Selecting vehicle actions based on combination of vehicle action intents

Abstract

Methods and systems for lane change and intent determination are provided. A method for operating an autonomous vehicle is provided. The method includes obtaining first scene data associated with a scene of an autonomous vehicle. The method includes generating a plurality of trajectories for the autonomous vehicle. The method includes selecting a trajectory from a plurality of trajectories. The method includes determining a vehicle action intent for the selected trajectory. The method includes combining the vehicle action intent of the selected trajectory with a set of vehicle action intent to form a plurality of vehicle action intent. The set of vehicle action intent corresponds to a set of trajectories generated from the second scene data prior to the selected trajectory. The method includes selecting a vehicle action for the autonomous vehicle and causing the autonomous vehicle to initiate proceeding of the vehicle action based on selecting the vehicle action.

Description

[0001] Cross - Reference to Related Applications

[0002] This application claims the benefit of priority of U.S. Provisional Patent Application No. 63 / 379,549, filed on October 14, 2022, entitled "SELECTING A VEHICLE ACTION BASED ON A COMBINATION OF VEHICLE ACTION INTENTS", which is hereby incorporated by reference in its entirety for all purposes. Additionally, this application claims the benefit of priority of U.S. Patent Application No. 18 / 149,133, filed on January 2, 2023, entitled "SELECTING A VEHICLE ACTION BASED ON A COMBINATION OF VEHICLE ACTION INTENTS", which is hereby incorporated by reference in its entirety for all purposes. Background Art

[0003] Autonomous vehicles can use multiple methods and systems to determine and implement a trajectory for the autonomous vehicle. However, due to changing conditions in the predicted trajectory, these methods and systems may result in instability in lane - change scenarios. Additionally, these methods and systems may not allow sufficient time to warn surrounding traffic of a potential lane change. Brief Description of the Drawings

[0004] Figure 1 is an example environment of a vehicle that can implement one or more components of an autonomous system;

[0005] Figure 2 is a diagram of one or more systems of a vehicle including an autonomous system;

[0006] Figure 3 is Figure 1 and Figure 2 is a diagram of one or more devices and / or components of one or more systems;

[0007] Figure 4A is a diagram of certain components of an autonomous system;

[0008] Figure 4B is a diagram of an implementation of a neural network;

[0009] Figure 4C and Figure 4D are diagrams illustrating example operations of a CNN;

[0010] Figure 5 is a block diagram illustrating an example of a lane - change system;

[0011] Figure 6 is a flowchart illustrating an example of a routine for controlling a vehicle;

[0012] Figure 7 is a state diagram illustrating an example of a processing state for a lane change process;

[0013] Figure 8 is a block diagram illustrating an example of a vehicle position associated with a lane change process; and

[0014] Figure 9 is a flowchart illustrating an example of a routine for causing a vehicle to change lanes. DETAILED DESCRIPTION

[0015] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. It will be apparent, however, that the embodiments described herein may be practiced without these specific details. In some instances, well-known structures and devices are illustrated in block diagram form in order to avoid unnecessarily obscuring aspects of the present disclosure.

[0016] In the drawings, for ease of description, a specific arrangement or order of illustrative elements (such as those representing systems, devices, modules, instruction blocks, and / or data elements, etc.) is illustrated. However, those skilled in the art will understand that unless explicitly described, the specific order or arrangement of the illustrative elements in the drawings is not intended to imply a required order or sequence of processing, or a separation of processing. Additionally, unless explicitly described, the inclusion of illustrative elements in the drawings is not intended to imply that such elements are required in all embodiments, nor that the features represented by such elements cannot be included in some embodiments or combined with other elements in some embodiments.

[0017] Furthermore, in the drawings, connecting elements (such as solid lines, dashed lines, or arrows, etc.) are used to illustrate connections, relationships, or associations between or among two or more other illustrative elements. The absence of any such connecting element is not intended to imply that no connection, relationship, or association can exist. In other words, some connections, relationships, or associations between elements are not illustrated in the drawings so as not to obscure the present disclosure. Additionally, for ease of illustration, a single connecting element may be used to represent multiple connections, relationships, or associations between elements. For example, if a connecting element represents the communication of a signal, data, or instruction (e.g., "software instruction"), those skilled in the art should understand that such an element may represent one or more signal paths (e.g., a bus) that may be required to affect the communication.

[0018] Although terms such as "first", "second", and / or "third" etc. are used to describe various elements, these elements should not be limited by these terms. The terms "first", "second", and / or "third" are only used to distinguish one element from another. For example, without departing from the scope of the described embodiments, a first contact may be referred to as a second contact, and similarly, a second contact may be referred to as a first contact. Both the first contact and the second contact are contacts, but they are not the same contact.

