Method and system for controlling a vehicle through a multi-lane turn

Abstract

The present technology relates to controlling an autonomous vehicle (100) through a multi-lane turn. In one example, data corresponding to the position of the autonomous vehicle in a lane (161, 162, 461, 462) of a multi-lane turn, a trajectory (480, 580) of the autonomous vehicle, and data corresponding to the position of an object near the autonomous vehicle can be received. Based on the position of the autonomous vehicle in the lane relative to the position of the object, it can be determined whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane. Based on whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane, the trajectory of the autonomous vehicle through the lane can be adjusted. The autonomous vehicle can be controlled based on the adjusted trajectory (481, 581).

Description

[0001] This application is a divisional application of the invention patent application with application date of October 10, 2019 and application number 201980076168.1.

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This application claims priority to application No. 16 / 165,114, filed on October 19, 2018, the disclosure of which is incorporated herein by reference. Technical Field

[0004] The present application relates to methods and systems for controlling a vehicle through a multi-lane turn. Background Art

[0005] Autonomous vehicles, such as vehicles that do not require a human driver, can be used to help transport passengers or items from one location to another. Such vehicles can operate in a fully autonomous mode, where the passenger can provide some initial input, such as a pick-up or destination location, and the autonomous vehicle will maneuver itself to that location. In order to do this safely, these vehicles must be able to detect and identify objects in the environment and react to them quickly. Typically, these objects are identified from information that can be sensed by sensors such as lidar, radar, or cameras.

[0006] In some cases, the detection and identification of other vehicles in the vicinity of an autonomous vehicle is critical to safely maneuvering the autonomous vehicle to its destination. For example, the trajectory of an autonomous vehicle may be affected by the activities of other vehicles driving around the autonomous vehicle. Therefore, being able to detect and respond to such activities is particularly important to ensure a safe and effective autonomous driving experience. Summary of the invention

[0007] The technology generally relates to a method for controlling an autonomous vehicle through a multi-lane turn. The method may include: receiving, by one or more processors, data corresponding to a position of the autonomous vehicle in a lane of the multi-lane turn and a trajectory of the autonomous vehicle; receiving, by one or more processors, data corresponding to a position of an object near the autonomous vehicle; determining, based on the position of the autonomous vehicle in the lane relative to the position of the object, whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane; adjusting, by one or more processors, a trajectory of the autonomous vehicle through the lane based on whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane; and controlling the autonomous vehicle through the multi-lane turn based on the adjusted trajectory.

[0008] In some embodiments, when it is determined that the position of the autonomous vehicle is positioned as the first vehicle in the lane, the trajectory can be adjusted based on historical data corresponding to previous trajectories of one or more vehicles crossing the lane. In some examples, the historical data can correspond to previous trajectories of the autonomous vehicle. In some cases, adjusting the trajectory based on the historical data can include determining an average lateral displacement of the previous trajectory relative to the trajectory of the autonomous vehicle; and adjusting the trajectory of the autonomous vehicle by the average lateral displacement. In some embodiments, the average lateral displacement can be limited to a predetermined distance from the left and right directions of the trajectory.

[0009] In some embodiments, when it is determined that the autonomous vehicle is positioned behind another vehicle, the trajectory can be adjusted based on the trajectory of the other vehicle. In some examples, the trajectory of the other vehicle can be tracked by an imaging sensor on the autonomous vehicle. In some cases, the adjusted trajectory can be defined by a predetermined distance to the left and right of the trajectory.

[0010] In some embodiments, adjusting the trajectory of the autonomous vehicle occurs continuously while negotiating a multi-lane turn.

[0011] In some embodiments, when it is determined that the autonomous vehicle is positioned behind multiple vehicles, the trajectory is adjusted based on the trajectories of the multiple vehicles through a multi-lane turn.

[0012] Another aspect of the present technology relates to a system for controlling an autonomous vehicle through a multi-lane turn, the system comprising: one or more processors, wherein the one or more processors are configured to: receive data corresponding to a position of the autonomous vehicle in a lane of a multi-lane turn; receive data corresponding to a position of an object near the autonomous vehicle; determine whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane based on the position of the autonomous vehicle in the lane relative to the position of the object; adjust, by the one or more processors, a trajectory of the autonomous vehicle through the lane based on whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane; and control the autonomous vehicle through the multi-lane turn based on the adjusted trajectory.

[0013] In some cases, the one or more processors may also be configured to, when determining that the position of the autonomous vehicle is located as the first vehicle in the lane, adjust the trajectory based on historical data corresponding to previous trajectories of one or more vehicles crossing the lane. In some examples, the historical data corresponds to a previous trajectory of the autonomous vehicle.

[0014] In some cases, adjusting the trajectory based on the historical data includes: determining an average lateral displacement of previous trajectories relative to the trajectory of the autonomous vehicle; and adjusting the trajectory of the autonomous vehicle by the average lateral displacement. In some examples, the average lateral displacement can be limited to a predetermined distance to the left and right of the trajectory.

[0015] In some embodiments, the one or more processors may also be configured to, when determining that the autonomous vehicle is positioned behind another vehicle, adjust the trajectory based on the trajectory of the other vehicle. In some examples, the trajectory of the other vehicle may be tracked by an imaging sensor on the autonomous vehicle. In some cases, the adjusted trajectory may be defined by a predetermined distance to the left and right of the trajectory.

