Vehicle control around multi-lane corners
By adjusting its trajectory based on position and historical data, the autonomous vehicle mitigates the risks of collisions and improves visibility during multi-lane turns, ensuring a safer and more comfortable driving experience.
Patent Information
- Application Number
- JP2023065302
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2018-10-19
- Filing Date
- 2023-04-13
- Publication Date
- 2024-11-20
- Estimated Expiration
- 2039-10-10
AI Technical Summary
Autonomous vehicles face challenges in safely navigating multi-lane turns due to the risk of being cut off or pinched by other vehicles, leading to uncomfortable or dangerous evasive maneuvers.
The autonomous vehicle adjusts its trajectory based on its position relative to other vehicles and historical data, using sensors to monitor and modify its path to avoid collisions and improve visibility, ensuring a safer and more predictable driving experience.
This approach enhances the safety and comfort of autonomous vehicle navigation in multi-lane turns by reducing the need for evasive maneuvers and improving visibility to surrounding drivers.
Smart Images

Figure 0007587627000001 
Figure 0007587627000002 
Figure 0007587627000003
Abstract
Description
[Technical field]
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to Application No. 16 / 165,114, filed October 19, 2018, the disclosure of which is incorporated herein by reference. [Background technology]
[0002] Autonomous vehicles, i.e. vehicles that do not require a human driver, may be used to assist in the transportation of passengers or goods from one location to another. Such vehicles can operate in a fully autonomous mode, where the passenger can provide some initial inputs, such as a pick-up location and destination, and the autonomous vehicle steers itself to navigate to the location. To do this safely, these vehicles need to be able to detect and identify objects in the environment and respond to them quickly. Typically, these objects are identified from information visible to sensors such as LIDAR, radar, and cameras.
[0003] In some cases, detecting and identifying other vehicles in the vicinity of an autonomous vehicle is paramount to safely maneuvering the autonomous vehicle to a destination. For example, the trajectory of an autonomous vehicle may be affected by the actions of other vehicles traveling around the autonomous vehicle. Thus, being able to detect and respond to such actions may be particularly important to ensure a safe and effective autonomous driving experience. Summary of the Invention
[0004] The technology generally relates to a method of controlling an autonomous vehicle through a multi-lane turn, the method including receiving, by one or more processors, data corresponding to a position of the autonomous vehicle within a lane of a multi-lane turn and a trajectory of the autonomous vehicle, receiving, by the one or more processors, data corresponding to a position of an object proximate the autonomous vehicle, determining whether the autonomous vehicle is positioned as a lead vehicle in the lane or behind another vehicle in the lane based on the position of the autonomous vehicle in the lane relative to the position of the object, adjusting, by one or more processors, the trajectory of the autonomous vehicle through the lane based on whether the autonomous vehicle is positioned as a lead vehicle in the lane or behind another vehicle in the lane, and controlling the autonomous vehicle through the multi-lane turn based on the adjusted trajectory.
[0005] In some embodiments, if the position of the autonomous vehicle is determined to be located as a lead vehicle in the lane, a trajectory may be adjusted based on historical data corresponding to a previous trajectory of one or more vehicles that have passed through the lane. In some examples, the historical data may correspond to a previous trajectory of the autonomous vehicle. In some cases, adjusting the trajectory based on the historical data may 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 may be limited to a predetermined distance to the left or right of the trajectory.
[0006] In some embodiments, if the autonomous vehicle determines that it is behind the other vehicle, it may 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 of the autonomous vehicle. In some cases, the adjusted trajectory may be limited by a predetermined distance to the left or right of the trajectory.
[0007] In some embodiments, adjusting the trajectory of the autonomous vehicle occurs continuously around the multi-lane turn.
[0008] In some embodiments, if the autonomous vehicle determines that it is behind multiple vehicles, it adjusts its trajectory based on the trajectories of the multiple vehicles around the multi-lane turn.
[0009] 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 configured to: receive data corresponding to a position of the autonomous vehicle within a lane of the multi-lane turn, receive data corresponding to a position of an object near the autonomous vehicle, determine whether the autonomous vehicle is positioned as a lead vehicle in the lane or 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, the trajectory of the autonomous vehicle through the lane based on whether the autonomous vehicle is positioned as a lead vehicle in the lane or behind another vehicle in the lane, and control the autonomous vehicle through the multi-lane turn based on the adjusted trajectory.
[0010] In some cases, the one or more processors may be further configured to, if the processor determines the position of the autonomous vehicle as being located as a lead vehicle in the lane, adjust the trajectory based on historical data corresponding to previous trajectories of one or more vehicles that have traversed the lane. In some examples, the historical data corresponds to previous trajectories of the autonomous vehicle.
[0011] In some cases, adjusting the trajectory based on the historical data includes 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 examples, the average lateral displacement may be limited to a predetermined distance to the left or right of the trajectory.
[0012] In some embodiments, the one or more processors may be further configured to adjust the trajectory based on a trajectory of the other vehicle if the autonomous vehicle determines that the autonomous vehicle is behind the other vehicle. In some examples, the trajectory of the other vehicle may be tracked by an imaging sensor of the autonomous vehicle. In some cases, the adjusted trajectory may be limited by a predetermined distance to the left or right of the trajectory.
