阅读说明：本技术 自动将自主驾驶车辆的转向返回至中心位置的系统和方法 (System and method for automatically returning steering of an autonomously driven vehicle to a central location ) 是由 朱帆 于 2020-12-10 设计创作，主要内容包括：实施例公开了一种自动将自主驾驶车辆(ADV)的转向返回至中心位置的系统和方法。根据第一方面,系统通过向自主驾驶车辆(ADV)施加转向命令来执行转弯。响应于转弯,系统确定ADV的当前百分比转向、速度和行驶方向。系统基于确定的ADV的速度从一个或多个转向返回轨迹配置文件中选择转向返回轨迹配置文件。系统基于选择生成转向返回轨迹。基于生成的转向返回轨迹,系统控制ADV将转向返回到中心位置。(Embodiments disclose a system and method for automatically returning steering of an autonomous vehicle (ADV) to a central location. According to a first aspect, the system performs a turn by applying a steering command to an Autonomous Driving Vehicle (ADV). In response to the turn, the system determines the current percent steering, speed, and direction of travel of the ADV. The system selects a steering return trajectory profile from the one or more steering return trajectory profiles based on the determined speed of the ADV. The system generates a turn-around trajectory based on the selection. Based on the generated turn-back trajectory, the system controls the ADV to return the turn to the center position.)

1. A method for operating an autonomously driven vehicle, ADV, the method comprising:

performing a turn by applying a steering command to the ADV;

determining a current percent steering, speed, and direction of travel of the ADV in response to the turn;

selecting a steering return trajectory profile from the one or more steering return trajectory profiles based on the determined speed of the ADV;

generating a steering return trajectory according to the selection; and

controlling the ADV to return the steering to the center position based on the generated steering return trajectory.

2. The method of claim 1, wherein generating a turn-around return trajectory based on the selected turn-around return trajectory profile comprises:

trimming the turn back trajectory profile with a percentage turn to match the current percentage turn of the ADV; and

and splicing the trimmed steering return track configuration file to the current driving direction and the current position of the ADV to generate a steering return track.

3. The method of claim 1, wherein performing the turn comprises performing a sharp turn, wherein for the sharp turn, a steering wheel is turned at an angle greater than 90 degrees.

4. The method of claim 1, wherein each of the one or more turn-around return trajectory profiles is associated with a particular speed.

5. The method of claim 1, wherein each of the one or more turn-back trajectory profiles is generated using about 100% turn-back to about 0% turn to the left (center turn) and/or about 100% turn-back to about 0% turn to the right (center turn).

6. The method of claim 1, wherein each turn return trajectory profile includes a plurality of trajectory segments, and each trajectory segment is associated with a percentage turn.

7. The method of claim 1, wherein each of the one or more steering return trajectory profiles represents a driving trajectory after a turn to return the steering of the ADV to center steering without applying a steering command.

8. A method for generating a steering return trajectory profile offline, the method comprising:

determining a trajectory of the vehicle returning the steering to the center position at a first speed, wherein the vehicle has performed a left or right turn;

determining a plurality of segments of the trajectory;

associating percentage turn information for each of a plurality of segments; and

generating one or more turn-back trajectory profiles based on the trajectory and segmented percentage turn information, wherein the turn-back trajectory profiles are utilized during autonomous driving of an Autonomously Driven Vehicle (ADV) to return to an initial turn position after a turn-turning operation.

9. The method of claim 8, further comprising:

determining another trajectory of the vehicle at a second speed to produce another turn-around return trajectory; and

one or more turn-around return trajectory profiles are generated based on another trajectory.

10. The method of claim 8, wherein each of the one or more turn-around return trajectory profiles is associated with a particular velocity, and the velocity is used for trajectory selection.

11. The method of claim 8, wherein a trajectory corresponding to a simulated environment or a real environment is generated for the vehicle.

12. A data processing system comprising:

one or more processors; and

a memory coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations of the method of any of claims 1-11.

Technical Field

Embodiments of the present disclosure relate generally to operating an autonomous vehicle. More particularly, embodiments of the present disclosure relate to a steering wheel auto-zero based path planning system for Autonomous Driving Vehicles (ADV).

Background

A vehicle operating in an autonomous mode (e.g., unmanned) may relieve some of the driving-related responsibilities of the occupants, particularly the driver. When operating in an autonomous mode, the vehicle may navigate to various locations using onboard sensors, allowing the vehicle to travel with minimal human interaction or in some situations without any passengers.

The steering system of the vehicle has the ability to return to its center (zero) position without any input. This auto-zeroing may provide a smooth and comfortable path curve when the vehicle is recovering from a turn.