[0019] The terms used in the description of the various embodiments herein are included only for the purpose of describing specific embodiments and are not intended to be limiting. As used in the description of the various embodiments and the appended claims, the singular forms "a", "an", and "the" are also intended to include the plural forms and may be used interchangeably with "one or more than one" or "at least one", unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items. It will also be understood that when the terms "comprise", "include", "have", and / or "with" are used in this specification, they specify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups.

[0020] As used herein, the terms "communicate" and "communicating" refer to at least one of receiving, receiving, transmitting, delivering, and / or providing information (or information represented by, for example, data, signals, messages, instructions, and / or commands, etc.). For a unit (e.g., a device, a system, a component of a device or system, and / or a combination thereof, etc.) that is to communicate with another unit, this means that the unit can directly or indirectly receive information from the other unit and / or send (e.g., transmit) information to the other unit. This may refer to a direct or indirect connection that is essentially wired and / or wireless. Additionally, even if the information transmitted can be modified, processed, relayed, and / or routed between the first unit and the second unit, the two units can still communicate with each other. For example, even if the first unit receives information passively and does not actively transmit information to the second unit, the first unit can still communicate with the second unit. As another example, if at least one intermediate unit (e.g., a third unit located between the first unit and the second unit) processes the information received from the first unit and transmits the processed information to the second unit, the first unit can communicate with the second unit. In some embodiments, a message may refer to a network packet (e.g., a data packet, etc.) that includes data.

[0021] As used herein, depending on the context, the term "if" is optionally interpreted to mean "when", "while", "in response to determining that", and / or "in response to detecting", etc. Similarly, depending on the context, the phrase "if it has been determined" or "if [stated condition or event] is detected" is optionally interpreted to mean "when determining...", "in response to determining that", or "when [stated condition or event] is detected" and / or "in response to detecting [stated condition or event]", etc. Further, as used herein, the terms "have", "having", or "possess", etc. are intended to be open-ended terms. Additionally, unless otherwise explicitly stated, the phrase "based on" is intended to mean "at least partially based on".

[0022] Reference will now be made in detail to the embodiments, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the various described embodiments. However, it will be apparent to one of ordinary skill in the art that the various described embodiments may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0023] General Overview

[0024] In some aspects and / or embodiments, the systems, methods, and computer program products described herein include and / or implement a lane change system. Due to changing conditions in a predicted trajectory, an automatic change in the trajectory for an autonomous vehicle may be prone to instability. For example, the autonomous vehicle 200 may determine that a lane change trajectory is safe at a given time and initiate a lane change. Before the autonomous vehicle completes the lane change, another vehicle may obstruct the lane change trajectory, causing the autonomous vehicle to abort the lane change. Thus, the autonomous vehicle may fluctuate between determining that the lane change is safe and determining that the lane change is unsafe. In some examples, the autonomous vehicle initiates certain actions based on determining that the lane change is safe and other actions based on determining that the lane change is unsafe. Thus, due to conflicting actions initiated based on alternating determinations of safe and unsafe lane changes, the change in the trajectory may be unstable. In some examples, lane change trajectory instability may also cause the autonomous vehicle to maintain a cycle of lane change attempts and aborts, which may be undesirable (e.g., uncomfortable and / or unsafe) for passengers.

[0025] However, by obtaining confirmation of the intention to change lanes over a period of time, an autonomous vehicle can follow a more stable lane change trajectory and avoid cycles of lane change attempts and aborting. By obtaining such confirmation, the system can determine and verify stable lane change conditions (e.g., conditions where the agent does not repeatedly reach and exit the vehicle lane change trajectory).

[0026] To address the issues of lane change trajectory instability and the cycle of lane change attempts and aborting, the system can obtain multiple confirmations of the intention to change the trajectory over time before initiating the action to change lanes. In some examples, which will be described in further detail below, the autonomous vehicle can determine an initial intention to change lanes and initiate a lane change sequence. Then, as the vehicle continues to determine confirmatory trajectory intentions over time, the autonomous vehicle can maintain its current trajectory for a period of time (e.g., a waiting period). In some cases, if a satisfactory intention determination ratio confirms the intention to change the trajectory, the vehicle can determine to initiate the action to change the trajectory. For example, the autonomous vehicle can scan adjacent lanes to obtain a clear trajectory for changing lanes. The vehicle can determine the intention to change lanes based on an indication that the lane change trajectory is clear. The autonomous vehicle can maintain its trajectory in its initial lane for a set period of time while the autonomous vehicle continues to scan adjacent lanes for a set period of time. Then, the autonomous vehicle can determine that it has received more indications that the lane change trajectory is clear (and the intention to change lanes) than indications that the lane change trajectory is not clear (and the intention to maintain position) during the set period of time. Then, the autonomous vehicle can initiate a lane change along the lane change trajectory.