[0016] In some embodiments, adjusting the trajectory of the autonomous vehicle occurs continuously while negotiating a multi-lane turn.

[0017] In some embodiments, the one or more processors may also be configured to adjust the trajectory based on the trajectories of the multiple vehicles through a multi-lane turn when it is determined that the autonomous vehicle is positioned behind multiple vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 An example road is shown in accordance with aspects of the present disclosure.

[0019] Figure 2 is a functional diagram of an example vehicle according to aspects of the present disclosure.

[0020] Figure 3 is an example representative view of a vehicle according to aspects of the present disclosure.

[0021] Figure 4A and 4B is an example view of a portion of a road on which an autonomous driving vehicle is traversing corresponding to map information according to aspects of the present disclosure.

[0022] Figure 5 is an example illustration of alternative trajectories for an autonomous vehicle according to aspects of the present disclosure.

[0023] Figure 6 is an example illustration of an autonomous vehicle following another vehicle's trajectory according to aspects of the present disclosure.

[0024] Figure 7 is an example illustration of two vehicles crossing an intersection according to aspects of the present disclosure.

[0025] Figure 8 is an example illustration of staggering an autonomous vehicle relative to surrounding vehicles according to aspects of the present disclosure.

[0026] Fig. 9 is an example illustration of an autonomous vehicle traveling too closely to surrounding vehicles in accordance with aspects of the present disclosure.

[0027] Fig.10 is an example illustration of an autonomous vehicle traveling too closely to surrounding vehicles in accordance with aspects of the present disclosure.

[0028] Fig.11 is an example illustration of an autonomous vehicle traveling too closely to surrounding vehicles in accordance with aspects of the present disclosure.

[0029] Fig.12 is a flow chart according to aspects of the present disclosure. DETAILED DESCRIPTION

[0030] Overview

[0031] The technology relates to controlling an autonomous vehicle through a multi-lane turn. In this regard, when traversing a multi-lane turn, such as a two-lane or three-lane, left turn or right turn, drivers often take shortcuts and cross lane boundaries. For example, Figure 1 A road portion 100 is shown on which vehicles 101 and 102 traverse a two-lane left turn 160 in an inner lane 161 and an outer lane 162, respectively. Vehicle 102, which is traversing outer lane 162, crosses into inner lane 161 and into the path of vehicle 101, which is traversing inner lane 161. In order to avoid hitting vehicle 102, vehicle 101 may be forced to adjust its trajectory. Vehicles such as vehicle 101 are often cut-off or pushed out of their current trajectory by vehicles traveling in adjacent lanes. These issues are magnified for autonomous vehicles because they may be programmed to follow a trajectory within the lane in which the vehicle is located. As such, during an autonomous vehicle executing a turn through a multi-lane turn, an evasive maneuver may be required when the autonomous vehicle is "cut-off" or "pinched" by another vehicle. Such evasive maneuvers may cause passengers of the autonomous vehicle to feel uncomfortable or unsafe.

[0032] To address these issues, the actions and trajectory of an autonomous vehicle may be adjusted as it traverses a multi-lane turn. The trajectory may be adjusted based on the position of the vehicle relative to other vehicles or based on historical data of the vehicle traversing a multi-lane turn. In this regard, the autonomous vehicle may be in a variety of positions relative to other vehicles when traversing a multi-lane turn, such as, for example, the first vehicle in a row of vehicles, the last vehicle in a row of vehicles, or in the middle of vehicles. For example, when the autonomous vehicle is positioned at the head of a row of vehicles, the trajectory of the autonomous vehicle may be adjusted so that it follows an alternative trajectory based on historical data corresponding to previous paths taken by the vehicle through the multi-lane turn. In the event that the autonomous vehicle is positioned in the middle or behind other vehicles, the trajectory of the autonomous vehicle may be adjusted so that it follows the trajectory of the vehicle positioned in front.

[0033] Historical data may include previous paths taken by the autonomous vehicle or other vehicles around a multi-lane turn, which may be monitored and used to alter the nominal trajectory of the autonomous vehicle. Based on the historical data, an alternate trajectory may be followed in place of the nominal trajectory of the autonomous vehicle to more closely resemble the previous trajectory of the vehicle through the turn. In some cases, the alternate trajectory may be constrained to prevent the autonomous vehicle from straying too far from a safe operating trajectory.

[0034] In the event that a vehicle crosses a lane adjacent to the autonomous vehicle, the autonomous vehicle may adjust its trajectory so that it is staggered relative to the adjacent vehicle to increase its visibility to the drivers of the adjacent vehicles. In other words, the autonomous vehicle may continuously position itself so that it is positioned between vehicles in the adjacent lanes so that the vehicles in the adjacent lanes can see the autonomous vehicle.

[0035] In the event that the autonomous vehicle cannot maintain a staggered position relative to vehicles in an adjacent lane, the autonomous vehicle may overtake or yield to one of the surrounding vehicles. The determination of whether to overtake or yield may be based on the comfort level of the passengers, such that any maneuvers to overtake or yield should not cause excessive passenger discomfort.