Disclosure of Invention

In a first aspect, there is provided a method for operating an ADV, the method comprising:

performing a turn by applying a steering command to the ADV;

determining a current percent steering, speed, and direction of travel of the ADV in response to the turn;

selecting a steering return trajectory profile from the one or more steering return trajectory profiles based on the determined speed of the ADV;

generating a steering return trajectory according to the selection; and

controlling the ADV to return the steering to the center position based on the generated steering return trajectory.

In a second aspect, a method for generating a steering return trajectory profile offline is provided, the method comprising:

determining a trajectory of the vehicle returning the steering to the center position at a first speed, wherein the vehicle has performed a left or right turn;

determining a plurality of segments of the trajectory;

associating percentage turn information for each of a plurality of segments; and

generating one or more turn-back trajectory profiles based on the trajectory and segmented percentage turn information, wherein the turn-back trajectory profiles are utilized during autonomous driving of an Autonomously Driven Vehicle (ADV) to return to an initial turn position after a turn-turning operation.

In a third aspect, there is provided a data processing system comprising:

one or more processors; and

a memory coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the operations of the method as described in the first aspect or the operations of the method as described in the second aspect.

According to the present invention, the ADV can be controlled to automatically turn and turn it back to the center position.

Drawings

Embodiments of the present disclosure are illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references indicate similar elements.

FIG. 1 is a block diagram illustrating a networked system according to one embodiment.

FIG. 2 is a block diagram illustrating an example of an autonomously driven vehicle according to one embodiment.

3A-3B are block diagrams illustrating an example of an autonomous driving system for use with an autonomously driven vehicle according to one embodiment.

FIG. 4 is a block diagram illustrating an auto-zero module according to one embodiment.

Figure 5 illustrates an example of time delays for an ADV to turn around using auto-zero steering according to one embodiment.

FIG. 6 illustrates a steer return trajectory profile for a vehicle, according to one embodiment.

Figure 7 is a flow diagram illustrating a method performed by an ADV according to one embodiment.

FIG. 8 is a block diagram illustrating an offline processing module according to one embodiment.

FIG. 9 is a flow diagram illustrating a method performed by an offline process, according to one embodiment.

Detailed Description

Various embodiments and aspects of the disclosure will be described with reference to details discussed below, and the accompanying drawings will illustrate the various embodiments. The following description and drawings are illustrative of the disclosure and are not to be construed as limiting the disclosure. Numerous specific details are described to provide a thorough understanding of various embodiments of the present disclosure. However, in certain instances, well-known or conventional details are not described in order to provide a concise discussion of embodiments of the present disclosure.

Reference in the specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the disclosure. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment.

Autonomous driving path planning may use various path planning algorithms/models to calculate trajectories. The trajectory of performing a 90 degree or U-turn may be calculated by such an algorithm. Such trajectories may have a wide turning path curve, and steering the vehicle from a large steering angle back to a center position (e.g., zero degrees) may cause the vehicle path to overshoot/oscillate, which may not be suitable for sharp turns.

Embodiments disclose a system and method for automatically turning an Autonomous Driving Vehicle (ADV) and returning the steering to a center position. According to a first aspect, the system performs a turn by applying a steering command to an Autonomous Driving Vehicle (ADV). In response to the turn, the system determines the current percent steering, speed, and direction of travel of the ADV. The system selects a steering return trajectory profile from the one or more steering return trajectory profiles based on the determined velocity of the ADV. The system generates a turn-around trajectory based on the selection. The system controls the ADV to return the steering to the center position according to the generated steering return trajectory.

According to a second aspect, an offline system generates one or more turn-around return trajectory profiles for an ADV. The system determines a trajectory for the vehicle to return steering to a center position at a first speed, wherein the vehicle has performed a left or right turn. The system determines a number of segments of the trajectory. The system associates a percentage turn information for each segment. The system generates one or more turn-back trajectory profiles based on the percentage turn information for the trajectory and segments.

Fig. 1 is a block diagram illustrating an autonomous driving network configuration according to one embodiment of the present disclosure. Referring to FIG. 1, a network configuration 100 includes an Autonomous Driving Vehicle (ADV)101 that may be communicatively coupled to one or more servers 103 and 104 via a network 102. Although one ADV is shown, multiple ADVs may be coupled to each other and/or to server 103 via network 102 and 104. The network 102 may be any type of network, such as a Local Area Network (LAN), a Wide Area Network (WAN) such as the Internet, a cellular network, a satellite network, or a combination thereof (wired or wireless). The server 103 and 104 may be any kind of server or server cluster, such as a Web or cloud server, an application server, a backend server, or a combination thereof. The server 103 and 104 may be a data analysis server, a content server, a traffic information server, an MPOI server, a location server, or the like.

ADV refers to a vehicle that may be used in an autonomous mode where the vehicle navigates through the environment with little or no operation by the driver. Such ADVs may include a sensor system having one or more sensors that are used to detect environmental information about the vehicle operating therein. The vehicle and its associated controller use the detected information to navigate through the environment. ADV101 may operate in a manual mode, a fully autonomous mode, or a partially autonomous mode.