[0027] In some cases, the vehicle can determine that an alternative trajectory is not clear. In such a case, the autonomous vehicle can maintain its initial trajectory and re-initiate the process to determine whether it should change the trajectory. By virtue of the implementation of the systems, methods, and computer program products described herein, the techniques for lane change provide a stable lane change routine. The techniques for lane change as described herein also provide routines that enable the vehicle to operate using reduced computing resources to address sudden vehicle movement in situations where a lane change is not appropriate. The techniques disclosed herein further provide smoother vehicle operation and increased comfort and safety during lane change.

[0028] Now refer to Figure 1, exemplary environment 100 is illustrated, in which vehicles including autonomous systems and vehicles not including autonomous systems operate. As illustrated, environment 100 includes vehicles 102a - 102n, objects 104a - 104n, routes 106a - 106n, area 108, vehicle - to - infrastructure (V2I) devices 110, network 112, remote autonomous vehicle (AV) system 114, queue management system 116, and V2I system 118. Vehicles 102a - 102n, vehicle - to - infrastructure (V2I) devices 110, network 112, autonomous vehicle (AV) system 114, queue management system 116, and V2I system 118 are interconnected via a wired connection, a wireless connection, or a combination of wired and wireless connections (e.g., establishing a connection for communication, etc.). In some embodiments, objects 104a - 104n are interconnected with at least one of vehicles 102a - 102n, vehicle - to - infrastructure (V2I) devices 110, network 112, autonomous vehicle (AV) system 114, queue management system 116, and V2I system 118 via a wired connection, a wireless connection, or a combination of wired and wireless connections.

[0029] Vehicles 102a - 102n (individually referred to as vehicle 102 and collectively as vehicles 102) include at least one device configured to transport goods and / or passengers. In some embodiments, vehicle 102 is configured to communicate with V2I device 110, remote AV system 114, queue management system 116, and / or V2I system 118 via network 112. In some embodiments, vehicles 102 include cars, buses, trucks, and / or trains, etc. In some embodiments, vehicle 102 is the same as or similar to vehicle 200 described herein (see Figure 2 ). In some embodiments, vehicles 200 in the set of vehicles 200 are associated with an autonomous queue manager. In some embodiments, as described herein, vehicle 102 travels along corresponding routes 106a - 106n (individually referred to as route 106 and collectively as routes 106). In some embodiments, one or more than one vehicle 102 includes an autonomous system (e.g., an autonomous system the same as or similar to autonomous system 202).

[0030] Objects 104a - 104n (individually referred to as object 104 and collectively as objects 104) include, for example, at least one vehicle, at least one pedestrian, at least one cyclist, and / or at least one structure (e.g., building, sign, fire hydrant, etc.). Each object 104 is stationary (e.g., located at a fixed location for a period of time) or moving (e.g., having a speed and associated with at least one trajectory). In some embodiments, object 104 is associated with a corresponding location in region 108.

[0031] Routes 106a - 106n (individually referred to as route 106 and collectively as routes 106) are each associated with (e.g., define) a series of actions (also referred to as a trajectory) that a connected AV can navigate along. Each route 106 begins at an initial state (e.g., a state corresponding to a first spatio - temporal location and / or speed, etc.) and ends at a final target state (e.g., a state corresponding to a second spatio - temporal location different from the first spatio - temporal location) or a target zone (e.g., a subspace of acceptable states (e.g., termination states)). In some embodiments, the first state includes a location where one or more individuals will board the AV, and the second state or zone includes one or more locations where one or more individuals boarding the AV will disembark. In some embodiments, route 106 includes multiple acceptable state sequences (e.g., multiple spatio - temporal location sequences) that are associated with (e.g., define) multiple trajectories. In an example, route 106 includes only high - level actions or imprecise state locations, such as a series of connected roads indicating a direction change at a roadway intersection. Additionally or alternatively, route 106 can include more precise actions or states, such as a specific target lane or precise location within a lane area and a target rate at those locations. In an example, route 106 includes multiple precise state sequences along at least one high - level action with a finite look - ahead horizon to reach an intermediate target, where the combination of consecutive iterations of the finite - horizon state sequences cumulatively corresponds to multiple trajectories that together form a high - level route terminating at the final target state or zone.