[0036] The features described herein allow for improved and safer travel of an autonomous vehicle through multi-lane turns. In this regard, the features described herein provide more comfortable turning conditions for passengers of the autonomous vehicle because evasive maneuvers such as emergency braking or rapid turns may be avoided. Additionally, the autonomous vehicle may be positioned so that it is more visible to surrounding vehicles to reduce the risk that the driver may not see the autonomous vehicle when traversing a multi-lane turn. Additionally, the movement of the autonomous vehicle through the multi-lane turn may be more typical for a human driver, thereby enabling drivers of surrounding vehicles to more easily predict the movement of the autonomous vehicle.

[0037] Example System

[0038] like Figure 2 As shown, a vehicle 201 according to one aspect of the present disclosure includes multiple components. Although certain aspects of the present disclosure are particularly useful for specific types of vehicles, the vehicle can be any type of vehicle, including but not limited to cars, trucks, motorcycles, buses, recreational vehicles, etc. The vehicle can have one or more computing devices, such as a computing device 210 that includes one or more processors 220, memory 230, and other components typically found in a general-purpose computing device.

[0039] The memory 230 stores information accessible by the one or more processors 220, including instructions 234 and data 232 that can be executed or otherwise used by the processor 220. The memory 230 can be of any type capable of storing information accessible by the processor, including computing device readable media, or other media that stores data that can be read by electronic devices, such as hard drives, memory cards, read-only memories, random access memories, digital video disks or other optical disks, and other writable and read-only memories. The systems and methods can include different combinations of the foregoing, whereby different portions of the instructions and data are stored on different types of media.

[0040] Instructions 234 may be any set of instructions that are directly executed by a processor (such as machine code) or indirectly executed (such as a script). For example, instructions may be stored as computing device code on a computing device readable medium. In this regard, the terms "instructions" and "programs" may be used interchangeably herein. Instructions may be stored in an object code format for direct processing by a processor, or in any other computing device language, including a collection of scripts or independent source code modules that are interpreted on demand or pre-compiled. The functions, methods, and routines of instructions are explained in more detail below.

[0041] Data 232 may be retrieved, stored, or modified by processor 220 according to instructions 234. For example, data may be stored in a computing device register, in a relational database as a table with a plurality of different fields and records, in an XML document, or in a flat file, although the claimed subject matter is not limited to any particular data structure. Data may also be formatted in any format readable by a computing device.

[0042] Processor 220 may be any one or more conventional processors, such as a commercially available CPU. Alternatively, one or more processors may be dedicated devices, such as an ASIC or other hardware-based processor. Figure 2The processor, memory, and other elements of computing device 210 are functionally shown within the same box, but one of ordinary skill in the art will appreciate that the processor, computing device, or memory may actually include multiple processors, computing devices, or memories, which may or may not be stored within the same physical housing. For example, memory 230 may be a hard drive and / or other storage medium located in a different housing than computing device 210. Thus, references to a processor or computing device will be understood to include references to a collection of processors or computing devices or memories, which may or may not operate in parallel.

[0043] The computing device 210 may include all components typically used in conjunction with a computing device (such as the processor and memory described above) as well as one or more user inputs 250 (e.g., a mouse, keyboard, touch screen, and / or microphone) and various electronic displays (e.g., a monitor with a screen or any other electronic device operable to display information). In this example, the vehicle includes one or more interior displays 252 and one or more speakers 254 to provide information or an audio-visual experience. In this regard, the display 252 may be located within the cabin of the vehicle 201 and may be used by the computing device 210 to provide information to passengers or maintenance personnel within or near the vehicle 201.

[0044] The computing device 210 may also include one or more wireless network connectors 256 to communicate with other computing devices, such as client computing devices and server computing devices described in detail below. Wireless network connections may include short-range communication protocols such as Bluetooth, Bluetooth Low Energy (LE), cellular connections, and various configurations and protocols, including the Internet, the World Wide Web, an intranet, a virtual private network, a wide area network, a local area network, a private network using one or more company-proprietary communication protocols, Ethernet, Wi-Fi, and HTTP, and various combinations of the above. The computing device 210 of the vehicle 201 may also send information to or receive information from other computing devices (not shown), such as computing devices that contain or otherwise store more map or perception data.

[0045] In one example, computing device 210 may control a computing device of an autonomous driving computing system coupled to vehicle 201. The autonomous driving computing system is capable of communicating with various components of the vehicle to control the movement of vehicle 201 according to the primary vehicle control code stored in memory 230. For example, computing device 210 may communicate with various systems of vehicle 201, such as deceleration system 260, acceleration system 262, steering system 264, signal system 266, navigation system 268, positioning system 270, perception system 272, and power system 274 (i.e., the engine or motor of the vehicle) to control the movement, speed, etc. of vehicle 201 according to instructions 234 of memory 230. Again, although these systems are shown as being external to computing device 210, in reality, these systems may also be coupled to computing device 210, also as an autonomous driving computing system for controlling vehicle 201.

