Baidu USA LLC

Other

Nokia Technologies Oy

Yifei Jiang

Jiangtao Hu

Dong Li

Jiaming Tao

Liangliang Zhang

Guang Yu Yang

Fan Zhu

Jingao Wang

Qi Kong

Qi Luo

Liyun Li

Yajia Zhang

Jinghao Miao

Hongyi Sun

Haoyang Fan

Jiacheng Pan

Jinyun Zhou

Shuang Wu

Zhuang Li

Kecheng Xu

Jiaxuan Xu

Shu Jiang

Weicheng Zhu

Zhigang Liu

Li Zhuang

Xiangquan Xiao

Du Li

Youling Zou

Shiyu Song

Xiang Yu

Siyang Yu

Lei Ma

Li Dong

Guang Yang

A sensor aggregation framework for autonomous driving vehicles is disclosed. In one embodiment, sensor data is collected from one or more sensors mounted on an autonomous driving vehicle (ADV) while the ADV is moving within a region of interest (ROI) that includes a number of obstacles. The sensor data includes obstacle information of the obstacles and vehicle data of the ADV. Each of the vehicle data is timestamped with a current time at which the vehicle data is captured to generate a number of timestamps that correspond to the vehicle data. The obstacle information, the vehicle data, and the corresponding timestamps are aggregated into training data. The training data is used to train a set of parameters that is subsequently utilized to predict at least in part future obstacle behaviors and vehicle movement of the ADV.

Sensor aggregation framework for autonomous driving vehicles

In one embodiment, a process is performed during controlling Autonomous Driving Vehicle (ADV). A confidence level associated with a sensed obstacle is determined. If the confidence level is below a confidence threshold, and a distance between the ADV and a potential point of contact with the sensed obstacle is below a distance threshold, then performance of a driving decision is delayed. Otherwise, the driving decision is performed to reduce risk of contact with the sensed obstacle.

Delay decision making for autonomous driving vehicles in response to obstacles based on confidence level and distance

An obstacle state evolution of a spatial position of a moving obstacle over a period of time is determined. A lane-obstacle relation evolution of the moving obstacle with each of one or more lanes near the moving obstacle over the period of time is further determined. An intended movement of the moving obstacle is predicted based on the obstacle state evolution and the lane-obstacle evolution. Thereafter, a trajectory of the ADV is planned to control the ADV to avoid a collision with the moving obstacle based on the predicted intended movement of the moving obstacle. The above process is iteratively performed for each of the moving obstacles detected within a predetermined proximity of the ADV.

Lane-attention: predicting vehicles' moving trajectories by learning their attention over lanes

According to one embodiment, during a first planning cycle, a first lane boundary of a driving environment perceived by an ADV is determined using a first lane boundary determination scheme (e.g., current lane boundary), which has been designated as a current lane boundary determination scheme. A first trajectory is planned based on the first lane boundary to drive the ADV to navigate through the driving environment. The first trajectory is evaluated against a predetermined set of safety rules (e.g., whether it will collide or get too close to an object) to avoid a collision with an object detected in the driving environment. In response to determining that the first trajectory fails to satisfy the safety rules, a second lane determination boundary of the driving environment is determined using a second lane boundary determination scheme and a second trajectory is planned based on the second lane boundary to drive the ADV.

Hierarchical path decision system for planning a path for an autonomous driving vehicle

In one embodiment, a system/method generates a driving trajectory for an autonomous driving vehicle (ADV). The system perceives an environment of an autonomous driving vehicle (ADV). The system determines one or more bounding conditions based on the perceived environment. The system generates a first trajectory using a neural network model, wherein the neural network model is trained to generate a driving trajectory. The system evaluates/determines if the first trajectory satisfies the one or more bounding conditions. If the first trajectory satisfies the one or more bounding conditions, the system controls the ADV autonomously according to the first trajectory. Otherwise, the system controls the ADV autonomously according to a second trajectory, where the second trajectory is generated based on an objective function, where the objective function is determined based on at least the one or more bounding conditions.

Hybrid planning system for autonomous vehicles

An ADV may determine whether there is preexisting map data for an environment or geographical area/location where the ADV is located/travelling. If there is no preexisting data, the ADV may generate map data based on sensor data obtained from one or more sensors of the ADV. The ADV may determine a path for the ADV based on the generated map data. If there is preexisting map data, the ADV may determine a path for the ADV based on the preexisting map data.

Determining driving paths for autonomous driving vehicles based on map data

According to some embodiments, described herein is a system and method for handling sensor failures in autonomous driving vehicles (ADV) that is navigating in a world coordination as an absolute coordination system. When the ADV encounters a sensor failure, but still has at least one camera working properly, the sensor failure handling system can switch the ADV from navigating in the world coordination to a local coordination, in which the ADV relies camera-based obstacle detection and lane mark detection to drive safely until human dis-engagement or until the ADV is parked along a road side.