In one embodiment, ADV101 includes, but is not limited to, an Autonomous Driving System (ADS)110, a vehicle control system 111, a wireless communication system 112, a user interface system 113, and a sensor system 115. ADV101 may also include certain common components in a typical vehicle, such as an engine, wheels, steering wheel, transmission, etc., which may be controlled by vehicle control system 111 and/or ADS 110 using various communication signals and/or commands, such as an acceleration signal or command, a deceleration signal or command, a steering signal or command, a braking signal or command, etc.

The components 110 and 115 can be communicatively coupled to each other via an interconnect, bus, network, or combination thereof. For example, the components 110 and 115 CAN be communicatively coupled to each other via a Controller Area Network (CAN) bus. The CAN bus is a vehicle bus standard intended to allow microcontrollers and devices to communicate with each other in applications without a host. It is a message-based protocol originally designed for multiple electrical wiring within an automobile, but is also used in many other situations.

Referring now to fig. 2, in one embodiment, sensor system 115 includes, but is not limited to, one or more cameras 211, a Global Positioning System (GPS) unit 212, an Inertial Measurement Unit (IMU)213, a radar unit 214, and a LIDAR unit 215. GPS system 212 may include a transceiver operable to provide location information regarding the ADV. The IMU unit 213 may sense position and orientation changes of the ADV based on inertial acceleration. Radar unit 214 may represent a system that utilizes radio signals to sense objects within the local environment of the ADV. In some embodiments, in addition to sensing objects, radar unit 214 may also sense the speed and/or heading of an object. The LIDAR unit 215 may sense objects in the environment in which the ADV is located using laser light. The LIDAR unit 215 may include one or more laser sources, laser scanners, and one or more detectors, among other system components. The camera 211 may include one or more devices to capture images of the environment surrounding the ADV. The camera 211 may be a still camera and/or a video camera. The camera may be moved mechanically, for example by mounting the camera on a rotating and/or tilting platform.

The sensor system 115 may also include other sensors, such as sonar sensors, infrared sensors, steering sensors, throttle sensors, brake sensors, and audio sensors (e.g., microphones). The audio sensor may be configured to capture sound from the environment surrounding the ADV. The steering sensor may be configured to sense a steering angle of a steering wheel, wheels of a vehicle, or a combination thereof. The throttle sensor and the brake sensor sense a throttle position and a brake position of the vehicle, respectively. In some cases, the throttle sensor and the brake sensor may be combined into an integrated throttle/brake sensor.

In one embodiment, the vehicle control system 111 includes, but is not limited to, a steering unit 201, a throttle unit 202 (also referred to as an acceleration unit), and a brake unit 203. The steering unit 201 is used to adjust the direction or the traveling direction of the vehicle. The throttle unit 202 will control the speed of the motor or engine and thus the speed and acceleration of the vehicle. The brake unit 203 decelerates the vehicle by providing friction to decelerate the wheels or tires of the vehicle. Note that the components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.

Referring again to fig. 1, wireless communication system 112 allows communication between ADV101 and external systems (e.g., devices, sensors, other vehicles, etc.). For example, the wireless communication system 112 may be in wireless communication with one or more devices directly or via a communication network (e.g., via server 103 over network 102 and 104). The wireless communication system 112 may communicate with another component or system using any cellular communication network or Wireless Local Area Network (WLAN), for example using WiFi. The wireless communication system 112 may communicate directly with devices (e.g., passenger's mobile device, display device, speakers in the vehicle 101), for example, using infrared links, bluetooth, etc. The user interface system 113 may be part of peripheral devices implemented within the vehicle 101 including, for example, keywords, touch screen display devices, microphones, speakers, and the like.

Some or all of the functions of ADV101 may be controlled or managed by ADS 110, particularly when operating in an autonomous driving mode. The ADS 110 includes the necessary hardware (e.g., processors, memory, storage) and software (e.g., operating systems, planning and routing programs) to receive information from the sensor system 115, the control system 111, the wireless communication system 112, and/or the user interface system 113, process the received information, plan a route or path from an origin to a destination, and then drive the vehicle 101 according to the planning and control information. Alternatively, the ADS 110 may be integrated with the vehicle control system 111.

For example, a user who is a passenger may specify a start location and a destination for a trip, e.g., via a user interface. ADS 110 obtains trip-related data. For example, ADS 110 may obtain location and route information from an MPOI server, which may be part of servers 103 and 104. The location server provides location services and the MPOI server provides map services and POIs for certain locations. Alternatively, such location and MPOI information may be cached locally in a persistent storage device of ADS 110.