[0046] As an example, computing device 210 may interact with one or more actuators or other such components of deceleration system 260 and / or acceleration system 262 (such as brakes, accelerator pedals, and / or the engine or motor of the vehicle) to control the speed of the vehicle. Similarly, computing device 210 may use one or more actuators or other such components of steering system 264, such as a steering wheel, a steering shaft, and / or a rack and pinion system, to control the direction of vehicle 201. For example, if vehicle 201 (such as a car or truck) is configured for use on a road, the steering system may include one or more actuators or other such devices to control the angle of the wheels to turn the vehicle. Computing device 210 may use signaling system 266 to signal the vehicle's intentions to other drivers or vehicles, such as by illuminating turn signals or brake lights when necessary.

[0047] Navigation system 268 may be used by computing device 210 to determine and follow a route to a location. In this regard, navigation system 268 and / or data 232 may store detailed map / route map information, such as a highly detailed map that identifies the shape and elevation of roads, lane lines, intersections, crosswalks, speed limits, traffic signals, buildings, signs, real-time traffic information, vegetation, or other such objects and information. For example, Figure 4AA road portion 400 is shown, which shows example map information identifying the shape, location, and other characteristics of various road features near an intersection 402. In this example, the road portion 400 corresponding to the map information includes information defining the shape and location of lane markings 410-414, stop lines 425, crosswalks 430, 432, sidewalks 440, traffic lights 420, 422, lane markings 471, 472, 473, and the shape and direction of traffic such as lanes 461, 462, 465, 466. The road portion 400 shows some of the road features included in the map information. The map information may also include additional features of the road, such as, for example, lane lines, shoulder areas, intersections, and lanes and directions. The map information may also identify various other road features, such as stop signs, yield signs, railroad tracks, railroad crossings, speed limit signs, road signs, speed bumps, and the like. Although not shown in road portion 400 , the map information may also include information identifying speed limits and other legal traffic requirements, such as the location of a given stop sign or the status of a traffic signal, which vehicle has the right of way, and the like.

[0048] Although the detailed map information corresponding to the road portion 400 is depicted as an image-based map herein, the map information need not be entirely image-based (e.g., raster-based). For example, the detailed map information may include one or more road maps or a graphical network of information, such as roads, lanes, intersections, and connections between these features. Each feature may be stored as graphical data and may be associated with information such as a geographic location and whether it is linked to other related features, e.g., a stop sign may be linked to roads and intersections, etc. In some examples, the associated data may include a grid-based index of the road map to allow efficient lookup of certain road map features.

[0049] Positioning system 270 can be used by computing device 210 to determine the relative or absolute position of the vehicle on a map or on the earth. For example, positioning system 270 can include a GPS receiver to determine the latitude, longitude and / or altitude position of the positioning system. Other positioning systems such as laser-based positioning systems, inertial assisted GPS, or camera-based positioning can also be used to identify the location of the vehicle. The location of the vehicle can include an absolute geographic location, such as latitude, longitude, and altitude, as well as relative position information, such as relative to the location of other cars in its immediate surroundings, which can generally be determined with less noise than the absolute geographic location.

[0050] Positioning system 270 may also include other devices in communication with computing device 210, such as accelerometers, gyroscopes, or another direction / speed detection device to determine the direction and speed of the vehicle or changes thereto. By way of example only, an acceleration device may determine its pitch, yaw, or roll (or changes thereto) relative to the direction of gravity or a plane perpendicular thereto. The device may also track increases or decreases in speed and the direction of such changes. Position and orientation data provided by the devices as described herein may be automatically provided to computing device 210, other computing devices, and combinations of the foregoing.

[0051] The perception system 272 may also include one or more components for detecting objects outside the vehicle, such as other vehicles, obstacles in the road, traffic signals, signs, trees, etc. For example, the perception system 272 may include lasers, sonars, radars, cameras, and / or any other detection devices that record data that can be processed by the computing device 210. For example, the perception system 272 may include lasers, sonars, radars, cameras, and / or any other detection devices that record data that can be processed by the computing device. In some cases, the perception system may include a laser or other sensor mounted on the roof or other convenient location of the vehicle. For example, the perception system 272 may use various sensors, such as LIDAR, sonar, radar, cameras, etc., to detect objects and their characteristics, such as location, orientation, size, shape, type, direction, and speed of movement. In the case where the vehicle is a passenger vehicle such as a minivan, the minivan may include a laser or other sensor mounted on the roof or other convenient location.

[0052] For example, Figure 3 is an example external view of vehicle 201. In this example, the top sensor housing 310 and the dome sensor housing 312 may include one or more lidar sensors, cameras, and / or radar units. In addition, the housing 320 located at the front end of the vehicle 200 and the housings 330, 332 on the driver and passenger sides of the vehicle may store lidar sensors, respectively. For example, the housing 330 is located in front of the driver's door 360. The vehicle 201 also includes housings 340, 342 for radar units and / or cameras that are also located on the roof of the vehicle 201. Other radar units and cameras (not shown) may be located at the front and rear ends of the vehicle 201, and / or at other locations along the roof or top sensor housing 310. In this regard, each of the housings 310, 312, 320, 330, 332, 340, and 342 may be considered a sensor housing, and any or all of the above sensors may be considered part of the vehicle perception system 272.