[0013] In some embodiments, adjusting the trajectory of the autonomous vehicle may occur continuously around the multi-lane turn.
[0014] In some embodiments, the one or more processors may be further configured to, if the autonomous vehicle determines that it is behind multiple vehicles, adjust the trajectory based on trajectories of the multiple vehicles around the multi-lane turn. [Brief description of the drawings]
[0015] [Figure 1] FIG. 1 illustrates an exemplary roadway according to an embodiment of the present disclosure.
[0016] [Diagram 2] FIG. 2 is a functional diagram of an exemplary vehicle according to an embodiment of the disclosure.
[0017] [Diagram 3] FIG. 3 is an exemplary representation of a vehicle according to an embodiment of the present disclosure.
[0018] [Figure 4A]FIG. 4A is an example diagram illustrating a segment of a roadway that an autonomous vehicle is traversing and that corresponds to map information, according to an aspect of the disclosure. [Figure 4B] FIG. 4B is an example diagram illustrating a segment of a roadway that an autonomous vehicle is traversing and that corresponds to map information, according to an aspect of the disclosure.
[0019] [Diagram 5] FIG. 5 is an example diagram illustrating alternative trajectories for an autonomous vehicle according to an embodiment of the disclosure.
[0020] [Figure 6] FIG. 6 is an example diagram illustrating an autonomous vehicle following the trajectory of another vehicle according to an embodiment of the disclosure.
[0021] [Figure 7] FIG. 7 is an example diagram of two vehicles passing through an intersection, according to an embodiment of the present disclosure.
[0022] [Figure 8] FIG. 8 is an example diagram of staggering an autonomous vehicle relative to surrounding vehicles, according to an embodiment of the disclosure.
[0023] [Figure 9] FIG. 9 is an example diagram illustrating an autonomous vehicle traveling too close to surrounding vehicles, according to an embodiment of the disclosure.
[0024] [Figure 10] FIG. 10 is an example diagram illustrating an autonomous vehicle traveling too close to surrounding vehicles, according to an aspect of the disclosure.
[0025] [Figure 11] FIG. 11 is an example diagram illustrating an autonomous vehicle traveling too close to surrounding vehicles, according to an embodiment of the disclosure.
[0026] [Figure 12] FIG. 12 is a flow diagram according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0027] overview The present technology relates to the control of an autonomous vehicle in a multi-lane turn. In this regard, when negotiating a multi-lane turn, i.e., a two- or three-lane left or right turn lane, etc., it is common for drivers to not follow the turn or to cross lane boundaries. For example, FIG. 1 shows a portion of a roadway 100 in which a vehicle 101 is traveling in an inside lane 161 and a vehicle 102 is traveling in an outside lane 162 of a two-lane left turn lane 160. The vehicle 102 traveling in the outside lane 162 encroaches on the inside lane 161 and encroaches on the path of the vehicle 101 traveling in the inside lane 161. To avoid colliding with the vehicle 102, the vehicle 101 may be forced to adjust its trajectory. Vehicles such as the vehicle 101 are often cut in or pushed out of their current trajectory by vehicles traveling in adjacent lanes. Such problems are magnified in autonomous vehicles. An autonomous vehicle may be programmed to follow a trajectory within the lane that the vehicle is in. Thus, while the autonomous vehicle is rounding a multi-lane turn, if the autonomous vehicle is "cut in" or "pinched" by another vehicle, evasive action may be required. Such evasive action may create an uncomfortable or dangerous situation for the occupants of the autonomous vehicle.
[0028] To address these issues, the operation and trajectory of an autonomous vehicle may be adjusted when the autonomous vehicle traverses a multi-lane turn. The trajectory may be adjusted based on the position of the autonomous vehicle relative to other vehicles or based on historical data of the vehicle traversing the multi-lane turn. In this regard, an autonomous vehicle may be in several positions relative to other vehicles when traversing a multi-lane turn, such as the first vehicle in a series of vehicles, the last vehicle in a series of vehicles, between vehicles, etc. For example, when an autonomous vehicle is located at the front of a series of vehicles, the trajectory of the autonomous vehicle may be adjusted to follow an alternative trajectory based on historical data corresponding to previous paths the vehicles took through the multi-lane turn. When the autonomous vehicle is located between or behind other vehicles, the trajectory of the autonomous vehicle may be adjusted to follow the trajectory of the vehicle located in front.
[0029] The historical data may consist of previous paths that the autonomous vehicle or other vehicles have taken around a multi-lane turn, and may be monitored and used to modify the autonomous vehicle's standard trajectory. Based on this historical data, an alternative trajectory may be followed instead of the autonomous vehicle's standard trajectory to more closely approximate the vehicle's previous trajectory around the turn. In some cases, the alternative trajectories may be limited to prevent the autonomous vehicle from deviating too far from a safe operating trajectory.
