Baidu USA LLC

Apollo Intelligent Driving Technology (beijing) Co., Ltd.

Baidu Online Network Technology (beijing) Co., Ltd.

Linedin Corporation

Liyun Li

Jingao Wang

Jiangtao Hu

Dong Li

Guang Yu Yang

Yifei Jiang

Jiaming Tao

Jinghao Miao

Shaoshan Liu

James P Peng

Shuang Wu

I-Hsuan Yang

Shiyuan Fang

Liangliang Zhang

Zhongpu Xia

Kecheng Xu

Yajia Zhang

Hyun Chul Lee

Shuai Li

Guang Yang

According to one embodiment, when a predicted trajectory is received, a set of one or more features are extracted from at least some of the trajectory points of the predicted trajectory. The predicted trajectory is predicted using a prediction method or algorithm based on perception data perceiving an object within a driving environment surrounding an autonomous driving vehicle (ADV). The extracted features are fed into a predetermined DNN model to generate a similarity score. The similarity score represents a difference or similarity between the predicted trajectory and a prior actual trajectory that was used to train the DNN model. The similarity score can be utilized to evaluate the prediction method that predicted the predicted trajectory.

Evaluation framework for predicted trajectories in autonomous driving vehicle traffic prediction

A surrounding environment of an autonomous vehicle is perceived to identify one or more vehicles nearby. For each of the identified vehicles, based on a current location of the identified vehicle, vehicle-independent information is obtained to determine context surrounding the identified vehicle, where the vehicle-independent information includes vehicle surrounding information that defines physical constraints imposed on the identified vehicle. For each of the identified vehicles, one or more trajectories for the identified vehicle are predicted based at least in part on the vehicle-independent information associated with the identified vehicle. The autonomous vehicle is controlled based on the one or more predicted trajectories of the one or more identified vehicles.

Method and system to predict one or more trajectories of a vehicle based on context surrounding the vehicle

In one embodiment, in response to perception data perceiving a driving environment surrounding an ADV, a map image of a map covering a location associated with the driving environment is obtained. An image recognition is performed on the map image to recognize one or more objects from the map image. An object may represent a particular road, a building structure (e.g., a parking lot, an intersection, or a roundabout). One or more features are extracted from the recognized objects, where the features may indicate or describe the traffic condition of the driving environment. Behaviors of one or more traffic participants perceived from the perception data are predicted based on the extracted features. A trajectory for controlling the ADV to navigate through the driving environment is planned based on the predicted behaviors of the traffic participants. A traffic participant can be a vehicle, a cyclist, or a pedestrian.

Traffic prediction based on map images for autonomous driving

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.

Group driving style learning framework for autonomous vehicles

In one embodiment, an intelligent and prompt alarm system is designed on autonomous driving vehicles to help autonomous driving vehicles to communicate to human drivers more vigilantly and promptly, and to improve human driver's performance to take over when an autonomous driving failure occurs. In one embodiment, an alarm system can be developed several levels: 1) basic warning, 2) risk warning, and 3) emergency/take-over alarming.

Alarm system of autonomous driving vehicles (ADVs)

According to one embodiment, a first image identifier (ID) is received identifying a first of a first set of images, where the first image is currently displayed at a mobile device of a user. A number of additional images the user likely accesses from the first image in sequence is determined based on user interactions of a current browsing session and user interactions of a prior browsing session associated with the user. A second set of images are identified based on the number of additional images the user likely accesses. A sequential order is determined based on rankings of the images in the second set in view of a set of image selection rules. The second set of images is transmitted to the mobile device to be displayed on the mobile device in sequence one at a time.

Method for processing and rendering feed-like based images for mobile devices

In one embodiment, systems and methods are disclosed for a planning-driven framework for an driving vehicle (ADV) driving decision system. Driving decisions are classified into at least seven categories, including: conservative decision, aggressive decision, conservative parameters, aggressive parameters, early decision, late decision, and non-decision problem. Using the outputs of an ADV decision planning module, an ADV driving decision problem is identified, categorized, and diagnosed. A local driving decision improvement can be determined and executed in a short time frame on the ADV. For a long term solution, if needed, the driving decision problem can be uploaded to an analytics server. The driving decision problems from a large plurality of ADVs can be aggregated and analyzed for improving the ADV decisions system for all ADVs.

Planning feedback based decision improvement system for autonomous driving vehicle

In response to sensor data received from sensors mounted on an autonomous vehicle, a surrounding environment is perceived based on the sensor data. The surrounding environment includes multiple sub-environments. For each of the sub-environments, one of a plurality of driving scenario handlers associated with the sub-environment is identified, each driving scenario handler corresponding to one of a plurality of driving scenarios. The identified driving scenario handler is invoked to determine an individual driving condition within the corresponding sub-environment. An overall driving condition for the surrounding environment is determined based on the individual driving conditions provided by the identified driving scenario handlers. A route segment is planned based on the overall driving condition of the surrounding environment, the route segment being one of a plurality of route segments associated with a route. The autonomous vehicle is controlled and driven based on the planned route segment.