[0032] Region 108 includes a physical region (e.g., a geographic region) in which vehicle 102 can navigate. In an example, region 108 includes at least one state (e.g., a country, a province, an individual state among a plurality of states included in a country, etc.), at least a portion of a state, at least one city, at least a portion of a city, and the like. In some embodiments, region 108 includes at least one named arterial (referred to herein as a "road"), such as a highway, an interstate highway, a parkway, an urban street, and the like. Additionally or alternatively, in some examples, region 108 includes at least one unnamed road, such as a lane, a section of a parking lot, a section of a vacant and / or undeveloped area, a dirt road, and the like. In some embodiments, a road includes at least one lane (e.g., a portion of the road through which vehicle 102 can pass). In an example, a road includes at least one lane associated with (e.g., identified based on) at least one lane marking line.

[0033] A vehicle-to-infrastructure (V2I) device 110 (sometimes referred to as a vehicle-to-infrastructure or vehicle-to-everything (V2X) device) includes at least one device configured to communicate with vehicle 102 and / or V2I system 118. In some embodiments, V2I device 110 is configured to communicate with vehicle 102, remote AV system 114, queue management system 116, and / or V2I system 118 via network 112. In some embodiments, V2I device 110 includes a radio frequency identification (RFID) device, a sign, a camera (e.g., a two-dimensional (2D) and / or three-dimensional (3D) camera), a lane marking, a streetlight, a parking meter, and the like. In some embodiments, V2I device 110 is configured to communicate directly with vehicle 102. Additionally or alternatively, in some embodiments, V2I device 110 is configured to communicate with vehicle 102, remote AV system 114, and / or queue management system 116 via V2I system 118. In some embodiments, V2I device 110 is configured to communicate with V2I system 118 via network 112.

[0034] Network 112 includes one or more wired and / or wireless networks. In an example, network 112 includes a cellular network (e.g., a Long-Term Evolution (LTE) network, a third-generation (3G) network, a fourth-generation (4G) network, a fifth-generation (5G) network, a Code Division Multiple Access (CDMA) network, etc.), a Public Land Mobile Network (PLMN), a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a telephone network (e.g., a Public Switched Telephone Network (PSTN)), a private network, an ad hoc network, an intranet, the Internet, a fiber-based network, a cloud computing network, etc., and / or a combination of some or all of these networks.

[0035] The remote AV system 114 includes at least one device configured to communicate with the vehicle 102, the V2I device 110, the network 112, the queue management system 116, and / or the V2I system 118 via the network 112. In an example, the remote AV system 114 includes a server, a server group, and / or other similar devices. In some embodiments, the remote AV system 114 is co-located with the queue management system 116. In some embodiments, the remote AV system 114 participates in the installation of some or all of the components of the vehicle (including autonomous systems, autonomous vehicle computing, and / or software implemented by autonomous vehicle computing, etc.). In some embodiments, the remote AV system 114 maintains (e.g., updates and / or replaces) these components and / or software during the life of the vehicle.

[0036] The queue management system 116 includes at least one device configured to communicate with the vehicle 102, the V2I device 110, the remote AV system 114, and / or the V2I system 118. In an example, the queue management system 116 includes a server, a server group, and / or other similar devices. In some embodiments, the queue management system 116 is associated with a ridesharing company (e.g., an organization for controlling the operation of multiple vehicles (e.g., vehicles including autonomous systems and / or vehicles not including autonomous systems), etc.).

[0037] In some embodiments, the V2I system 118 includes at least one device configured to communicate with the vehicle 102, the V2I device 110, the remote AV system 114, and / or the queue management system 116 via the network 112. In some examples, the V2I system 118 is configured to communicate with the V2I device 110 via a connection different from the network 112. In some embodiments, the V2I system 118 includes a server, a server group, and / or other similar devices. In some embodiments, the V2I system 118 is associated with a municipal authority or a private institution (e.g., a private institution for maintaining the V2I device 110, etc.).

[0038] Provide Figure 1 The number and arrangement of the illustrated elements are provided as an example. Compared with Figure 1 the illustrated elements, there may be additional elements, fewer elements, different elements, and / or elements with different arrangements. Additionally or alternatively, at least one element of the environment 100 may perform one or more functions described as being performed by Figure 1 at least one different element. Additionally or alternatively, at least one set of elements of the environment 100 may perform one or more functions described as being performed by at least one different set of elements of the environment 100.