[0030] When a vehicle is traveling in a lane adjacent to an autonomous vehicle, the autonomous vehicle may adjust its trajectory to be staggered relative to the adjacent vehicle to increase visibility to the driver of the adjacent vehicle. In other words, the autonomous vehicle may continually position itself to be between the vehicles in the adjacent lanes so that the vehicles in the adjacent lanes can see the autonomous vehicle.
[0031] If the autonomous vehicle is unable to maintain a staggered position relative to vehicles in an adjacent lane, the autonomous vehicle may go ahead of or let one of the surrounding vehicles go ahead. The decision to go ahead or let go may be made based on the comfort level of the occupants, and the go ahead or let go maneuver should not cause undue discomfort to the occupants.
[0032] The features described herein enable improved and safe navigation of autonomous vehicles around multi-lane turns. In this regard, the features described herein provide more comfortable turning conditions for occupants of the autonomous vehicle, as evasive maneuvers such as hard braking and steering may be avoided. Additionally, the autonomous vehicle may be positioned to be more visible to surrounding vehicles to reduce the risk that the driver will not see the autonomous vehicle while negotiating a multi-lane turn. Additionally, the behavior of the autonomous vehicle around a multi-lane turn may be made more typical of a human driver, and the behavior of the autonomous vehicle may be more easily predicted by drivers of surrounding vehicles. Exemplary System
[0033] As shown in Figure 2, a vehicle 201 according to an embodiment of the disclosure includes various components. Certain embodiments of the disclosure are particularly useful in connection with certain types of vehicles, which may be any type of vehicle, including, but not limited to, automobiles, trucks, motorcycles, buses, recreational vehicles, etc. The vehicle may have one or more computing devices, such as computing device 210, which may include one or more processors 220, memory 230, and other components typically present in a general-purpose computing device.
[0034] Memory 230 stores information accessible by one or more processors 220, including instructions 234 and data 232 that may be executed or otherwise used by the processors 220. Memory 230 may be any type of memory capable of storing information accessible by a processor, including computing device readable media or other media that store data that can be read using electronic devices such as hard drives, memory cards, ROM, RAM, DVDs or other optical disks, and other writable and read-only memories. Systems and methods may include different combinations of the above whereby different portions of the instructions and data are stored on different types of media.
[0035] The instructions 234 may be any set of instructions executed directly (such as machine code) or indirectly (such as script) by a processor. For example, the instructions may be stored as computing device code on a computing device readable medium. In that regard, the terms "instructions" and "program" may be used interchangeably herein. The instructions may be stored in 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 precompiled. The functions, methods, and routines of the instructions are described in further detail below.
[0036] Data 232 may be retrieved, stored, or modified by processor 220 in accordance with instructions 234. For example, the data may be stored in a computing device register, in a relational database as a table with multiple different fields and records, an XML document, or a flat file, although claimed subject matter is not limited to any particular data structure. The data may also be formatted in any computing device readable format.
[0037] The processor 220 may be any one or more conventional processors, such as a commercially available CPU. Alternatively, the one or more processors may be dedicated devices, such as an ASIC or other hardware-based processor. Although FIG. 2 functionally illustrates the processor, memory, and other elements of the computing device 210 as being in the same block, it will be understood by those skilled in the art that a processor, computing device, or memory may actually include multiple processors, computing devices, or memories that may or may not be stored in the same physical enclosure. For example, the memory 230 may be a hard drive and / or other storage medium located in an enclosure different from that of the computing device 210. Thus, it will be understood that reference to a processor or computing device includes reference to a collection of processors or computing devices or memories that may or may not operate in parallel.
[0038] The computing device 210 may include all of the components typically used in connection with a computing device, such as the processor and memory described above, as well as one or more user input devices 250 (e.g., a mouse, keyboard, touch screen, and / or microphone) and various electronic displays (e.g., a monitor having a screen, or any other electrical device operable to display information). In this example, the vehicle includes an interior electronic display 252, as well as one or more speakers 254 to provide information or an audiovisual 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 occupants and maintenance personnel in or around the vehicle 201.
[0039] The computing device 210 may also include one or more wireless network connections 256 to facilitate communication with other computing devices, such as client and server computing devices, described in more detail below. The wireless network connections may include short-range communication protocols, such as Bluetooth, Bluetooth Low Energy (LE), cellular connections, as well as various configurations and protocols, including the Internet, the World Wide Web, an intranet, a virtual private network, a wide area network, a local network, a private network using one or more corporate proprietary communication protocols, Ethernet, WiFi, and HTTP, and various combinations thereof. The computing device 210 of the vehicle 201 may also send and receive information to and from other computing devices (not shown), such as computing devices that include or store additional map or perception data.
[0040] In one example, the computing device 210 may control a computing device of an autonomous driving computing system integrated into the vehicle 201. This autonomous driving computing system may be capable of communicating with various components of the vehicle to control the movement of the vehicle 201 according to the primary vehicle control code stored in the memory 230. For example, the computing device 210 may communicate with various systems of the vehicle 201, such as a deceleration system 260, an acceleration system 262, a steering system 264, a signaling system 266, a navigation system 268, a positioning system 270, a perception system 272, and a power system 274 (i.e., the vehicle's engine or motor), to control the movement, speed, etc. of the vehicle 201 according to the instructions 234 in the memory 230. Also, although these systems are shown as being external to the computing device 210, in practice, these systems may also be integrated into the computing device 210 as an autonomous driving computing system for controlling the vehicle 201.
