Tusimple, Inc.

Beijing Tusen Zhitu Technology Co., Ltd.

Yufei Zhao

Liu Liu

Wutu Lin

Xing Sun

Zijie Xuan

Kai-Chieh Ma

Hunter Scott Willoughby

Dishi Li

Scott Douglas Foster

Yuwei Wang

Xiaomin Zhang

Yilun Chen

Guangyu Li

Lei Wang

Yujia Wu

Haoming Sun

Xiaodi Hou

Tianqu Shao

Fan Mo

Xuren Zhou

Weiyang Zhang

An example method includes detecting, via sensor data collected from sensors located on the AV, an upcoming object located on a roadway. The method further includes determining, from the sensor data, a relative distance and a relative direction of the upcoming object with respect to the autonomous vehicle. The method further includes mapping the upcoming object to an absolute location with respect to the roadway based on map data that describes upcoming topology of the roadway and a location of the autonomous vehicle. The method further includes associating the upcoming object with a lane of the roadway based on the absolute location mapped to the upcoming object and based on lane geometry data for the roadway. The method further includes operating the autonomous vehicle based on a relationship between the lane associated with the upcoming object and a current lane in which the autonomous vehicle is located.

Systems and methods for operating an autonomous vehicle

A system for implementing a lane bias maneuver to negotiate a curved road comprises an autonomous vehicle and a control device. The control device determines that the autonomous vehicle is approaching a curved road. The control device determines a road radius of the curved road. The control device calculates a first lane bias adjustment amount associated with a road curvature of the curved road based on the road radius. The control device calculates a second lane bias adjustment amount associated with a trailer angle between a trailer and a semi-truck tractor unit of the autonomous vehicle. The control device calculates a total lane bias adjustment amount by combining the first and second lane bias adjustment amounts. The control device instructs the autonomous vehicle to perform a lane bias maneuver that comprises driving the autonomous vehicle off-center in a curved lane based on the total lane bias adjustment amount.

Lane bias maneuver for autonomous vehicles to negotiate a curved road

A control device associated with an autonomous vehicle receives sensor data and detects that the autonomous vehicle is approaching a railroad crossing based on the sensor data. The control device determines a target lane to travel while crossing the railroad. The target lane is a lane that has available space with at least a length of the autonomous vehicle on the other side of the railroad as opposed to a side of the railroad where the autonomous vehicle is currently traveling. The control device instructs the autonomous vehicle to travel on the target lane. The control device determines that a train is approaching the railroad crossing and waits for the train to pass the railroad crossing. The control device determines that the train has passed the railroad crossing. The control device instructs the autonomous vehicle to cross the railroad.

Autonomous vehicle navigation in response to an oncoming train on a railroad track

An autonomous vehicle (AV) includes features that allows the AV to perform safe driving operations. An example method includes detecting that a motorcycle is operating on a roadway on which the autonomous vehicle is located. The method further includes classifying a behavior state of the motorcycle based on a location of the motorcycle relative to a split zone that extends between and into two adjacent lanes of the roadway. The behavior state indicates whether the motorcycle is lane splitting. The method further includes determining, based on the behavior state of the motorcycle, a lane permission parameter that controls whether a given trajectory for the autonomous vehicle can extend into one of the two adjacent lanes. The method further includes causing the autonomous vehicle to operate in accordance with a trajectory that satisfies the lane permission parameter based on transmitting instructions related to the trajectory to subsystems of the autonomous vehicle.

A system and method for autonomous vehicle control to minimize energy cost are disclosed. A particular embodiment includes: generating a plurality of potential routings and related vehicle motion control operations for an autonomous vehicle to cause the autonomous vehicle to transit from a current position to a desired destination; generating predicted energy consumption rates for each of the potential routings and related vehicle motion control operations using a vehicle energy consumption model; scoring each of the plurality of potential routings and related vehicle motion control operations based on the corresponding predicted energy consumption rates; selecting one of the plurality of potential routings and related vehicle motion control operations having a score within an acceptable range; and outputting a vehicle motion control output representing the selected one of the plurality of potential routings and related vehicle motion control operations.

System and method for autonomous vehicle control to minimize energy cost

A control device associated with an autonomous vehicle receives sensor data and detects that the autonomous vehicle is approaching a railroad crossing based on the sensor data. The control device determines that the railroad crossing is closed from the sensor data. The control device determines one or more re-routing options from map data. The control device determines whether at least one re-routing option reaches a predetermined destination of the autonomous vehicle. In response to determining that the at least one re-routing option reaches the predetermined destination, the control device selects a particular re-routing option based at least on determining that the autonomous vehicle is able to travel according to the particular re-routing option autonomously. The control device instructs the autonomous vehicle to re-route according to the particular re-routing option.

Autonomous vehicle navigation in response to a closed railroad crossing

A system and method for providing multiple agents for decision making, trajectory planning, and control for autonomous vehicles are disclosed. A particular embodiment includes: partitioning a multiple agent autonomous vehicle control module for an autonomous vehicle into a plurality of subsystem agents, the plurality of subsystem agents including a deep computing vehicle control subsystem and a fast response vehicle control subsystem; receiving a task request from a vehicle subsystem; determining if the task request is appropriate for the deep computing vehicle control subsystem or the fast response vehicle control subsystem based on content of the task request or a context of the autonomous vehicle; dispatching the task request to the deep computing vehicle control subsystem or the fast response vehicle control subsystem based on the determination; causing execution of the deep computing vehicle control subsystem or the fast response vehicle control subsystem by use of a data processor to produce a vehicle control output; and providing the vehicle control output to a vehicle control subsystem of the autonomous vehicle.