[0053] Based on the data received from the various system components, the computing device 210 can control the direction, speed, acceleration, etc. of the autonomous vehicle 201 by sending instructions to the various components of the vehicle. For example, the computing device can use the data from the map information and navigation system to fully automatically navigate the autonomous vehicle to the destination location. The computing device can use the positioning system to determine the location of the autonomous vehicle, and use the perception system to detect and respond to objects when it is necessary to safely reach the location. To do this, the computing device can accelerate the autonomous vehicle (e.g., by increasing the fuel or other energy provided to the engine by the acceleration system), decelerate (e.g., by reducing the fuel supplied to the engine, changing gears and / or applying brakes through the deceleration system), change direction (e.g., turning the front or rear wheels of the autonomous vehicle through the steering system), and signal such changes (e.g., by illuminating the turn signal of the signal system). Therefore, the acceleration system and the deceleration system can be part of the powertrain system, which includes various components between the engine of the autonomous vehicle and the wheels of the autonomous vehicle. Similarly, by controlling these systems, the computing device 210 can also control the powertrain system of the autonomous vehicle so as to fully automatically maneuver the vehicle to the destination location using data from the map information and navigation system.

[0054] Example Method

[0055] In addition to the operations described above and shown in the accompanying drawings, various operations will now be described. It should be understood that the following operations do not have to be performed in the exact order described below. Instead, the various steps can be processed in a different order or simultaneously, and steps can also be added or omitted. It should also be understood that the term "autonomous" can include semi-autonomous driving vehicles, including vehicles where a human driver can take over control of the vehicle.

[0056] When traversing a multi-lane turn, the autonomous vehicle may be in a variety of positions relative to other vehicles. For example, autonomous vehicle 401 may be the first vehicle in a line of vehicles (e.g., Figure 4A ), or the autonomous vehicle 401 may be positioned in the middle or rear of a row of vehicles (as shown in Figure 6 and 7 Although the examples described herein show the automated driving vehicle 401 traversing a two-lane left turn 460, the features described herein can be applied to any multi-lane turn. For example, the features can be used for a three-lane left turn, a two-lane right turn, a three-lane right turn, a straight section of a multi-lane road with one or more offsets and / or displacements, such as an intersection entrance, an exit location, an on-ramp, an off-ramp, or other such sections with multiple lanes.

[0057] The trajectory of the autonomous vehicle can be adjusted based on the position of the autonomous vehicle relative to other vehicles traversing a multi-lane turn. Figure 4A and 4B 4, an autonomous vehicle 401 is positioned in front of a line of vehicles including a vehicle 407 in a double left turn lane 460. When positioned in front of a line of vehicles (e.g., the first vehicle), the autonomous vehicle may follow a nominal trajectory 480, such as if it were making a single lane turn, such as Figure 4A In other words, a computing device of an autonomous vehicle, such as computing device 210, can instruct autonomous vehicle 401 to drive within its normal operating parameters, or more specifically, to follow a nominal trajectory according to typical driving practice such that the autonomous vehicle is centered or nearly centered in the turning lane.

[0058] Historical data corresponding to previous paths traversed by the autonomous vehicle or other vehicles around a multi-lane turn can be monitored and used to change the nominal trajectory of the autonomous vehicle. In this regard, past trajectories, such as the actual path traveled by the vehicle or the actual path traveled by the vehicle relative to a nominal driving path defined in map information (i.e., the portion of the road that the vehicle typically travels through) can be tracked. Behavior of other vehicles or the autonomous vehicle itself, such as acceleration and deceleration, can also be tracked. Historical data can be tracked by sensors of the autonomous vehicle, such as sensors of the perception system 272, sensors of other vehicles, and / or sensors located at or near the multi-lane turn.

[0059] The historical data collected by the sensors may include these previous trajectories of the vehicle crossing the inner and outer lanes of a two-lane left turn. Figure 4B As shown, vehicles 403 and 405 in the outer lane 462 of a two-lane left turn (i.e., the lane with a wider turning radius) may tend to move toward and / or cut into the inner lane 461 (i.e., the lane with a shorter turning radius). To avoid collisions with vehicles in the outer lane 462, vehicles such as the automated driving vehicle 401 and the vehicle 407 that cross the inner lane 461 may generally follow a trajectory that results in a sharper turn than would normally be followed if there were no vehicles in the outer lane 462.

[0060] Based on this historical data, a computing device of vehicle 402, such as computing device 210 or another such computer, may determine an alternative trajectory that should be followed in place of the nominal trajectory. In this regard, the trajectory of autonomous vehicle 401 may be adjusted from its nominal trajectory to an alternative trajectory that is more similar to a previous trajectory of vehicles traversing a turn. For example, and as previously described, historical data may indicate that vehicles traveling in outer lane 462 tend to move into inner lane 461 during a turn. Based on the historical data, computing device 210 may determine an average lateral displacement of vehicles traversing a turn relative to nominal trajectory 480. Nominal trajectory 480 of the autonomous vehicle may be adjusted to more closely follow the average lateral displacement so that the adjusted trajectory 481 of the autonomous vehicle is similar to other vehicles, such as, for example, Figure 4B As further shown. As the autonomous vehicle traverses a multi-lane turn, the trajectory of the autonomous vehicle may be continuously adjusted. A computing device of the autonomous vehicle, such as computing device 210, may then control the autonomous vehicle 401 according to the adjusted trajectory 481. In some cases, the historical data may be filtered before determining the average lateral displacement to remove vehicle trajectories that are greater than a predetermined distance from the nominal trajectory.