[0041] As an example, computing device 210 may interact with one or more actuators or other components of deceleration system 260 and / or acceleration system 262, such as the vehicle's brake, accelerator pedal, and / or engine or motor, to control the vehicle's speed. Similarly, one or more actuators or other components of steering system 264, such as a steering wheel, steering shaft, and / or a pinion and rack of a rack-and-pinion system, may be used by computing device 210 to control the direction of vehicle 201. For example, if vehicle 201 is configured for use on a road, such as a car or truck, the steering system may include one or more actuators or other devices that control the angle of the wheels to turn the vehicle. Signaling system 266 may be used by computing device 210 to communicate the vehicle's intentions to other drivers or vehicles, for example, by illuminating turn signals or brake lights as needed.
[0042] 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 / road map information, such as high-precision maps that identify roadway shape and elevation, lane lines, intersections, crosswalks, speed limits, traffic signals, buildings, signs, real-time traffic information, vegetation, or other such objects and information. For example, FIG. 4A illustrates a portion of roadway 400 showing example map information identifying the shape, location, and other characteristics of various road features proximate intersection 402. In this example, the portion of roadway 400 that corresponds to the map information includes information defining the shape and location of lane markers 410-414, stop line 425, crosswalk 430, 432, sidewalk 440, traffic lights 420, 422, lane markings 471, 472, 473, and the shape and direction of traffic in lanes 461, 462, 465, 466, etc. The portion of roadway 400 illustrates several road features that are included in map information. The map information may include additional roadway features, such as lane lines, shoulder areas, intersections, lanes and bearings, for example. The map information may also identify various other roadway features, such as stop signs, yield signs, railroad tracks, railroad crossings, speed limit signs, road markings, speed bumps, and the like. Although not shown in the portion of roadway 400, the map information may also include information identifying speed limits and other legal traffic requirements, such as the location of stop signs and which vehicles have priority depending on the status of traffic signals.
[0043] Although the detailed map information corresponding to portions of roadway 400 is depicted herein as an image-based map, the map information need not be entirely image-based (e.g., raster). For example, the detailed map information may include one or more road graphs, or graph networks of information such as roads, lanes, intersections, and connections between these features. Each feature may be stored as graph data and may be associated with information such as a geographic location and whether or not it is linked to other related features, e.g., a stop sign may be linked to a road and an intersection. In some examples, the associated data may include a grid-based index of the road graph to enable efficient searching of specific road graph features.
[0044] The positioning system 270 may be used by the computing device 210 to determine the relative or absolute position of the vehicle on a map or on the Earth. For example, the positioning system 270 may include a GPS receiver to determine the latitude, longitude, and / or altitude position of the positioning system. Other location systems, such as laser-based location systems, inertial-aided GPS, or camera-based location may also be used to determine the location of the vehicle. The location of the vehicle may include absolute geographic location information, such as latitude, longitude, and altitude, as well as relative location information, such as location with respect to other vehicles in the immediate vicinity, which can often be determined with less noise than absolute geographic location.
[0045] The positioning system 270 may also include other devices in communication with the computing device 210, such as an accelerometer, gyroscope, or another direction / speed detection device for determining the vehicle's direction and speed, or changes thereto. By way of example only, an acceleration device may determine 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. Provision of device position and orientation data as described herein may be provided automatically to the computing device 210, other computing devices, and combinations of the above.
[0046] The perception system 272 may also include one or more components to detect objects external to the vehicle, such as other vehicles, obstacles in the roadway, traffic signals, signs, trees, etc. For example, the perception system 272 may include lasers, sonar, radar, 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, sonar, radar, cameras, and / or any other detection devices that record data that can be processed by a computing device in the vehicle. In some cases, the perception system may include lasers or other sensors mounted on the roof of the vehicle or other convenient location. 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 their position, 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 lasers or other sensors mounted on the roof or other convenient location.
[0047] For example, FIG. 3 is an exemplary exterior view of vehicle 201. In this example, rooftop sensor housing 310 and dome sensor housing 312 may include one or more lidar sensors, cameras, and / or radar units. Additionally, housing 320 located at the front end of vehicle 200, and housings 330, 332 on the driver's and passenger's sides of the vehicle may each house a lidar sensor. For example, housing 330 is located in front of driver door 360. Vehicle 201 also includes housings 340, 342 for radar units and / or cameras, also located on the roof of vehicle 201. Additional radar units and cameras (not shown) may be installed at the front and rear ends of vehicle 201 and / or at other locations along the roof or rooftop 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 aforementioned sensors may be considered part of the vehicle's perception system 272.