System and method for providing multiple agents for decision making, trajectory planning, and control for autonomous vehicles

A system and method for real world autonomous vehicle trajectory simulation may include: receiving training data from a data collection system; obtaining ground truth data corresponding to the training data; performing a training phase to train a plurality of trajectory prediction models; and performing a simulation or operational phase to generate a vicinal scenario for each simulated vehicle in an iteration of a simulation. Vicinal scenarios may correspond to different locations, traffic patterns, or environmental conditions being simulated. Vehicle intention data corresponding to a data representation of various types of simulated vehicle or driver intentions.

System and method for real world autonomous vehicle trajectory simulation

A system and method for real world autonomous vehicle perception simulation are disclosed. A particular embodiment includes: configuring a sensor noise modeling module to produce simulated sensor errors or noise data with a configured degree, extent, and timing of simulated sensor errors or noise based on a set of modifiable parameters; using the simulated sensor errors or noise data to generate simulated perception data by simulating errors related to constraints of one or more of a plurality of sensors, and by simulating noise in data provided by a sensor processing module corresponding to one or more of the plurality of sensors; and providing the simulated perception data to a motion planning system for the autonomous vehicle.

Perception simulation for improved autonomous vehicle control

A system includes an autonomous vehicle (AV) configured to travel along a road and a control device communicatively coupled to the AV. The control device determines that the AV should move from a current lane of the road to an adjacent lane of the road. The control device determines two or more candidate windows into which the AV may move in the adjacent lane. Each candidate window corresponds to a space in the adjacent lane between two vehicles traveling in the adjacent lane. The control device determines that the AV should move into a first candidate window, and, in response to this determination, causes the AV to begin moving along a trajectory leading to the first candidate window (e.g., by accelerating or decelerating).

Proactive lane change for autonomous vehicles

An autonomous vehicle (AV) includes features that allows the AV to comply with applicable regulations and statutes for performing safe driving operation. An example method includes detecting that a group of motorcycles is operating on a roadway on which the AV is located. The group of motorcycles are each located within a pre-determined distance away from one another. The method further includes determining an aggregate footprint area that surrounds respective locations of the group of motorcycles. The method further includes causing navigation of the autonomous vehicle that avoids penetration of the aggregate footprint area based on transmitting navigation instructions to one or more subsystems of the autonomous vehicle.

A control device associated with an autonomous vehicle receives sensor data and detects that the autonomous vehicle is approaching a railroad crossing based on the sensor data. The control device determines that no train is approaching the railroad crossing from the sensor data. The control device detects an indication of a stopped vehicle in front of the autonomous vehicle and behind the railroad crossing. The control device determines whether the stopped vehicle is associated with a mandatory stop rule. The mandatory stop rule indicates vehicles carrying hazardous materials have to stop behind the railroad crossing even when no train is approaching or traveling through the railroad crossing. If it is determined that the stopped vehicle is associated with the mandatory stop rule, the control device waits behind the stopped vehicle until the stopped vehicle crosses the railroad crossing and instructs the autonomous vehicle to cross the railroad.

Autonomous vehicle navigation in response to a stopped vehicle at a railroad crossing

An autonomous vehicle simulation system for analyzing motion planners is disclosed. A particular embodiment includes: receiving map data corresponding to a real world driving environment; obtaining perception data and configuration data including pre-defined parameters and executables defining a specific driving behavior for each of a plurality of simulated dynamic vehicles; generating simulated perception data for each of the plurality of simulated dynamic vehicles based on the map data, the perception data, and the configuration data; receiving vehicle control messages from an autonomous vehicle control system; and simulating the operation and behavior of a real world autonomous vehicle based on the vehicle control messages received from the autonomous vehicle control system.

Autonomous vehicle simulation system for analyzing motion planners

A system and method for using human driving patterns to manage speed control for autonomous vehicles are disclosed. A particular embodiment includes: generating data corresponding to desired human driving behaviors; training a human driving model module using a reinforcement learning process and the desired human driving behaviors; receiving a proposed vehicle speed control command; determining if the proposed vehicle speed control command conforms to the desired human driving behaviors by use of the human driving model module; and validating or modifying the proposed vehicle speed control command based on the determination.

System and method for using human driving patterns to manage speed control for autonomous vehicles

Systems and methods for autonomous lane level navigation are disclosed. In one aspect, a control system for an autonomous vehicle includes a processor and a computer-readable memory configured to cause the processor to receive a partial high-definition (HD) map that defines a plurality of lane segments that together represent one or more lanes of a roadway, the partial HD map including at least a current lane segment. The processor is also configured to generate auxiliary global information for each of the lane segments in the partial HD map. The processor is further configured to generate a subgraph including a plurality of possible routes between the current lane segment and the destination lane segment using the partial HD map and the auxiliary global information, select one of the possible routes for navigation based on the auxiliary global information, and generate lane level navigation information based on the selected route.

Growing community of inventors

San Diego, CA, United States of America

Yufei Zhao