[0061] The alternative trajectory can be limited so that the autonomous vehicle does not deviate too far from the safe operating trajectory. In this regard, the autonomous vehicle 401 can be defined by a range in the lateral direction around the turning trajectory (i.e., limited to the distance to the left and / or right of the trajectory). For example, as shown in the map information 500, the unbounded initial alternative trajectory 580 can cause it to deviate from the right or left of the nominal trajectory by a certain amount, for example, two feet or three feet, or more, or less, and outside the range shown as "X", which may result in unsafe driving conditions for the autonomous vehicle 401 and / or other surrounding vehicles.

[0062] To address this issue, the initial alternative trajectory 580 may be modified so that it is within the predetermined range "X". Figure 5 As shown, the unbounded initial alternate trajectory 580 may cause the autonomous vehicle 401 to cross the stop line 425 of traffic traveling in a lane traveling in the opposite direction of the autonomous vehicle 401. When the vehicle may be positioned on or beyond the stop line 425, the initial alternate trajectory 580 may be adjusted so that it is within the predetermined range "X", as shown by the adjusted trajectory 581. The adjusted trajectory 581 may provide sufficient space between the autonomous vehicle 401 and the stop line 425 so that the autonomous vehicle does not cross the stop line. Other boundaries may be based on the location of lane dividers and other such obstacles that may be in the autonomous vehicle trajectory.

[0063] A confidence interval can be determined for each portion of the turn to determine whether the alternative trajectory is within a certain distance from the nominal trajectory for each portion of the turn. In other words, as long as the path of the leading vehicle is within an arbitrary determined range of the nominal path, the confidence interval can be a parameter that can be adjusted to provide a compromise between the autonomous vehicle 401 following the path of the leading vehicle, otherwise the autonomous vehicle can follow its nominal path. In this regard, the turn can be subdivided into a series of fixed or non-fixed length intervals. Within each interval, a potential lateral displacement distribution relative to the nominal trajectory can be generated via historical data observations or using a model. Based on the distribution of displacements, samples can be generated and arbitrary confidence intervals can be specified, such as 95% or greater or less. The alternative trajectory can be compared to the displacement samples to ensure that the alternative trajectory is within a distance range from the nominal trajectory defined by the displacement samples with a specified confidence interval, such as 0.5 meters, or greater or less.

[0064] In situations where the autonomous vehicle is positioned in the middle or at the end of a line of vehicles, the autonomous vehicle may follow the trajectory of another vehicle or the vehicle in front of it. In this regard, a perception system of autonomous vehicle 402, such as perception system 272, may track in real time the path of vehicles traversing the same multi-lane turning lane as the autonomous vehicle. Based on the path tracked by the perception system, the autonomous vehicle may follow the same or similar trajectory. For example, Figure 6 As shown, autonomous vehicle 401 is positioned in inner lane 461 of a two-lane left turn 460 between vehicles 601 and 603. As vehicle 601 crosses lane 461, perception system 272 of autonomous vehicle 401 can track trajectory 680 of vehicle 601. Autonomous vehicle 401 can then follow the same trajectory 680 as the autonomous vehicle crosses the two-lane left turn. In some cases, the trajectory of the autonomous vehicle can be bounded as described herein, such that the autonomous vehicle can deviate from the trajectory of other vehicles if the trajectory of the other vehicles falls outside of the bounded range.

[0065] In some cases, vehicles in the adjacent lanes of a multi-lane turn may be too close together, thereby reducing the visibility of other vehicles to the drivers of other vehicles. In layman's terms, the adjacent vehicles are considered to be the "blind spots" of the drivers of surrounding vehicles. In such cases, there is an increased risk that a vehicle driver may enter the adjacent lane without realizing that another vehicle is in his or her blind spot. For example, if Figure 7 As shown, vehicle 701 is crossing the inner lane 461 of the two-lane left turn 460. The driver of vehicle 703, which is positioned adjacent to vehicle 701 (within the blind spot of vehicle 710) and is crossing the outside of outer lane 462, may not see vehicle 701 and attempt to cross into inner lane 461, thereby blocking vehicle 701.

[0066] To avoid these problems when navigating a multi-lane turn, the autonomous vehicle's computing device can cause the autonomous vehicle to stagger relative to surrounding vehicles. By doing so, the autonomous vehicle can increase visibility to other drivers of vehicles ahead and behind. For example, Figure 8 As shown, the autonomous vehicle 401 traveling in lane 461 of the two-lane left turn 460 can be positioned so that it is between vehicles 801 and 803 crossing the adjacent outer lane 462. By doing so, the vehicles in the adjacent outer lane 462 can see the autonomous vehicle 401. In addition, by staggering the vehicles in the adjacent outer lane 462 with respect to the autonomous vehicle 401, fewer actuations, such as by braking and / or accelerating, may be required to avoid a collision.