[0048] The computing device 210 may control the direction, speed, acceleration, etc. of the autonomous vehicle 201 by sending commands to various components of the autonomous vehicle 201 based on data received from various system components. For example, the computing device may use map information and data from a navigation system to navigate the autonomous vehicle to a destination fully autonomously. The computing device may use a positioning system to determine the location of the autonomous vehicle and may use a perception system to detect and respond to objects if necessary to safely reach that location. To do so, the computing device may cause the autonomous vehicle to accelerate (e.g., by increasing fuel or other energy provided to the engine by an acceleration system), decelerate (e.g., by reducing fuel provided to the engine, shifting gears, and / or applying brakes by a deceleration system), turn (e.g., by changing the direction of the autonomous vehicle's front or rear wheels by a steering system), and signal these changes (e.g., by illuminating a turn indicator of a signaling system). The acceleration and deceleration systems may thus be part of a drivetrain that includes various components between the engine of the autonomous vehicle and the wheels of the autonomous vehicle. Again, by controlling these systems, the computing device 210 may also control the drivetrain of the autonomous vehicle to operate the vehicle fully autonomously to a destination using data from the map information and navigation system. Exemplary Methods
[0049] In addition to the operations described above and illustrated, various operations are described. It should be understood that the following operations do not have to be performed in the exact order described below. Rather, various steps may be processed in different orders or simultaneously, and steps may also be added or omitted. Additionally, it should be understood that the term autonomous may include semi-autonomous vehicles, including vehicles in which a human driver may take over control of the vehicle.
[0050] When negotiating a multi-lane turn, an autonomous vehicle may be in several positions relative to other vehicles. For example, autonomous vehicle 401 may be compared to vehicle 201 and may be the lead vehicle in a series of vehicles as shown in FIG. 4A, or may be between or behind the series of vehicles as shown in FIGS. 6 and 7, respectively. Although the example described herein shows autonomous vehicle 401 navigating a two-lane left turn 460, the features described herein may be applied to any multi-lane turn. For example, these features may be used for a three-lane left turn, a two-lane right turn, a three-lane right turn, a straight portion of a multi-lane roadway where one or more offsets and / or displacements exist, such as an intersection entrance, exit location, entry lane, exit lane, or other such roadway segment with multiple lanes.
[0051] The trajectory of the autonomous vehicle may be adjusted depending on the position of the autonomous vehicle relative to other vehicles negotiating a multi-lane turn. For example, as shown in the portion of roadway 400 in FIGS. 4A and 4B, autonomous vehicle 401 is in front of a series of vehicles, including vehicle 407 in a two-lane left-turn lane 460. When the autonomous vehicle is positioned in front of the series of vehicles (e.g., as the lead vehicle), it may travel a standard trajectory 480 as when turning one lane, as shown in FIG. 4A. In other words, a computing device of the autonomous vehicle, such as computing device 210, may command autonomous vehicle 401 to travel within its normal operating parameters, or rather, to follow a standard trajectory, such that the autonomous vehicle is centered or near the center of the turn lane, in accordance with typical driving practices.
[0052] Historical data corresponding to previous paths that the autonomous vehicle or other vehicles have taken around a multi-lane turn may be monitored and used to modify the standard 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 standard driving corridor (i.e., a portion of a road that the vehicle typically travels along) defined in map information, may be tracked. Behavior, such as acceleration and deceleration, of other vehicles or the autonomous vehicle may also be tracked. Historical data may be tracked by sensors of the perception system 272, sensors of other vehicles, and / or sensors of the autonomous vehicle, such as sensors located at or near the multi-lane turn.
[0053] The historical data collected by the sensors may include these previous trajectories of vehicles traversing the inside and outside lanes of a two-lane left turn. For example, as shown in FIG. 4B, vehicles 403 and 405 in the outside lane 462 (i.e., the lane with the wider turning radius) of a two-lane left turn tend to move toward and / or move into the inside lane 461 (i.e., the lane with the shorter turning radius). To avoid a collision with a vehicle in the outside lane 462, vehicles traversing the inside lane 461, such as autonomous vehicle 401 and vehicle 407, may follow a trajectory that typically results in a sharper turn than they would normally follow if there were no vehicles in the outside lane 462.
[0054] Based on this historical data, a computing device of vehicle 402, such as computing device 210, or other such computer, may determine that an alternate trajectory should be followed instead of the standard trajectory. In this regard, the trajectory of autonomous vehicle 401 may be adjusted from its standard trajectory to an alternate trajectory that is more similar to the vehicle's previous trajectory traversing the turn. For example, and as discussed above, historical data may indicate that a vehicle traveling in outside lane 462 tends to cross into inside lane 461 while turning. Based on the historical data, computing device 210 may determine an average lateral displacement of the vehicle traversing the turn relative to standard trajectory 480. Standard trajectory 480 of the autonomous vehicle may be adjusted to more closely follow the average lateral displacement such that adjusted trajectory 481 of the autonomous vehicle is similar to the trajectory of other vehicles, as further shown in FIG. 4B. The trajectory of the autonomous vehicle may be adjusted continuously as the autonomous vehicle traverses the multi-lane turn. A computing device of the autonomous vehicle, such as computing device 210, may then control autonomous vehicle 401 according to adjusted trajectory 481. In some cases, the historical data may be filtered prior to determining the average lateral displacement to remove vehicle trajectories beyond a predetermined distance from the standard trajectory.
