Pony Ai Inc.

Jie Hou

Xiang Yu

Jun Peng

Tiancheng Lou

Hao Song

Sinan Xiao

Yiming Liu

Zhuo Zhang

Bo Xiao

Tianyi Li

Zichao Qi

Kai Chen

Nengxiu Deng

Zhenhao Pan

Systems, methods, and non-transitory computer readable media configured to generate enhanced training information. Training information may be obtained. The training information may characterize behaviors of moving objects. The training information may be determined based on observations of the behaviors of the moving objects. Behavior information may be obtained. The behavior information may characterize a behavior of a given object. Enhanced training information may be generated by inserting the behavior information into the training information.

Enhanced training information generation

A lens mount apparatus mountable on a vehicle and a method for controlling a lens mount apparatus are described. The lens mount apparatus includes a plurality of lenses concentrically arranged around a center, and the plurality of lenses include a first lens having a first focal length and a second lens having a second focal length that is shorter than the first focal length. The method includes positioning one of the plurality of lenses, such that one of the lenses that has a focal length suitable for capturing an object is used for image capturing.

Camera multi-lens mount for assisted-driving vehicle

Systems, methods, and non-transitory computer readable media configured to generate enhanced three-dimensional information. Three-dimensional information of a scene may be obtained. The three-dimensional information may define a three-dimensional point cloud model of the scene. The three-dimensional information may be determined based on distances of the scene from a location. Image information may be obtained. The image information may define one or more images of an object. The object may be identified based on the image information. A three-dimensional point cloud model of the object may be obtained. Enhanced three-dimensional information of the scene may be generated by inserting the three-dimensional point cloud model of the object into the three-dimensional point cloud model of the scene.

Enhanced three-dimensional training data generation

A system included and a computer-implemented method performed in an autonomous-driving vehicle are described. The system performs: detecting one or more movable objects; determining a target movable object from the one or more detected objects; determining a manner of generating a directed alert notification selectively toward the target movable object; and causing a directed alert notification of the determined manner to be generated toward the target movable object.

Directed alert notification by autonomous-driving vehicle

Systems and methods directed to projecting a current trajectory path of the autonomous vehicle on a surface of road is disclosed. In some embodiments, an autonomous vehicle with a light projector is disclosed, where the light projector is on a top surface of an autonomous vehicle. Additionally, in some embodiments, the autonomous vehicle may include an electronic control unit for controlling an operation of the light projector, where the electronic control unit detects whether the autonomous vehicle is turned on. In further embodiments, the electronic control unit receives data of an environmental condition surrounding the autonomous vehicle and receives an upcoming trajectory path of the autonomous vehicle. The electronic control unit may also project a light from the light projector onto a surface of a road indicating the upcoming trajectory path of the autonomous vehicle.

System and method for projecting trajectory path of an autonomous vehicle onto a road surface

Systems, methods, and non-transitory computer-readable media are provided for implementing a preemptive control for an autonomous vehicle to improve ride quality. Data from one or more sensors onboard the autonomous vehicle can be acquired. A surface imperfection of a road can be identified from the data. A next action for the autonomous vehicle can be determined based on the surface imperfection. A signal can be outputted that causes the autonomous vehicle to act in accordance with the next action.

Systems and methods for implementing a preemptive control for an autonomous vehicle to improve ride quality

A system included and a computer-implemented method performed in one of a plurality of self-driving vehicles that are connected through a network are described. The system performs: processing image data of one or more scene images received by said one of the plurality of self-driving vehicles, to detect one or more objects included in the one or more scene images; determining a target object from the one or more detected objects at least based on the processed image data; predicting movement of the target object at least based on a current position and a current movement state of the target object; and performing a self-driving operation to drive said one of the plurality of self-driving vehicles based on the predicted movement of the target object.

Coordinated control of self-driving vehicles under emergency situations

Embodiments disclosed herein are directed to autonomous vehicles comprising at least one interior compartment including: at least one table; at least one seating unit; at least one closet; at least one window configured to transition between a substantially transparent state and a substantially opaque state and to display at least navigational information; at least one vanity; at least one storage area; or combinations thereof; wherein the vehicle is configured to operate in at least an autonomous mode. In some instance, the vehicle may not include steering equipment (e.g., steering wheel) and/or acceleration or deceleration equipment (e.g., a gas or brake pedal).

Growing community of inventors

San Francisco, CA, United States of America

Jie Hou