ADS 110 may also obtain real-time traffic information from a traffic information system or server (TIS) as ADV101 moves along a route. Note that server 103 and 104 may be operated by a third party entity. Alternatively, the functionality of server 103-104 may be integrated with ADS 110. Based on the real-time traffic information, MPOI information, and location information, as well as real-time local environmental data (e.g., obstacles, objects, nearby vehicles) detected or sensed by the sensor system 115, the ADS 110 may plan an optimal route and drive the vehicle 101 according to the planned route (e.g., via the control system 111) to a specified destination safely and efficiently.

Server 103 may be a data analysis system that performs data analysis services for various clients. In one embodiment, data analysis system 103 includes a data collector 121 and a machine learning engine 122. The data collector 121 collects driving statistics 123 from various vehicles, which are conventional vehicles driven by ADVs or human drivers. The driving statistics 123 include information indicative of driving commands issued (e.g., throttle, brake, steering commands) and responses of the vehicle (e.g., speed, acceleration, deceleration, direction) captured by sensors of the vehicle at different points in time. The driving statistics 123 may further include information describing driving environments at different points in time, such as routes (including origin and destination locations), MPOIs, weather conditions, and road conditions, such as slow traffic on expressways, stopped traffic, car accidents, road construction, temporary detours, unknown obstacles, and the like.

Based on the driving statistics 123, the machine learning engine 122 generates or trains a set of rules, algorithms, and/or predictive models 124 for various purposes, including algorithms that perform turns/turns for the ADV using the turn-back trajectory and return to the center redirector. The algorithm/model 124 may then be uploaded to the ADV for real-time utilization by the ADV during autonomous driving.

In one embodiment, the data analysis system 103 includes an offline process or processing module 125. The offline process 125 may generate one or more turn-around return trajectory profiles for the ADV. In particular, different brands and/or models of vehicles may be associated with a set of turn-back trajectory profiles.

Fig. 3A and 3B are block diagrams illustrating an example of an ADS for use with an ADV according to one embodiment. System 300 may be implemented as part of ADV101 of fig. 1, including but not limited to ADS 110, control system 111, and sensor system 115. Referring to fig. 3A-3B, ADS 110 includes, but is not limited to, a location module 301, a perception module 302, a prediction module 303, a decision module 304, a planning module 305, a control module 306, a routing module 307, and an auto-zero steering module 308.

Some or all of the modules 301-308 may be implemented in software, hardware, or a combination thereof. For example, the modules may be installed in the persistent storage 352, loaded into the memory 351, and executed by one or more processors (not shown). Note that some or all of these modules may be communicatively coupled to or integrated with some of the modules of the vehicle control system 111 of FIG. 2. Some of the modules 301 and 308 may be integrated as integrated modules.

The location module 301 determines the current location of the ADV 300 (e.g., using the GPS unit 212) and manages any data related to the user's travel or route. The location module 301 (also referred to as a map and route module) manages any data related to the user's journey or route. The user may log in and specify the start location and destination of the tour, for example, through a user interface. The positioning module 301 communicates with other components of the ADV 300, such as map and route information 311, to obtain data related to the journey. For example, the location module 301 may obtain location and route information from a location server and an MPOI server. The location server provides location services and the MPOI server provides map services and POIs for certain locations, which may be cached as part of the map and route information 311. The positioning module 301 may also acquire temporal traffic information from a traffic information system or server as the ADV 300 moves along the route.

Based on the sensor data provided by the sensor system 115 and the positioning information obtained by the positioning module 301, a perception of the surrounding environment is determined by the perception module 302. The perception information may exhibit the same information as the perception of the surrounding vehicle by an ordinary driver when driving the vehicle. The perception may include, for example, lane configuration in a lane, a traffic light, another vehicle relative position, a pedestrian, a building, a crosswalk, or other traffic-related indicia (e.g., a no-pass indicia, a yield indicia), etc., such as in the form of an object. The lane configuration includes information describing one or more lanes, such as the shape of the lane (e.g., straight or curved), the width of the lane, the number of lanes in a road, one-way or two-way lanes, merge or split lanes, exit lanes, and the like.

The perception module 302 may include a computer vision system or functionality of a computer vision system to process and analyze images captured by one or more cameras in order to identify objects and/or features in the ADV environment. The objects may include traffic signals, road boundaries, other vehicles, pedestrians, and/or obstacles, etc. Computer vision systems may use object recognition algorithms, video tracking, and other computer vision techniques. In some embodiments, the computer vision system may draw a map of the environment, track objects and estimate object velocities, and the like. The perception module 302 may also detect objects based on data provided by other sensors, such as radar and/or LIDAR.

For each object, the prediction module 303 predicts the behavior of the object in the current situation. Based on the perception data, the driving environment at a specific time can be perceived in combination with a set of map or route information 311 and traffic rules 312. For example, if the object is a vehicle traveling in the opposite direction and the current driving environment includes an intersection, the prediction module 303 will predict whether the vehicle can travel straight or turn. If the perception data suggests that the intersection has no traffic lights, the prediction module 303 can predict that the vehicle may have to stop completely before entering the intersection. If the perception data suggests that the vehicle is currently located in a left-turn lane or a right-turn lane, the prediction module 303 may predict that the vehicle will be more likely to turn left or right, respectively.