[0055] The alternate trajectory may be limited to prevent the autonomous vehicle from straying too far from a safe operating trajectory. In this regard, the autonomous vehicle 401 may be limited by a lateral range around the trajectory of the turn (i.e., limited to a distance to the left and / or right of the trajectory). For example, as shown in the map information 500, an unlimited initial alternate trajectory 580 may be outside the range indicated by an "X" that deviates a certain amount, e.g., 2 or 3 feet to the right or left of the standard trajectory, or so. This may result in unsafe driving conditions for the autonomous vehicle 401 and / or other surrounding vehicles.
[0056] To address this, initial alternate trajectory 580 may be modified such that it is within a predefined range "X". For example, as shown in FIG. 5, an unrestricted initial alternate trajectory 580 may result in autonomous vehicle 401 crossing stop line 425 of a vehicle traveling in a lane going in the opposite direction as autonomous vehicle 401. Because the vehicle may be located on or beyond stop line 425, initial alternate trajectory 580 may be adjusted such that it is within predefined range "X", as shown by adjusted trajectory 581. Adjusted trajectory 581 may provide enough space between autonomous vehicle 401 and stop line 425 so that the autonomous vehicle does not run over the stop line. Other boundaries may be based on the placement of lane dividers and other such obstacles that may be on the autonomous vehicle's trajectory.
[0057] A confidence interval may be determined for each portion of the turn to determine whether the alternate trajectory is within a certain distance from the standard trajectory for each portion of the turn. In other words, the confidence interval may be a parameter that can be adjusted to provide a trade-off such that the autonomous vehicle 401 may follow the path of the leading vehicle as long as the path of the leading vehicle is within an arbitrarily determined range of the standard path, otherwise the autonomous vehicle may follow its standard path. In this regard, the turn may be subdivided into a series of intervals of fixed or non-fixed length. Within every interval, a distribution of potential lateral displacements relative to the standard trajectory may be observed via historical data or generated using a model. Based on the distribution of displacements, samples may be generated and assigned an arbitrary confidence interval, such as on the order of 95%. The alternate trajectory may be compared to the sample of displacements to ensure that the alternate trajectory is within a distance, such as on the order of 0.5 meters, from the standard trajectory defined by the sample of displacements with the assigned confidence interval.
[0058] When the autonomous vehicle is between or at the end of a series of vehicles, the autonomous vehicle may follow the trajectory of another vehicle or a vehicle in front of it. In this regard, a perception system of the autonomous vehicle 402, such as the perception system 272, may track in real time the path of the vehicle traversing the same lanes of a multi-lane turn 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, as shown in FIG. 6, the autonomous vehicle 401 is located in the inside lane 461 of a two-lane left turn 460, between vehicles 601 and 603. The perception system 272 of the autonomous vehicle 401 may track the trajectory 680 of the vehicle 601 as it traverses the lane 461. The autonomous vehicle 401 may then follow the same trajectory 680 as the autonomous vehicle traverses the two-lane left turn. In some cases, the trajectory of the autonomous vehicle may be constrained as described herein. That is, an autonomous vehicle may deviate from the trajectory of another vehicle if the trajectory of the other vehicle is outside of a limit range.
[0059] In some cases, vehicles in side-by-side lanes of a multi-lane turn may be positioned too close to each other, thereby reducing the visibility of the other vehicles to the drivers of the other vehicles. In general terms, adjacent vehicles are considered to be in the "blind spot" of the drivers of the surrounding vehicles. In such a situation, there is an increased risk that the driver of a vehicle may encroach into the adjacent lane without realizing that another vehicle is in his or her blind spot. For example, as shown in FIG. 7, vehicle 701 is passing through the inside lane 461 of a two-lane left turn 460. The driver of vehicle 703, which is positioned adjacent to vehicle 701 (and within the blind spot of vehicle 710) and passing on the outside of the outside lane 462, may not be able to see vehicle 701 and may cut in front of vehicle 701 in an attempt to encroach into the inside lane 461.
[0060] To avoid these problems when negotiating a multi-lane turn, the autonomous vehicle's computing device may stagger the autonomous vehicle relative to surrounding vehicles. By doing so, the autonomous vehicle may improve visibility to other drivers of vehicles in front and behind. For example, as shown in FIG. 8, an autonomous vehicle 401 traveling in the inside lane 461 of a two-lane left turn 460 may position itself to be between vehicles 801 and 803 passing in the adjacent outside lane 462. By doing so, vehicles in the adjacent outside lane 462 can see the autonomous vehicle 401. Additionally, by staggering the autonomous vehicle 401 relative to vehicles in the adjacent outside lane 462, fewer actions such as braking and / or accelerating may be required to avoid a collision.