[0039] Now refer to Figure 2 , vehicle 200 (which may be the same as or similar to vehicle 102 of Figure 1 ) includes an autonomous system 202, a powertrain control system 204, a steering control system 206, and a braking system 208, or is associated with the autonomous system 202, the powertrain control system 204, the steering control system 206, and the braking system 208. In some embodiments, vehicle 200 is the same as or similar to vehicle 102 (see Figure 1 ). In some embodiments, the autonomous system 202 is configured to endow vehicle 200 with autonomous driving capabilities (e.g., implement at least one of the following driving automation or maneuver-based functions, features, and / or devices, etc., the at least one driving automation or maneuver-based function, feature, and / or device enabling vehicle 200 to operate partially or completely without human intervention, including but not limited to fully autonomous vehicles (e.g., vehicles that dispense with reliance on human intervention, such as level 5 ADS-operated vehicles, etc.), highly autonomous vehicles (e.g., vehicles that dispense with reliance on human intervention in certain situations, such as level 4 ADS-operated vehicles, etc.), and / or conditionally autonomous vehicles (e.g., vehicles that dispense with reliance on human intervention in limited situations, such as level 3 ADS-operated vehicles, etc.), etc.). In one embodiment, the autonomous system 202 includes the operational or tactical functionality required to operate vehicle 200 in road traffic and continuously perform a part or all of the dynamic driving task (DDT). In another embodiment, the autonomous system 202 includes an advanced driver assistance system (ADAS) that includes driver support features. The autonomous system 202 supports various levels of driving automation ranging from no driving automation (e.g., level 0) to full driving automation (e.g., level 5). For a detailed description of fully autonomous vehicles and highly autonomous vehicles, reference may be made to SAE International standard J3016: Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems, the entire content of which is incorporated by reference. In some embodiments, vehicle 200 is associated with an autonomous queue manager and / or a ridesharing company.

[0040] The autonomous system 202 includes a sensor suite that includes one or more devices such as a camera 202a, a LiDAR sensor 202b, a Radar sensor 202c, and a microphone 202d. In some embodiments, the autonomous system 202 may include more or fewer devices and / or different devices (e.g., ultrasonic sensors, inertial sensors, GPS receivers (discussed below), and / or odometer sensors for generating data associated with an indication of the distance traveled by the vehicle 200, etc.). In some embodiments, the autonomous system 202 uses one or more devices included in the autonomous system 202 to generate data associated with the environment 100 described herein. The data generated by one or more devices of the autonomous system 202 may be used by one or more systems described herein to observe the environment (e.g., environment 100) in which the vehicle 200 is located. In some embodiments, the autonomous system 202 includes a communication device 202e, an autonomous vehicle computing 202f, a drive-by-wire (DBW) system 202h, and a safety controller 202g.

[0041] The camera 202a includes at least one device configured to communicate with the communication device 202e, the autonomous vehicle computing 202f, and / or the safety controller 202g via a bus (e.g., a bus 302 that is the same or similar to Figure 3 the bus). The camera 202a includes at least one camera (e.g., a digital camera using an optical sensor such as a charge-coupled device (CCD), a thermal camera, an infrared (IR) camera, and / or an event camera, etc.) for capturing images including physical objects (e.g., cars, buses, curbs, and / or people, etc.). In some embodiments, the camera 202a generates camera data as output. In some examples, the camera 202a generates camera data that includes image data associated with the image. In this example, the image data may specify at least one parameter corresponding to the image (e.g., image characteristics such as exposure, brightness, etc., and / or an image timestamp, etc.). In such an example, the image may be in a format (e.g., RAW, JPEG, and / or PNG, etc.). In some embodiments, the camera 202a includes a plurality of independent cameras configured on (e.g., positioned on) the vehicle for capturing images for the purpose of stereoscopic vision (stereo vision). In some examples, the camera 202a includes generating image data and transmitting the image data to the autonomous vehicle computing 202f and / or a queue management system (e.g., the same as Figure 1a plurality of cameras of the same or similar queue management system as the queue management system 116. In such an example, the autonomous vehicle computing 202f determines the depth to one or more objects in the fields of view of at least two of the plurality of cameras based on image data from at least two cameras. In some embodiments, the camera 202a is configured to capture images of objects within a distance relative to the camera 202a (e.g., up to 100 meters and / or up to 1 kilometer, etc.). Thus, the camera 202a includes features such as sensors and lenses optimized for sensing objects at one or more distances relative to the camera 202a.