For each object, the decision module 304 makes a decision on how to process the object. For example, for a particular object (e.g., another vehicle in the intersection) and its metadata describing the object (e.g., speed, direction, turn angle), the decision module 304 decides to process the encountered object (e.g., cut, yield, stop, pass). The decision module 304 may make such decisions based on a set of rules, such as traffic rules or driving rules 312, which may be stored in the persistent storage 352.

The routing module 307 is configured to provide one or more routes or paths from an origin to a destination. For a given trip, e.g., received from a user, from a start location to a destination location, the routing module 307 obtains route and map information 311 and determines all possible routes or paths from the start location to the destination location. The routing module 307 may generate a reference line in the form of a topographical map for each route it determines to reach from the start location to the destination location. The reference line is an ideal route or path that is not disturbed by other vehicles, obstacles, or other factors such as traffic conditions. That is, if there are no other vehicles, pedestrians, or obstacles on the road, the ADV should be driven exactly or closely to the reference line. The terrain map is then provided to a decision module 304 and/or a planning module 305. The decision module 304 and/or the planning module 305 detects all possible routes to select and modify the best route based on other data provided by other modules, such as traffic conditions from the location module 301, driving environment sensed by the sensing module 302, and traffic conditions predicted by the prediction module 303. The actual path or route used to control the ADV may be close to or different from the reference line provided by the routing module 307, depending on the particular driving environment at a particular point in time.

Based on the decision for each object perceived, the planning module 305 utilizes the provided reference lines based on the routing module 307 to plan the path or route of the ADV and driving parameters (e.g., distance, speed, and/or turn angle). That is, for a given object, the decision module 304 decides how to process the object, while the planning module 305 determines how to operate. For example, for a given subject, the decision module 304 decides to pass through the subject, and the planning module 305 may determine whether to pass on the left or right side of the subject. Planning and control data is generated by the planning module 305, which includes information describing how the vehicle 300 will move in the next travel cycle (e.g., the next route or path segment). For example, the planning and control data may instruct the vehicle 300 to move 10 meters at a speed of 30 miles per hour (mph) and then change to the right lane at a speed of 25 mph.

Based on the planning and control data, the control module 306 controls and drives the autonomous vehicle by sending appropriate commands or signals to the vehicle control system 111 according to the route or path given by the planning and control data. The planning and control data includes sufficient information to drive the vehicle from a first point of the route or path to a second point or route using appropriate vehicle settings or driving parameters (e.g., throttle, brake, steering commands) at different points in time along the path.

In one embodiment, the planning phase is performed in a plurality of planning periods (also referred to as driving periods), for example in each 100 millisecond (ms) time interval. For each planning or driving cycle, one or more control commands will be issued based on the planning and control data. That is, for every 100 milliseconds, the planning module 305 plans the next route segment or path segment, for example, including the target location and the time required for the ADV to reach the target location. Alternatively, the planning module 305 may further specify a particular speed, direction, and/or steering angle, etc. In one embodiment, the planning module 305 plans a route segment or path segment for the next predetermined time period (e.g., 5 seconds). For each planning cycle, the planning module 305 plans the target location for the current cycle (e.g., the next 5 seconds) based on the target locations planned in the previous cycle. The control module 306 then generates one or more control commands (e.g., throttle, brake, steering control commands) based on the current cycle of planning and control data.

Note that the decision module 304 and the planning module 305 may be integrated into one integrated module. The decision module 304 or the planning module 305 may include a navigation system or a function of a navigation system to determine a driving path for an ADV. For example, the navigation system may determine a range of speeds and heading directions that affect an ADV moving along a path that substantially avoids perceived obstacles as the ADV is driven along a road-based path to a final destination. The destination may be set according to user input via the user interface system 113. The navigation system may dynamically update the driving path while the ADV is running. The navigation system may combine data from the GPS system and one or more maps to determine the driving path of the ADV.

The decision module 304/planning module 305 may also include a collision avoidance system or the functionality of a collision avoidance system to identify, assess, avoid, or otherwise negotiate potential obstacles in the ADV environment. For example, the collision avoidance system may alter the navigation of the ADV by manipulating 111 one or more subsystems in the control system for a steering maneuver, a turning maneuver, a braking maneuver, and the like. The collision avoidance system can automatically determine feasible obstacle avoidance actions according to surrounding traffic modes, road conditions and the like. The collision avoidance system may be used to not engage in a steering maneuver when other sensor systems detect vehicles, building obstacles, etc. in the area near the ADV to be steered. The collision avoidance system can automatically select maneuvers that are both available and maximize ADV occupant safety. The collision avoidance system may select an avoidance maneuver predicted to cause the least acceleration in the passenger cabin of the ADV.