[0061] The autonomous vehicle's computing device may continually adjust the autonomous vehicle's trajectory and position relative to the positions of surrounding vehicles in adjacent lanes. In this regard, the autonomous vehicle's perception system, such as perception system 272, may track the positions of surrounding vehicles in front of (forward surroundings) and behind (backward surroundings) the autonomous vehicle 401 to determine their positions relative to the autonomous vehicle 401. The distance that the autonomous vehicle 401 can maintain between the rear surrounding vehicles and the forward surrounding vehicles may be based on a fixed stopping range. For example, with reference to FIG. 6, the front bumper of the autonomous vehicle 401 may be on the order of one meter away from the rear bumper of the vehicle 601 located in front of the autonomous vehicle. For a surrounding vehicle behind the autonomous vehicle, such as vehicle 603, the rear bumper of the autonomous vehicle 401 may be one meter away from the front bumper of the surrounding vehicle 603.
[0062] The autonomous vehicle's computing device may adjust the autonomous vehicle's speed and / or acceleration to maintain the staggered position based on the distance between the rear surrounding vehicle and the front surrounding vehicle. For example, as shown in FIG 9, if an autonomous vehicle 401 traversing the inside lane of a two-lane left-turn lane 460 is too close to a surrounding vehicle 903 traversing the rear, adjacent outside lane 462, the autonomous vehicle's computing device, such as computing device 210, may accelerate the autonomous vehicle 401, increasing its speed until it reaches an appropriate distance between the rear surrounding vehicle.
[0063] If the autonomous vehicle is positioned too close to the surrounding vehicle ahead, the autonomous vehicle's computing device may slow down the autonomous vehicle's speed and / or reduce acceleration until the surrounding vehicle ahead moves further ahead of the autonomous vehicle. For example, as shown in FIG. 10, if an autonomous vehicle 401 passing through the inside lane of a two-lane left turn lane 460 is too close to the surrounding vehicle ahead 1001, the autonomous vehicle's computing device, such as computing device 210, may slow down and decelerate the autonomous vehicle 401 until it reaches an appropriate distance from the surrounding vehicle ahead 1001.
[0064] When an appropriate spacing between the forward surrounding vehicle and the rearward surrounding vehicle has been reached, the autonomous vehicle's computing device may maintain the autonomous vehicle's current speed and / or acceleration.
[0065] In some cases, the autonomous vehicle may not be able to be staggered due to the forward and / or rear surrounding vehicles. In this regard, the forward and / or rear surrounding vehicles may be too close to each other for the autonomous vehicle to be staggered. In such a situation, the autonomous vehicle may get ahead of or let one of the surrounding vehicles get ahead of it. For example, as shown in FIG. 11, the rear surrounding vehicle 1103 traveling in the outer lane 462 of a two-lane left-turn lane 460 is too close to the forward surrounding vehicle 1101 for the autonomous vehicle to be staggered. In response, the autonomous vehicle 401 passing through the inner lane 461 may let the rear surrounding vehicle 1103 get ahead by decreasing the vehicle's speed and / or acceleration (e.g., the rear surrounding vehicle moves to a location ahead of the autonomous vehicle) or get ahead of the forward surrounding vehicle 1101 by increasing the vehicle's speed and / or acceleration (e.g., the autonomous vehicle moves to a location ahead of the forward surrounding vehicle).
[0066] The decision to go ahead or let go may be based on the passenger's comfort level. In this regard, a computing device such as computing device 210 may monitor the autonomous vehicle's angular trajectory, its current speed, its current acceleration, and its position relative to the surrounding vehicles. Based on these factors, the computing device may determine whether it is more comfortable for the passenger to have the autonomous vehicle go ahead of the surrounding vehicle in front or let the surrounding vehicle behind go ahead. This is because the passenger may feel uncomfortable if the autonomous vehicle gets too close laterally to another vehicle and / or if the autonomous vehicle turns too quickly or too slowly. For example, the autonomous vehicle may monitor factors such as the following distance between the front and rear vehicles, the lateral separation distance between the surrounding vehicles, the braking actions of the surrounding vehicles, etc. Based on those factors and their potential or actual impact on the vehicle's operation, the computing device of the autonomous vehicle may determine whether it is more comfortable for the passenger to go ahead of the surrounding vehicle, let the surrounding vehicle go ahead, or maintain the autonomous vehicle's current position.
[0067] FIG. 12 includes an illustrative flow diagram 1200 of some examples for controlling a vehicle as described above. In this example, the steps of the flow diagram may be executed by one or more processors of one or more computing devices, such as processor 220 of computing device 210 of vehicle 201. For example, in block 1201, one or more processors receive data corresponding to a position of an autonomous vehicle and a trajectory of the autonomous vehicle in a lane of a multi-lane turn. In block 1203, one or more processors receive data corresponding to a position of an object near the autonomous vehicle. In block 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 a lead vehicle in the lane or behind another vehicle in the lane. As shown in block 1207, the trajectory of the autonomous vehicle through the lane may be adjusted by one or more processors based on whether the autonomous vehicle is positioned as a lead vehicle in the lane or behind another vehicle in the lane. As shown in block 1209, the autonomous vehicle may be controlled in the multi-lane turn based on the adjusted trajectory.
