Tusimple, Inc.

Siyuan Liu

Xiaodi Hou

Mingdong Wang

Zehua Huang

Lingting Ge

Chenzhe Qian

Yijie Wang

Chenyang Li

Wei Liu

Lei Su

Zhipeng Yan

Yixin Yang

Dinghua Li

Jiangming Jin

Kai Zhou

Yifan Gong

A method of lane detection for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs include instructions, which when executed by a computing device, cause the computing device to perform the following steps comprising: generating a ground truth associated with lane markings expressed in god's view; receiving features from at least one of a hit-map image and a fitted lane marking, wherein the hit-map image includes a classification of pixels that hit a lane marking, and the fitted lane marking includes pixels optimized based on the hit-map image; and training a confidence module based on the features and the ground truth, the confidence module configured to determine on-line whether a fitted lane marking is reasonable, using parameters that express a lane marking in an arc.

Verification module system and method for motion-based lane detection with multiple sensors

Image processing techniques are described to obtain an image from a camera located on a vehicle while the vehicle is being driven, cropping a portion of the obtained image corresponding to a region of interest, detecting an object in the cropped portion, adding a bounding box around the detected object, determining position(s) of reference point(s) on the bounding box, and determining a location of the detected object in a spatial region where the vehicle is being driven based on the determined one or more positions of the second set of one or more reference points on the bounding box.

Perception system for autonomous vehicles

A system and method for proximate vehicle intention prediction for autonomous vehicles are disclosed. A particular embodiment is configured to: receive perception data associated with a host vehicle; extract features from the perception data to detect a proximate vehicle in the vicinity of the host vehicle; generate a trajectory of the detected proximate vehicle based on the perception data; use a trained intention prediction model to generate a predicted intention of the detected proximate vehicle based on the perception data and the trajectory of the detected proximate vehicle; use the predicted intention of the detected proximate vehicle to generate a predicted trajectory of the detected proximate vehicle; and output the predicted intention and predicted trajectory for the detected proximate vehicle to another subsystem.

System and method for proximate vehicle intention prediction for autonomous vehicles

A vehicle position and velocity estimation system based on camera and LIDAR data is disclosed. An embodiment includes: receiving input object data from a subsystem of a vehicle, the input object data including image data from an image generating device and distance data from a distance measuring device, the distance measuring device comprising one or more LIDAR sensors; determining a first position of a proximate object near the vehicle from the image data; determining a second position of the proximate object from the distance data; correlating the first position and the second position by matching the first position of the proximate object detected in the image data with the second position of the same proximate object detected in the distance data; determining a three-dimensional (3D) position of the proximate object using the correlated first and second positions; and using the 3D position of the proximate object to navigate the vehicle.

System and method for vehicle position and velocity estimation based on camera and LIDAR data

Devices, systems and methods for fusing scenes from real-time image feeds from on-vehicle cameras in autonomous vehicles to reduce redundancy of the information processed to enable real-time autonomous operation are described. One example of a method for improving perception in an autonomous vehicle includes receiving a plurality of cropped images, wherein each of the plurality of cropped images comprises one or more bounding boxes that correspond to one or more objects in a corresponding cropped image; identifying, based on the metadata in the plurality of cropped images, a first bounding box in a first cropped image and a second bounding box in a second cropped image, wherein the first and second bounding boxes correspond to a common object; and fusing the metadata corresponding to the common object from the first cropped image and the second cropped image to generate an output result for the common object.

Image fusion for autonomous vehicle operation

A vehicle position and velocity estimation based on camera and LIDAR data are disclosed. A particular embodiment includes: receiving input object data from a subsystem of an autonomous vehicle, the input object data including image data from an image generating device and distance data from a distance measuring device; determining a two-dimensional (2D) position of a proximate object near the autonomous vehicle using the image data received from the image generating device; tracking a three-dimensional (3D) position of the proximate object using the distance data received from the distance measuring device over a plurality of cycles and generating tracking data; determining a 3D position of the proximate object using the 2D position, the distance data received from the distance measuring device, and the tracking data; determining a velocity of the proximate object using the 3D position and the tracking data; and outputting the 3D position and velocity of the proximate object relative to the autonomous vehicle.

Image processing techniques are described to receive bounding box information that describes a bounding box located around a detected object in an image, determine one or more positions of one or more reference points on the bounding box, determine, for each reference point, 3D world coordinates of a point of intersection of the reference point and the road surface, and assign the 3D world coordinates of the one or more reference points to a location of the detected object.

Depth estimation in images obtained from an autonomous vehicle camera

Image processing techniques are described to select and crop a region of interest from an image obtained from a camera located on or in a vehicle, such as an autonomous semi-trailer truck. The region of interest can be identified by selecting one or more reference points and determining one or more positions of the one or more reference points on the image obtained from the camera. As an example, a location of two reference points may be 500 meters and 1000 meters in front of a location of autonomous vehicle, where the front of the autonomous vehicle is an area towards which the autonomous vehicle is being driven.

Partitioning images obtained from an autonomous vehicle camera

The present disclosure provides a method, an apparatus and a system for multi-module scheduling, capable of solving the problem associated with inconsistency in data inputted to a computing module in the multi-module scheduling technique in the related art. The method includes: reading, by a master process, a pre-stored configuration file storing a directed computation graph; initializing, by the master process, states of all the nodes and connecting edges in the directed computation graph initially in computation in a current computing period; determining a node to be called based on the computation direction in the directed computation graph and the states of the nodes, the node to be called comprising a node having all of its input edges in a complete state; transmitting, to the computing module in the slave process corresponding to the node to be called, a call request of Remote Process Call (RPC) to execute the computing module; updating the state of the node and the state of each output edge of the node upon receiving a response to the call request; and proceeding with a next computing period upon determining that the states of all the nodes have been updated.

Method, apparatus, and system for multi-module scheduling

The present disclosure provides a method, an apparatus and a system for multi-module scheduling, capable of solving at least one of the problems associated with the multi-module scheduling technique in the related art, i.e., inconsistency in data inputted to a computing module, and a significant delay or low throughput in data transmission between computing modules. The method includes: reading, by a master process, a pre-stored configuration file storing a directed computation graph; initializing, by the master process, states of the nodes and connecting edges in a current computing period; determining a node to be called based on the computation direction of the directed computation graph and the states of the nodes, the node to be called comprising a node having all of its input edges in a complete state; transmitting, to the computing module in the slave process corresponding to the node to be called, a call request of Remote Process Call (RPC) to execute the computing module; updating the state of the node and the state of each output edge of the node upon receiving a response to the call request; and proceeding with a next computing period after determining that the states of all the nodes in the directed computation graph have been updated.

Growing community of inventors

San Diego, CA, United States of America

Siyuan Liu