FIG. 4 is a block diagram illustrating an example of an auto-zero steering module according to one embodiment. The auto-zero steering module 308 may steer the ADV and return the steering of the ADV to a center position based on the steering return trajectory profile. Referring to fig. 4, the auto-zero steering module 308 may include sub-modules such as turn/steer 401, percent steer determiner 403, speed/direction of travel determiner 405, steer return trajectory profile selector 407, steer return trajectory generator 409, and steering controller 411. Turning/steering 401 may turn/steer the ADV such that the ADV travel direction is the direction of steering. The percent steer determiner 403 may determine the current percent steer of the ADV. The percentage diversion may be in the range of 100% to 0%. 100% may be to the left or to the right. Here, 0% turn represents the center turn position. The speed/direction of travel determiner 405 may determine a current speed and/or a current direction of travel of the ADV. The steering return trajectory profile selector 407 may select a steering return trajectory profile based on the current velocity of the ADV. The turn-around return trajectory generator 409 may generate a turn-around return trajectory based on the selected configuration file. Steering controller 411 may use the generated steering return trajectory to control steering of the ADV. Note that although auto-zero steering module 308 is illustrated as a separate module, auto-zero steering module 308 and planning module 305 may be integrated modules.

Figure 5 illustrates an example of time delays for an ADV to turn around using auto-zero steering according to one embodiment. Referring to fig. 5, a block diagram 500 shows ADV101 with a direction of travel 510 at times t0, t1, t2, and t 3. At t0, the ADS of ADV101 (e.g., ADS 110 of FIG. 3A) may have planned a turn around of ADV 101. In this case, the ADS plans a trajectory 501 to turn around ADV 101. At time t1, ADV101 turns following u-turn trajectory 501.

In one embodiment, at time t2, if it is determined that the u-turn is complete, ADV101 may determine the direction of travel, speed, and percentage turn of ADV101 based on the completion of trajectory 501. Based on the determined speed of ADV101, ADV101 selects a steer return trajectory profile associated with the speed closest to the determined speed of ADV101 (as part of steer return trajectory profile 313 of fig. 3A). There may be multiple trajectories already configured (e.g., based on previous driving data for a large number of vehicles), each corresponding to a particular vehicle speed. Here, each turn-back trajectory profile may include one or more turn-back trajectories with a range of turns (e.g., 100% turn left to 0% turn left, 100% turn right 0%) for a particular speed. The turn-back trajectory represents a driving trajectory that automatically returns the turn from 100% to the center position (0% turn) when the turn is released (e.g., no turn command). In one embodiment, the steering return trajectory may include a series of x-y points with a direction of travel and percent steering information for each x-y point. In another embodiment, the steering return trajectory may include a series of x-y segments with direction of travel and percent steering information. The steering return trajectory may represent a pre-recorded trajectory previously driven for ADV in a real-world or simulated driving environment. Note that although fig. 5 illustrates a u-turn, the auto-zero steering module 308 may perform any type of turn, including a sharp turn. Here, a sharp turn may mean any turn in which the steering wheel turns through an angle greater than 90 degrees.

Although the steering return trajectory covers an automatic return of 100% to 0% steering, the current steering angle of the ADV may be less than 100%. In one embodiment, ADV101 generates a new turn back trajectory by trimming 100% to 0% of the turn back trajectory from the selected turn back trajectory profile to match the current turn percentage of the ADV. Referring to fig. 5, if the current turn is 80% to the right for ADV101, then when the u-turn is completed at time t2, the portion of the turn-back trajectory profile from 100% to 80% may be clipped. In this case, 80% to 0% of the turning section can be trimmed and used to generate a new turning return trajectory. The new trimmed 80% to 0% turn trajectory 503 is then spliced to the current trajectory (e.g., the u-turn trajectory 501), matching the direction and speed of travel of the ADV101 at time t 2.

In one embodiment, the trimmed turn trajectory 503 is in the x-y coordinate system, while the current trajectory 501 is in the station-lateral (SL) coordinate system. In one embodiment, prior to stitching the trajectory 503 to the trajectory 501, the trajectory 503 is transformed to the SL coordinate system based on the current geographic location and current direction of travel of the ADV.

Trajectory 503 then directs ADV101 to turn from 80% to 0% from time t2 to time t3, while controlling the speed of ADV101 according to trajectory 503. Note that since the steering return trajectory 503 corresponds to auto-zero, no steering command needs to be issued from time t2 to time t 3. Note that auto-zero or auto-center-return refers to the tendency of the vehicle to automatically return to a center-aligned position (also denoted as a 0% turn or center position) when the operator releases the steering wheel of the vehicle after turning. When the operator releases the steering wheel after a turn, any movement of the vehicle will create a torque force that pushes the turn back to the center aligned position.