[0067] The computing device of the autonomous vehicle can continuously adjust the trajectory and position of the autonomous vehicle relative to the positions of surrounding vehicles in adjacent lanes. In this regard, the perception system of the autonomous vehicle, such as perception system 272, can track the positions of surrounding vehicles in front of the autonomous vehicle 401 (front surround) and behind (rear surround) to determine their positions relative to the autonomous vehicle 401. The distance that the autonomous vehicle 401 can maintain between the surrounding vehicles behind and the surrounding vehicles in front can be based on a fixed stopping range. For example, referring to Figure 6 , the front bumper of the autonomous driving vehicle 401 may be one meter away from the rear bumper of the vehicle 601 positioned in front of the autonomous driving vehicle, or more or less. For surrounding vehicles behind the autonomous driving vehicle, such as vehicle 603, the rear bumper of the autonomous driving vehicle 401 may be one meter away from the front bumper of the surrounding vehicle 603.

[0068] Based on the distance between the rear surrounding vehicle and the front surrounding vehicle, the computing device of the autonomous vehicle can adjust the speed and / or acceleration of the autonomous vehicle to maintain the staggered position. For example, when the autonomous vehicle 401 crossing the inner lane of the double left turn lane 460 is too close to the rear surrounding vehicle 903 crossing the adjacent outer lane 462, as shown in FIG. Fig. 9 As shown, a computing device of the autonomous vehicle, such as computing device 210, can cause the autonomous vehicle 401 to accelerate and increase its speed until an appropriate distance is reached from surrounding vehicles behind.

[0069] In the event that the autonomous vehicle is positioned too close to the surrounding vehicle ahead, the computing device of the autonomous vehicle may reduce the speed of the autonomous vehicle and / or reduce the acceleration to allow the surrounding vehicle ahead time to further get ahead of the autonomous vehicle. For example, when the autonomous vehicle 401 crossing the inner lane of the double left turn lane 460 is too close to the surrounding vehicle ahead, such as Fig.10As shown, a computing device of the autonomous vehicle, such as computing device 210, can cause the autonomous vehicle 401 to slow down and reduce its speed until an appropriate distance is reached from the surrounding vehicle 1001 ahead.

[0070] If an appropriate spacing is achieved between surrounding vehicles in front and behind, the autonomous vehicle's computing device can maintain the autonomous vehicle's current speed and / or acceleration.

[0071] In some cases, the surrounding vehicles ahead and / or behind may prevent the autonomous vehicle from passing. In this regard, the surrounding vehicles ahead and / or behind may be too close to allow the autonomous vehicle to pass. In this case, the autonomous vehicle may pass or yield to one of the surrounding vehicles. For example, if Fig.11 As shown, the rear surrounding vehicle 1103 traveling in the outer lane 462 of the double left turn lane 460 is too close to the front surrounding vehicle 1101 to allow the autonomous vehicle to interleave. In response, the autonomous vehicle 401 passing through the inner lane 461 can yield to the rear surrounding vehicle 1103 by reducing the vehicle's speed and / or acceleration to allow the rear surrounding vehicle to pass (e.g., the rear surrounding vehicle maneuvers into a position in front of the autonomous vehicle), or by increasing the vehicle's speed and / or acceleration to pass the front surrounding vehicle 1101 (e.g., the autonomous vehicle moves to a position in front of the front surrounding vehicle).

[0072] Whether to overtake or yield can be determined based on passenger comfort. In this regard, a computing device such as computing device 210 can monitor the angular trajectory of the autonomous vehicle, its current speed, its current acceleration, and its position relative to surrounding vehicles. Based on these factors, if the vehicle is to overtake the surrounding vehicles in front or if the vehicle is to yield to the surrounding vehicles behind, the computing device can determine whether the autonomous vehicle will be more comfortable for the passengers, because if the autonomous vehicle is too close to another vehicle laterally and / or if the autonomous vehicle turns too fast or too slowly, it will make the passengers feel uneasy. For example, the autonomous vehicle can monitor factors such as the spacing between the vehicles in front and / or behind it, the lateral spacing distance between the surrounding vehicles, the braking action of the surrounding vehicles, etc. Based on these factors and their potential or actual impact on the operation of the vehicle, the computing device of the autonomous vehicle can determine whether overtaking the surrounding vehicles, yielding to the surrounding vehicles, or maintaining the current position of the autonomous vehicle will make the passengers more comfortable.

[0073] Fig.12An example flowchart 1200 including some examples for controlling a vehicle as described above. In this example, the steps of the flowchart may be performed by one or more processors of one or more computing devices, such as processor 220 of computing device 210 of vehicle 201. For example, at box 1201, one or more processors receive data corresponding to the position of an autonomous vehicle in a lane of a multi-lane turn and the trajectory of the autonomous vehicle. At box 1203, one or more processors receive data corresponding to the position of an object near the autonomous vehicle. At box 1205, based on the position of the autonomous vehicle in the lane relative to the position of the object, it is determined whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane. As shown in box 1207, based on whether the autonomous vehicle is positioned as the first vehicle in the lane or positioned behind another vehicle in the lane, the one or more processors may adjust the trajectory of the autonomous vehicle through the lane. As shown in box 1209, based on the adjusted trajectory, the autonomous vehicle may be controlled through the multi-lane turn.