[0042] In an embodiment, the camera 202a includes at least one camera configured to capture one or more images associated with one or more traffic lights, street signs, and / or other physical objects that provide visual navigation information. In some embodiments, the camera 202a generates traffic light data associated with one or more images. In some examples, the camera 202a generates TLD (Traffic Light Detection) data associated with one or more images including a format (e.g., RAW, JPEG, and / or PNG, etc.). In some embodiments, the camera 202a that generates TLD data is different from other systems incorporating cameras described herein in that the camera 202a may include one or more cameras having a wide field of view (e.g., a wide-angle lens, a fish-eye lens, and / or a lens having a viewing angle of about 120 degrees or greater, etc.) to generate images related to as many physical objects as possible.

[0043] The Light Detection and Ranging (LiDAR) sensor 202b includes being configured to communicate with the communication device 202e, the autonomous vehicle computing 202f, and / or the safety controller 202g via a bus (e.g., with Figure 3at least one device configured to communicate via a bus (e.g., a bus identical or similar to bus 302). The LiDAR sensor 202b includes a system configured to emit light from a light emitter (e.g., a laser emitter). The light emitted by the LiDAR sensor 202b includes light outside the visible spectrum (e.g., infrared light, etc.). In some embodiments, during operation, the light emitted by the LiDAR sensor 202b encounters a physical object (e.g., a vehicle) and is reflected back to the LiDAR sensor 202b. In some embodiments, the light emitted by the LiDAR sensor 202b does not penetrate the physical object it encounters. The LiDAR sensor 202b also includes at least one light detector that detects the light after the light emitted from the light emitter encounters a physical object. In some embodiments, at least one data processing system associated with the LiDAR sensor 202b generates an image (e.g., a point cloud and / or a combined point cloud, etc.) representing the objects included in the field of view of the LiDAR sensor 202b. In some examples, at least one data processing system associated with the LiDAR sensor 202b generates an image representing the boundary of a physical object and / or the surface of a physical object (e.g., the topology of the surface), etc. In such examples, the image is used to determine the boundary of the physical object in the field of view of the LiDAR sensor 202b.

[0044] A Radio Detection and Ranging (Radar) sensor 202c includes at least one device configured to communicate with a communication device 202e, an autonomous vehicle computer 202f, and / or a safety controller 202g via a bus (e.g., a bus identical or similar to Figure 3 bus 302). The Radar sensor 202c includes a system configured to emit (pulsed or continuous) radio waves. The radio waves emitted by the Radar sensor 202c include radio waves within a predetermined spectrum. In some embodiments, during operation, the radio waves emitted by the Radar sensor 202c encounter a physical object and are reflected back to the Radar sensor 202c. In some embodiments, the radio waves emitted by the Radar sensor 202c are not reflected by some objects. In some embodiments, at least one data processing system associated with the Radar sensor 202c generates a signal representing the objects included in the field of view of the Radar sensor 202c. For example, at least one data processing system associated with the Radar sensor 202c generates an image representing the boundary of a physical object and / or the surface of a physical object (e.g., the topology of the surface), etc. In some examples, the image is used to determine the boundary of the physical object in the field of view of the Radar sensor 202c.

[0045] The microphone 202d includes at least one device configured to communicate with the communication device 202e, the autonomous vehicle computing 202f, and / or the safety controller 202g via a bus (e.g., a bus the same or similar to Figure 3 bus 302). The microphone 202d includes one or more microphones (e.g., an array microphone and / or an external microphone, etc.) that capture an audio signal and generate data associated with (e.g., representing) the audio signal. In some examples, the microphone 202d includes a transducer device and / or a similar device. In some embodiments, one or more of the systems described herein can receive data generated by the microphone 202d and determine the position (e.g., distance, etc.) of an object relative to the vehicle 200 based on the audio signal associated with the data.

[0046] The communication device 202e includes at least one device configured to communicate with the camera 202a, the LiDAR sensor 202b, the Radar sensor 202c, the microphone 202d, the autonomous vehicle computing 202f, the safety controller 202g, and / or the DBW (drive-by-wire) system 202h. For example, the communication device 202e can include a device the same or similar to Figure 3 communication interface 314. In some embodiments, the communication device 202e includes a vehicle-to-vehicle (V2V) communication device (e.g., a device for enabling wireless communication of data between vehicles).

