vehicle, in response to predicting that the vehicle is to be collided with the obstacle when the vehicle continues travelling at the current velocity, the control information being used to control the vehicle to avoid collision with the obstacle.

Embodiments of the present disclosure provide a control method of an unmanned vehicle and an unmanned vehicle, which have excellent safety. The control method of the unmanned vehicle includes: detecting vibration information and running attitude information of the unmanned vehicle; according to the vibration information, the running attitude information and a running status of the unmanned vehicle, determining a condition of the unmanned vehicle, wherein the running status of the unmanned vehicle includes a stop status and a driving status; and when the condition of the unmanned vehicle is abnormal, controlling the unmanned vehicle according to an abnormal condition coping strategy.

A vehicle system configured to control a vehicle provided with a vehicle platform that includes a drive unit, an auxiliary device, a first controller, a second controller, a high-voltage electric power source, a low-voltage electric power source, an autonomous driving platform that performs autonomous driving control, and a vehicle control interface that connects the vehicle platform and the autonomous driving platform to each other and is configured to convert a first control instruction into a second control instruction with respect to the vehicle platform, and transmit the second control instruction. The vehicle system includes a controlling device configured to cause the second controller and the vehicle control interface to enter an operating state and cut off supply of electric power from the high-voltage electric power source to the drive unit.