[0074] Unless otherwise stated, the foregoing alternative examples are not mutually exclusive, but may be implemented in various combinations to achieve unique advantages. Since these and other variations and combinations of the features discussed above can be utilized without departing from the subject matter defined by the claims, the foregoing description of the embodiments should be understood in an illustrative manner rather than in a manner that is limited by the subject matter defined by the claims. In addition, the provision of the examples described herein and the phrases expressed as "such as", "including", etc. should not be interpreted as limiting the subject matter of the claims to specific examples; rather, these examples are intended to illustrate only one of many possible embodiments. In addition, the same reference numerals in different figures may identify the same or similar elements.

Claims

1. A method for controlling an autonomous driving vehicle through a multi-lane turn, the method comprising: receiving, by one or more processors, data corresponding to a position of the autonomous vehicle in a lane of a multi-lane turn relative to a position of each of the first vehicle and the second vehicle and a trajectory of the autonomous vehicle; determining, based on a position of the automated driving vehicle relative to a position of each of the first vehicle and the second vehicle, that the automated driving vehicle is positioned in an inner lane of a multi-lane turn and that the first vehicle and the second vehicle are positioned in adjacent lanes of the inner lane; determining, by the one or more processors, a distance between the autonomous vehicle and each of the first vehicle and the second vehicle such that the autonomous vehicle is in a staggered position relative to the first vehicle and the second vehicle such that the first vehicle is a front surrounding vehicle and the second vehicle is a rear surrounding vehicle; adjusting, by the one or more processors, a trajectory of the autonomous vehicle based on the distance to maintain a staggered position; and Based on the adjusted trajectory, the autonomous vehicle is controlled to make turns in multiple lanes.

2. The method according to claim 1, wherein: The distance is maintained based on a fixed stopping range.

3. The method according to claim 1, wherein: The speed and acceleration of the autonomous vehicle are adjusted to maintain a staggered position of the autonomous vehicle relative to each of the first vehicle and the second vehicle.

4. The method according to claim 3, wherein: The speed and acceleration of the autonomous vehicle are adjusted based on the distance between the autonomous vehicle and each of the first vehicle and the second vehicle.

5. The method according to claim 2, wherein: When the autonomous vehicle is within a fixed stopping range of the second vehicle, the autonomous vehicle accelerates and increases its speed until an appropriate distance between the second vehicle and the autonomous vehicle is reached.

6. The method according to claim 2, wherein: When the autonomous vehicle is within a fixed stopping range of the first vehicle, the autonomous vehicle decelerates and reduces its speed until an appropriate distance between the first vehicle and the autonomous vehicle is reached.

7. The method according to claim 1, wherein: Adjusting the trajectory of the autonomous vehicle occurs continuously while negotiating a multi-lane turn.

8. The method according to claim 1, wherein: The trajectory of each of the first vehicle and the second vehicle is tracked by an imaging sensor on the autonomous vehicle.

9. The method according to claim 1, wherein: When the autonomous vehicle traverses a multi-lane turn, the trajectory of the autonomous vehicle is adjusted to maintain a staggered position relative to each of the first vehicle and the second vehicle.

10. A system for controlling an autonomous vehicle through a multi-lane turn, the system comprising: One or more processors, wherein the one or more processors are configured to: receiving data corresponding to a position of the autonomous vehicle relative to a position of each of the first vehicle and the second vehicle in a lane of a multi-lane turn and a trajectory of the autonomous vehicle; determining, based on a position of the automated driving vehicle relative to a position of each of the first vehicle and the second vehicle, that the automated driving vehicle is positioned in an inner lane of a multi-lane turn and that the first vehicle and the second vehicle are positioned in adjacent lanes of the inner lane; determining a distance between the autonomous vehicle and each of the first vehicle and the second vehicle such that the autonomous vehicle is in a staggered position relative to the first vehicle and the second vehicle such that the first vehicle is a front surrounding vehicle and the second vehicle is a rear surrounding vehicle; Adjusting the trajectory of the autonomous vehicle based on distance to maintain the staggered position; and Based on the adjusted trajectory, the autonomous vehicle is controlled to make turns in multiple lanes.

11. The system according to claim 10, wherein: The distance is maintained based on a fixed stopping range.

12. The system according to claim 10, wherein: The speed and acceleration of the autonomous vehicle are adjusted to maintain a staggered position of the autonomous vehicle relative to each of the first vehicle and the second vehicle.

13. The system according to claim 12, wherein: The speed and acceleration of the autonomous vehicle are adjusted based on the distance between the autonomous vehicle and each of the first vehicle and the second vehicle.

14. The system according to claim 11, wherein: When the autonomous vehicle is within a fixed stopping range of the second vehicle, the autonomous vehicle accelerates and increases its speed until an appropriate distance between the second vehicle and the autonomous vehicle is reached.

15. The system according to claim 11, wherein: When the autonomous vehicle is within a fixed stopping range of the first vehicle, the autonomous vehicle decelerates and reduces its speed until an appropriate distance between the first vehicle and the autonomous vehicle is reached.

16. The system of claim 10, wherein: Adjusting the trajectory of the autonomous vehicle occurs continuously while negotiating a multi-lane turn.

17. The system according to claim 10, wherein: The trajectory of each of the first vehicle and the second vehicle is tracked by an imaging sensor on the autonomous vehicle.

18. The system of claim 10, wherein: When the autonomous vehicle traverses a multi-lane turn, the trajectory of the autonomous vehicle is adjusted to maintain a staggered position relative to each of the first vehicle and the second vehicle.

Images