[0047] The autonomous vehicle computing 202f includes at least one device configured to communicate with the camera 202a, the LiDAR sensor 202b, the Radar sensor 202c, the microphone 202d, the communication device 202e, the safety controller 202g, and / or the DBW system 202h. In some examples, the autonomous vehicle computing 202f includes devices such as a client device, a mobile device (e.g., a cellular phone and / or a tablet computer, etc.), and / or a server (e.g., a computing device including one or more central processing units and / or graphics processing units, etc.). In some embodiments, the autonomous vehicle computing 202f is the same or similar to the autonomous vehicle computing 400 described herein. Additionally or alternatively, in some embodiments, the autonomous vehicle computing 202f is configured to communicate with an autonomous vehicle system (e.g., an autonomous vehicle system the same or similar to Figure 1 the remote AV system 114), a queue management system (e.g., a queue management system the same or similar to Figure 1 queue management system 116), a V2I device (e.g., a V2I device the same or similar to Figure 1 V2I device 110), and / or a V2I system (e.g., a V2I system the same or similar to Figure 1communicate with a V2I system 118 that is the same as or similar to the V2I system).

[0048] The safety controller 202g includes at least one device configured to communicate with the camera 202a, the LiDAR sensor 202b, the Radar sensor 202c, the microphone 202d, the communication device 202e, the autonomous vehicle computing 202f, and / or the DBW system 202h. In some examples, the safety controller 202g includes one or more controllers (such as an electrical controller and / or an electromechanical controller, etc.) configured to generate and / or transmit control signals to operate one or more devices of the vehicle 200 (such as the powertrain control system 204, the steering control system 206, and / or the braking system 208, etc.). In some embodiments, the safety controller 202g is configured to generate control signals that take precedence over (e.g., override) the control signals generated and / or transmitted by the autonomous vehicle computing 202f.

[0049] The DBW system 202h includes at least one device configured to communicate with the communication device 202e and / or the autonomous vehicle computing 202f. In some examples, the DBW system 202h includes one or more controllers (such as an electrical controller and / or an electromechanical controller, etc.) configured to generate and / or transmit control signals to operate one or more devices of the vehicle 200 (such as the powertrain control system 204, the steering control system 206, and / or the braking system 208, etc.). Additionally or alternatively, one or more controllers of the DBW system 202h are configured to generate and / or transmit control signals to operate at least one different device of the vehicle 200 (such as turn signals, headlights, door locks, and / or windshield wipers, etc.).

[0050] The powertrain control system 204 includes at least one device configured to communicate with the DBW system 202h. In some examples, the powertrain control system 204 includes at least one controller and / or actuator, etc. In some embodiments, the powertrain control system 204 receives control signals from the DBW system 202h, and the powertrain control system 204 causes the vehicle 200 to perform longitudinal vehicle movements (such as starting to move forward, stopping moving forward, starting to move backward, stopping moving backward, accelerating in a certain direction, decelerating in a certain direction, etc.), or perform lateral vehicle movements (such as making a left turn and / or making a right turn, etc.). In an example, the powertrain control system 204 increases, maintains the same, or decreases the energy (such as fuel and / or electricity, etc.) provided to the motor of the vehicle, thereby causing at least one wheel of the vehicle 200 to rotate or not rotate.

[0051] The steering control system 206 includes at least one device configured to rotate one or more wheels of the vehicle 200. In some examples, the steering control system 206 includes at least one controller and / or actuator, etc. In some embodiments, the steering control system 206 rotates two front wheels and / or two rear wheels of the vehicle 200 left or right to turn the vehicle 200 left or right. In other words, the steering control system 206 causes the activities required to regulate the y-axis component of the vehicle's movement.

[0052] The braking system 208 includes at least one device configured to actuate one or more brakes to decelerate the vehicle 200 and / or keep it stationary. In some examples, the braking system 208 includes at least one controller and / or actuator configured to close one or more calipers associated with one or more wheels of the vehicle 200 on the corresponding rotors of the vehicle 200. Additionally or alternatively, in some examples, the braking system 208 includes an automatic emergency braking (AEB) system and / or a regenerative braking system, etc.

[0053] In some embodiments, the vehicle 200 includes at least one platform sensor (not explicitly illustrated) for measuring or inferring the nature of the state or condition of the vehicle 200. In some examples, the vehicle 200 includes platform sensors such as a global positioning system (GPS) receiver, an inertial measurement unit (IMU), a wheel rate sensor, a wheel braking pressure sensor, a wheel torque sensor, an engine torque sensor, and / or a steering angle sensor, etc. Although the braking system 208 is illustrated as being proximal to the vehicle 200 within Figure 2 the vehicle 200, the braking system 208 can be located anywhere within the vehicle 200.