FIG. 6 illustrates a steer return trajectory profile for a vehicle, according to one embodiment. Referring to FIG. 6, the configuration file 600 includes a return track 601-609. Each of the trajectories 601-609 may represent an auto-zero trajectory (or a turn-back trajectory) at a particular speed. In one embodiment, the track 601-609 may include metadata with speed information. For example, track 601 may be associated with 5m/s, track 603 may be associated with 4m/s, track 605 may be associated with 3m/s, track 607 may be associated with 2m/s, and track 609 may be associated with 1 m/s. The ADV101 uses the speed to select one of the tracks 601-609 to match the current speed of the vehicle, so the track can be trimmed and spliced to match the current speed of the vehicle in real time. In another embodiment, each trajectory may include a plurality of segments (or points), and each segment (or point) may be associated with a percentage turn. Here, fig. 6 shows segments 611 associated with 20%, 40%, 60%, 80%, and 100% turn. Note that although FIG. 6 illustrates five velocity tracks 601-609 with 20%, 40%, 60%, 80%, 100% turn segment granularity, the track profile 600 may include any number of tracks (e.g., at different velocities), with finer or coarser percentage turn granularity.

Figure 7 is a flow diagram illustrating a method performed by an ADV according to one embodiment. Process 700 may be performed by processing logic that may include software, hardware, or a combination thereof. For example, process 700 may be performed by auto-zero steering module 308 of FIG. 4. Referring to FIG. 7, at block 701, processing logic executes a turn by applying a steering command to an autonomous vehicle (ADV). At block 702, in response to turning, processing logic determines the current percent steering, speed, and direction of travel of the ADV. At block 703, processing logic selects a steering return trajectory profile from the one or more steering return trajectory profiles based on the determined velocity of the ADV. At block 704, processing logic generates a turn-around return trajectory based on the selection. At block 705, processing logic controls the ADV to return the steering to the center position based on the generated steering return trajectory.

In one embodiment, generating the turn-around return trajectory based on the selected turn-around return trajectory profile includes: the steering return trajectory profile is trimmed at the percent steer to match the current percent steer of the ADV, and the trimmed steering return trajectory profile is spliced to the current heading and current position of the ADV to generate the steering return trajectory. In one embodiment, performing the turn includes performing a sharp turn, wherein for the sharp turn, the steering of the steering wheel is greater than a 90 degree angle.

In one embodiment, each of the one or more turn-around return trajectory profiles is associated with a particular speed. In one embodiment, each of the one or more turn-back trajectory profiles is pre-recorded by using about 100% turn to left to return to about 0% turn (center turn) and/or about 100% turn to right to return to about 0% turn (center turn).

In one embodiment, each turn-back trajectory profile includes a plurality of trajectory segments, and each trajectory segment is associated with a percentage turn. In one embodiment, each of the one or more steering return trajectory profiles represents a trajectory to be performed after a turn to return the ADV to the center steering without applying a steering command.

FIG. 8 is a block diagram illustrating an offline processing module according to one embodiment. Offline processing module 125 may generate one or more turn-around return trajectory profiles offline. Referring to FIG. 8, the offline processing module 125 may include sub-modules such as a trajectory determiner 801, a segmentation determiner 803, a percentage turn determiner 805, and a turn back trajectory profile generator 807. The trajectory determiner 801 may determine/acquire or record a trajectory of the vehicle. The trajectory may include direction of travel, speed, and location information of the vehicle. The trajectory may be recorded by a simulated vehicle or a vehicle in a real-world environment. The segment determiner 803 may determine a plurality of segments of the trajectory. The percent turn determiner 805 may determine percent turn information for each segment. The turn back trajectory profile generator 807 may generate one or more return trajectory profiles based on the percentage turn information for the one or more trajectories and segments. Note that the configuration file may be generated offline, e.g., by server 103, or online, by ADV101 of fig. 1 or any other vehicle.

To generate the profile, in one embodiment, an operator operating the vehicle may physically (or via steering control commands) turn the steering wheel to steer the vehicle 100% to the left (maximum steering). The operator applies the throttle (or via speed control commands) to maintain the vehicle at a steady speed. The operator releases the steering control while maintaining the vehicle at the first speed (e.g., 1 m/s). In one embodiment, the offline processing module 125 may collect (or record) data information about different points in time along an auto-zero trajectory, for example, where the auto-zero trajectory is a trajectory that releases the steering from 100% steering to automatically return to 0% steering (center position) after the vehicle performs a turn. The trajectory is associated with different percentages of turns along the trajectory (e.g., using metadata) to generate a turn-back trajectory profile.