Methods for handling sensor failures in autonomous driving vehicles

A perception module is configured to perceive a driving environment surrounding an autonomous driving vehicle (ADV) based on sensor data, and to generate perception information using various perception models or methods. The perception information describes the perceived driving environment. Based on the perception information, a planning module is configured to plan a trajectory representing a route or a path for a current planning cycle. The ADV is then controlled and driven based on the trajectory. In addition, the planning module determines a critical region (also referred to as a critical area) surrounding the ADV based on the trajectory in view of a current location or position of the ADV. The metadata describing the critical region is transmitted to the perception module via an application programming interface (API) to allow the perception module to generate perception information for a next planning cycle in view of the critical region.

Perception and planning collaboration framework for autonomous driving

Via a first processing thread, an ADV is controlled according to a first trajectory that was generated based on a first reference line starting at a first location. Concurrently via a second processing thread, a second reference line is generated based on a second location of the first trajectory that the ADV will likely reach within a predetermined period of time in future. The predetermined period of time is greater than or equals to an amount of time to generate a reference line for the ADV. The second reference line is generated while the ADV is moving according to the first trajectory and before reaching the second location. Subsequently, in response to determining that the ADV is within a predetermined proximity of the second location, a second trajectory is generated based on the second reference line without having to calculate the second reference line at the second location.

Method and system for generating reference lines for autonomous driving vehicles using multiple threads

A server may determine whether traffic control devices in an environment have changed, based on one or more report messages and sensor data. If the traffic control devices in an environment have changed, the server may generate updated map data and transmit the updated map data to an autonomous driving vehicle (ADV).

Updating map data for autonomous driving vehicles based on sensor data

System and method for training a machine learning model are disclosed. In one embodiment, for each of the driving scenarios, responsive to sensor data from one or more sensors of a vehicle and the driving scenario, driving statistics and environment data of the vehicle are collected while the vehicle is driven by a human driver in accordance with the driving scenario. Upon completion of the driving scenario, the driver is requested to select a label for the completed driving scenario and the selected label is stored responsive to the driver selection. Features are extracted from the driving statistics and the environment data based on predetermined criteria. The extracted features include some of the driving statistics and some of the environment data collected at the different points in time during the driving scenario.

System and method for training a machine learning model deployed on a simulation platform

In response to a search query received from a client, a content item is identified from a content database based on one or more keywords associated with the search query. In addition, a search is performed in an image store to identify a list of image candidates based on one or more keywords associated with the search query. An image is selected from the list of image candidates using an image selection algorithm. Metadata associated with the content provider is inscribed onto the selected image to generate a customized image. The customized image is integrated with the content item to generate a composite content item such as a poster. As a result, the content represented by the composite content item is closely tied to the content provider. The composite content item is then transmitted to the client.

Method and system for dynamically overlay content provider information on images matched with content items in response to search queries

In one embodiment, a set of predetermined driving parameters is determined from a set of driving statistics data collected from a number of vehicles, which may be driven by human drivers. For each pair of the predetermined driving parameters, a distribution of the pair of driving parameters is plotted based on their relationship on a two-dimensional (2D) distribution space. The 2D distribution space is partitioned into a number of grid cells, each grid cell representing a particular pair of driving parameters. For each of the grid cells, a probability is calculated that the pair of driving parameter likely falls in the grid cell. A grid table is generated corresponding to the pair of driving parameters. The grid table can be utilized during the autonomous driving at real-time or during simulation to determine a ride stability of an autonomous driving vehicle (ADV) in view of the pair of driving parameters.

Method for determining ride stability of an autonomous driving system controlling an autonomous driving vehicle

In one embodiment, a system monitors states of an autonomous driving vehicle (ADV) using a number of sensors mounted on the ADV. The system perceives a driving environment surrounding the ADV using at least a portion of the sensors. The system analyzes the states in view of the driving environment to determine a real-time traffic condition at a point in time. The system determines whether the real-time traffic condition of the driving environment matches at least a predetermined traffic condition. The system transmits data concerning the real-time traffic condition to a remote server over a network to allow the remote server to generate an updated map having real-time traffic information, in response to determining the real-time traffic condition is unknown. In response to receiving the updated map, the system plans and controls the ADV based on the updated map.

System for building a vehicle-to-cloud real-time traffic map for autonomous driving vehicles (ADVS)

A social driving style learning framework or system for autonomous vehicles is utilized, which can dynamically learn the social driving styles from surrounding vehicles and adopt the driving style as needed. Each of the autonomous vehicles within a particular driving area is equipped with the driving style learning system to perceive the driving behaviors of the surrounding vehicles to derive a set of driving style elements. Each autonomous vehicle transmits the driving style elements to a centralized remote server. The server aggregates the driving style elements collected from the autonomous vehicles to determine a driving style corresponding to that particular driving area. The server transmits the driving style back to each of the autonomous vehicles. The autonomous vehicles can then decide whether to adopt the driving style, for example, to follow the traffic flow with the rest of the vehicles nearby.

Growing community of inventors

Sunnyvale, CA, United States of America

Yifei Jiang