[0068] Unless otherwise stated, the aforementioned alternatives are not mutually exclusive, but may be implemented in various combinations to achieve unique advantages. These and other variations and combinations of the above-mentioned features may be utilized without departing from the subject matter defined by the claims, and therefore the foregoing description of the embodiments should be considered as illustrative, and not limiting, of the subject matter defined by the claims. In addition, the examples described herein, as well as the provision of phrases such as "such as," "including," and the like, should not be construed as limiting the subject matter of the claims to any particular examples, but rather, the examples are intended to illustrate merely one of many possible embodiments. Additionally, the same reference numbers in different drawings may identify the same or similar elements.
Claims
1. 1. A method for controlling an autonomous vehicle around a multi-lane corner, comprising: receiving, by one or more processors, data corresponding to a position of the autonomous vehicle and a trajectory of the autonomous vehicle relative to a position of at least one other vehicle in a lane of the multi-lane turn, the at least one other vehicle including a surrounding vehicle relative to the autonomous vehicle; determining, based on the position of the autonomous vehicle relative to the position of the at least one other vehicle, that the autonomous vehicle is located in an inside lane of the multi-lane turn and that the at least one other vehicle is located in an adjacent lane outside the inside lane; determining, by the one or more processors, a distance between the autonomous vehicle and the at least one other vehicle such that the autonomous vehicle is staggered relative to the at least one other vehicle around the multi-lane corner; adjusting, by the one or more processors, the trajectory of the autonomous vehicle based on the distance to maintain the staggered position in the multi-lane turn; and controlling the autonomous vehicle through the multi-lane turn based on the adjusted trajectory.
2. The method of claim 1 , wherein the at least one other vehicle is located in front of the autonomous vehicle such that the at least one other vehicle is a forward surrounding vehicle with respect to the autonomous vehicle.
3. The method of claim 2 , wherein the distance is maintained based on a fixed stopping range.
4. 2. The method of claim 1, wherein a velocity and acceleration of the autonomous vehicle are adjusted to maintain the staggered position of the autonomous vehicle relative to the at least one other vehicle.
5. The method of claim 4 , wherein the velocity and acceleration of the autonomous vehicle are adjusted based on the distance between the autonomous vehicle and the at least one other vehicle.
6. 4. The method of claim 3, wherein when the autonomous vehicle is within the fixed stopping range, the autonomous vehicle accelerates until an appropriate distance between the surrounding vehicles and the autonomous vehicle is reached.
7. 4. The method of claim 3, wherein if the at least one other vehicle includes the forward surrounding vehicle and the autonomous vehicle is within the fixed stopping range, the autonomous vehicle slows down until an appropriate distance between the forward surrounding vehicle and the autonomous vehicle is reached.
8. The method of claim 1 , wherein adjusting the trajectory of the autonomous vehicle occurs continuously around the multi-lane turn.
9. The method of claim 1 , wherein the trajectory of the at least one other vehicle is tracked by an imaging sensor on the autonomous vehicle.
10. 1. A system for controlling an autonomous vehicle around a multi-lane turn, the system comprising: one or more processors, the one or more processors receiving data corresponding to a position of the autonomous vehicle relative to a position of at least one other vehicle within a lane of the multi-lane turn, the position of the at least one other vehicle including a surrounding vehicle relative to the autonomous vehicle and a trajectory of the autonomous vehicle; determining, based on the position of the autonomous vehicle relative to the position of the at least one other vehicle, that the autonomous vehicle is located in an inside lane of the multi-lane turn and that the at least one other vehicle is located in an adjacent lane outboard of the inside lane; determining a distance between the autonomous vehicle and the at least one other vehicle such that the autonomous vehicle is staggered relative to the at least one other vehicle at the multi-lane turn; adjusting the trajectory of the autonomous vehicle based on the distance to maintain the staggered position around the multi-lane turn; and controlling the autonomous vehicle around the multi-lane corner based on the adjusted trajectory.
11. 11. The system of claim 10, wherein the at least one other vehicle is located in front of the autonomous vehicle such that the at least one other vehicle is a forward surrounding vehicle with respect to the autonomous vehicle.
12. The system of claim 11 , wherein the distance is maintained based on a fixed stopping range.
13. 11. The system of claim 10, wherein a velocity and acceleration of the autonomous vehicle are adjusted to maintain the staggered position of the autonomous vehicle relative to the at least one other vehicle.
14. 14. The system of claim 13, wherein the velocity and acceleration of the autonomous vehicle are adjusted based on the distance between the autonomous vehicle and the at least one other vehicle.
15. 13. The system of claim 12, wherein when the autonomous vehicle is within the fixed stopping range, the autonomous vehicle accelerates until an appropriate distance between the rear surrounding vehicles and the autonomous vehicle is reached.
16. 13. The system of claim 12, wherein if the at least one other vehicle includes the ahead surrounding vehicle and the autonomous vehicle is within the fixed stopping range, the autonomous vehicle slows down until an appropriate distance between the ahead surrounding vehicle and the autonomous vehicle is reached.
17. The system of claim 10 , wherein adjusting the trajectory of the autonomous vehicle occurs continuously around the multi-lane turn.
18. The system of claim 10 , wherein the trajectory of the at least one other vehicle is tracked by an imaging sensor on the autonomous vehicle.
Citation Information
Patent Citations
Drive control device and drive control method
JP2014151838A
Drive support apparatus
JP2015120476A