The above process may be repeated to generate a profile for steering the vehicle 100% to the right and/or additional profiles at different speeds (e.g., 2, 3, 4, and 5 m/s). Note that each profile may be associated with a different speed. The maximum speed may be limited by centripetal acceleration, a ═ speed ^2/r < ═ 1, where r is the minimum turning radius (1/curvature), which corresponds to the turning radius of a vehicle with 100% steering.

In one embodiment, data collection or trajectory recording may be performed using a simulation model that simulates an ADV in a simulation environment. Here, steering and speed control may be modeled such that data may be collected for a plurality of steering return trajectories for 100% to 0% steering to the left, 100% to 0% steering to the right, and one or more speeds. In some embodiments, the collected data may include the vehicle's turn percentage, direction of travel, speed, x-y position at various points along the trajectory. The collected data may be used to generate one or more turn-around return trajectory profiles. In one embodiment, the turn-around return trajectory profile includes a turn-around return trajectory and metadata information indicating percentage turns at different segments/points along the turn-around return trajectory. Here, the generated trajectory may be divided/segmented into a plurality of segments such that a turn percentage may be associated with each segment. When the ADV retrieves the turn-around trajectory profile, the turn-around trajectory may be trimmed at any segment to splice the turn-around trajectory to the trajectory of the ADV.

Figure 9 is a flow diagram illustrating a method performed by an ADV according to one embodiment. Process 900 may be performed by processing logic that may comprise software, hardware, or a combination thereof. For example, process 900 may be performed by offline processing module 125 of FIG. 8. Referring to FIG. 9, at block 901, processing logic determines a trajectory for a vehicle to return steering to a center position at a first speed, where the vehicle has performed a left or right turn. At block 902, processing logic determines a plurality of segments of the trajectory. In another embodiment, the trajectory may be divided into one or more segments. At block 903, processing logic associates percentage turn information with each segment. At block 904, processing logic generates one or more turn-around return trajectory profiles based on the trajectory and the percentage turn-around information.

In one embodiment, the processing logic further determines another trajectory of the vehicle at the second speed to generate another turn-back trajectory and generates one or more turn-back trajectory profiles based on the other trajectory. In one embodiment, each of the one or more turn-back trajectory profiles is associated with a particular speed, and the speed is used for trajectory selection.

In one embodiment, each of the one or more turn-back trajectory profiles is generated using about 100% turn-back to about 0% turn to the left (center turn) and/or about 100% turn-back to about 0% turn to the right (center turn). In one embodiment, a trajectory corresponding to a simulated or real-world environment is generated for a vehicle. In one embodiment, each of the one or more steering return trajectory profiles represents a driving trajectory after a turn to return the steering of an Autonomous Driving Vehicle (ADV) to center steering without applying a steering command.

Note that some or all of the components shown and described above may be implemented in software, hardware, or a combination thereof. For example, these components may be implemented as software installed and stored in a persistent storage device, which may be loaded and executed by a processor (not shown) in memory to perform the processes or operations described throughout this application. Alternatively, these components may be implemented as executable code programmed or embedded into special-purpose hardware, such as an integrated circuit (e.g., an application specific IC or ASIC), a Digital Signal Processor (DSP) or a Field Programmable Gate Array (FPGA), which is accessible via corresponding drivers and/or operating systems from applications. Further, these components may be implemented as specific hardware logic within a processor or processor core as part of an instruction set accessible via one or more specific instruction software components.

Some portions of the preceding detailed description have been presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, considered to be a self-consistent sequence of operations leading to a desired result. The operations are those requiring physical manipulations of physical quantities.

It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the above discussion, it is appreciated that throughout the description, discussions utilizing terms such as those set forth in the appended claims refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.

Embodiments of the present disclosure also relate to apparatuses for performing the operations herein. Such a computer program is stored in a non-transitory computer readable medium. A machine-readable medium includes any mechanism for storing information in a form readable by a machine (e.g., a computer). For example, a machine-readable (e.g., computer-readable) medium includes a machine (e.g., computer) readable storage medium (e.g., read only memory ("ROM"), random access memory ("RAM"), magnetic disk storage media, optical storage media, flash memory devices).

The processes or methods described in the foregoing figures may be performed by processing logic that comprises hardware (e.g., circuitry, dedicated logic, etc.), software (e.g., embodied on a non-transitory computer readable medium), or a combination of both. Although the processes or methods are described above in terms of some sequential operations, it should be understood that some of the operations described may be performed in a different order. Further, some operations may be performed in parallel rather than sequentially.

Embodiments of the present disclosure are not described with reference to any particular programming language. It will be appreciated that various programming languages may be used to implement the teachings of the embodiments of the disclosure as described herein.

In the foregoing specification, embodiments of the disclosure have been described with reference to specific exemplary embodiments thereof. It will be evident that various modifications may be made thereto without departing from the broader spirit and scope of the disclosure as set forth in the following claims. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.