Method and system to construct surrounding environment for autonomous vehicles to make driving decisions

Route segment information is received from a first autonomous vehicle over a network. The route segment information includes one or more route segments and estimated entrance times, each of the entrance times being associated with one of the route segments and representing a time the first autonomous vehicle enters the route segment. Whether the first autonomous vehicle is within a specific route segment is determined based on an entrance time associated with the specific route segment and a current location of the first autonomous vehicle. If the first autonomous vehicle is within the specific route segment, a request is sent to invite the first autonomous vehicle to join a vehicle group of one or more vehicles associated with the specific route segment. The vehicle group is one of a plurality of vehicle groups that were determined based on route segment information received from a plurality of autonomous vehicles.

Method and system to manage vehicle groups for autonomous vehicles

The present disclosure discloses a method and an apparatus for generating an autonomous driving strategy. A specific implementation of the method comprises: measuring state information of an instant vehicle and ambient scene information, the ambient scene information comprising: state information of an impediment vehicle, road structure information, and traffic scene information of the instant vehicle; determining a running track of the impediment vehicle according to the state information of the impediment vehicle within a predetermined period of time; determining a first mapping relation based on the state information of the impediment vehicle within the predetermined period of time and the running track of the impediment vehicle; and generating the autonomous driving strategy of the instant vehicle based on the first mapping relation, the road structure information, the state information of the instant vehicle and the traffic scene information of the instant vehicle.

Method and apparatus for generating automatic driving strategy

In one embodiment, an image analysis is performed on an image captured using a camera mounted on an autonomous vehicle, the image representing an exterior environment of an autonomous vehicle. Localization information surrounding the autonomous vehicle is obtained at a point in time. A perception of an audience external to the autonomous vehicle is determined based on the image analysis and the localization information. One or more content items are received from one or more content servers over a network in response to the perception of the audience. A first content item selected from the one or more content items is displayed on a display device mounted on an exterior surface of the autonomous vehicle.

System and method for providing content in autonomous vehicles based on perception dynamically determined at real-time

A first reference line representing a trajectory from a first location to a second location associated with an autonomous driving vehicle (ADV) is received. The first reference line is segmented into a number of reference line segments. For each of the reference line segments, a quintic polynomial function is defined to represent the reference line segment. An objective function is determined based on the quintic polynomial functions of the reference line segments. An optimization is performed on coefficients of the quintic polynomial functions in view of a set of constraints associated with the reference line segments, such that an output of the objective function reaches minimum while the constraints are satisfied. A second reference line is then generated based on the optimized parameters or coefficients of the quintic polynomial functions of the objective function. The second reference line is then utilized to plan and control the ADV.

Non-linear reference line optimization method using piecewise quintic polynomial spiral paths for operating autonomous driving vehicles

In one embodiment, systems and methods are disclosed for evaluating autonomous driving vehicle (ADV) driving decisions. A driving scenario is selected, such as a route or destination or type of driving condition. ADV planning and control modules are turned off and do not control the ADV. As a user drives the ADV, sensors detect and periodically log a plurality of objects external to the ADV. Driving control inputs of the human driver are also logged periodically. An ADV driving decision module generates driving decisions with respect to each object detected by the sensors. The ADV driving decisions are logged, but are not used to control the ADV. An ADV driving decision is identified in the logs, and a corresponding human driving decision is extracted, graded, and compared to the ADV driving decision. The ADV driving decision can be graded using the logs and graded human driving decision.

Evaluation framework for decision making of autonomous driving vehicle

Responsive to sensor data received from one or more sensors of an autonomous vehicle, one or more predicted trajectories are generated, with each of the predicted trajectories having an associated probability. One or more driving scenarios that trigger gesture recognition are identified. For each of the identified driving scenarios, one or more gestures from one or more vehicles are detected in accordance with a gesture detection protocol. One or more gestures from the autonomous vehicle are emitted for communication with the vehicles in accordance with a gesture emission protocol based on the detected gestures. The predicted trajectories are modified based on the detected gestures, the emitted gestures and the associated probabilities of the predicted trajectories. The autonomous vehicle is controlled based on the modified predicted trajectories.

Method and system to predict vehicle traffic behavior for autonomous vehicles to make driving decisions

In one embodiment, a first image of a physical object external to an autonomous vehicle is received, where the first image is captured by an image sensor attached to the autonomous vehicle. An image recognition is performed on the first image to derive one or more keywords related to the physical object. A list of one or more content items are identified based on the one or more keywords. A first content item selected from the list of content items is augmented onto the first image to generate a second image. The second image is displayed on a display device within the autonomous vehicle.

Growing community of inventors

Sunnyvale, CA, United States of America

Liyun Li