[0054] Now refer to Figure 3 , a schematic diagram illustrating the device 300. As illustrated, the device 300 includes a processor 304, a memory 306, a storage component 308, an input interface 310, an output interface 312, a communication interface 314, and a bus 302. In some embodiments, the device 300 corresponds to: at least one device of the vehicle 102 (e.g., at least one device of the system of the vehicle 102); and / or one or more devices of the network 112 (e.g., one or more devices of the system of the network 112). In some embodiments, one or more devices of the vehicle 102 (e.g., one or more devices of the system of the vehicle 102), and / or one or more devices of the network 112 (e.g., one or more devices of the system of the network 112) include at least one device 300 and / or at least one component of the device 300. As Figure 3As shown, device 300 includes bus 302, processor 304, memory 306, storage component 308, input interface 310, output interface 312, and communication interface 314.

[0055] Bus 302 includes components that permit communication between the components of device 300. In some cases, processor 304 includes a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), and / or an accelerated processing unit (APU), etc.), a microphone, a digital signal processor (DSP), and / or any processing component that can be programmed to perform at least one function (e.g., a field programmable gate array (FPGA) and / or an application specific integrated circuit (ASIC), etc.). Memory 306 includes random access memory (RAM), read only memory (ROM), and / or another type of dynamic and / or static storage device that stores data and / or instructions for use by processor 304 (e.g., flash memory, magnetic memory, and / or optical memory, etc.).

[0056] Storage component 308 stores data and / or software related to the operation and use of device 300. In some examples, storage component 308 includes a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optical disk, and / or a solid state disk, etc.), a compact disk (CD), a digital versatile disk (DVD), a floppy disk, a cassette tape, a magnetic tape, a CD-ROM, a RAM, a PROM, an EPROM, a FLASH-EPROM, an NV-RAM, and / or another type of computer-readable medium, and corresponding drives.

[0057] Input interface 310 includes components that permit device 300 to receive information such as via a user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, and / or a camera, etc.). Additionally or alternatively, in some embodiments, input interface 310 includes sensors for sensing information (e.g., a global positioning system (GPS) receiver, an accelerometer, a gyroscope, and / or an actuator, etc.). Output interface 312 includes components for providing output information from device 300 (e.g., a display, a speaker, and / or one or more light emitting diodes (LEDs), etc.).

[0058] In some embodiments, communication interface 314 includes transceiver-like components (e.g., a transceiver and / or separate receiver and transmitter, etc.) that permit device 300 to communicate with other devices via a wired connection, a wireless connection, or a combination of a wired connection and a wireless connection. In some examples, communication interface 314 permits device 300 to receive information from another device and / or provide information to another device. In some examples, communication interface 314 includes an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, an interface and / or a cellular network interface, etc.

[0059] In some embodiments, the device 300 performs one or more processes described herein. The device 300 performs these processes based on software instructions executed by a processor 304 stored in a computer-readable medium such as a memory 306 and / or a storage component 308. A computer-readable medium (e.g., a non-transitory computer-readable medium) is defined herein as a non-transitory memory device. A non-transitory memory device includes a storage space located within a single physical storage device or a storage space distributed across multiple physical storage devices.

[0060] In some embodiments, software instructions are read into the memory 306 and / or the storage component 308 from another computer-readable medium or from another device via a communication interface 314. When the software instructions stored in the memory 306 and / or the storage component 308 are executed, they cause the processor 304 to perform one or more processes described herein. Additionally or alternatively, instead of software instructions or in combination with software instructions, hardwired circuitry is used to perform one or more processes described herein. Thus, unless otherwise explicitly stated, the embodiments described herein are not limited to any particular combination of hardware circuitry and software.

[0061] The memory 306 and / or the storage component 308 includes a data storage or at least one data structure (e.g., a database, etc.). The device 300 is capable of receiving information from the data storage or at least one data structure in the memory 306 or the storage component 308, storing the information in the data storage or at least one data structure, communicating the information to the data storage or at least one data structure, or searching for the information stored in the data storage or at least one data structure. In some examples, the information includes network data, input data, output data, or any combination thereof.

[0062] In some embodiments, the device 300 is configured to execute software instructions stored in the memory 306 and / or the memory of another device (e.g., another device identical or similar to the device 300). As used herein, the term "module" refers to at least one instruction stored in the memory 306 and / or the memory of another device, which, when executed by the processor 304 and / or the processor of another device (e.g., another device identical or similar to the device 300), causes the device 300 (e.g., at least one component of the device 300) to perform one or more processes described herein. In some embodiments, the module is implemented in software, firmware, and / or hardware, etc.

[0063] Provide Figure 3 The number and arrangement of the illustrated components are provided as examples. In some embodiments, compared with Figure 3Compared with the illustrated components, device 300 may include additional components, fewer components, different components, or components arranged differently. Additionally or alternatively, a set of components of device 300 (e.g., one or more than one component) may perform one or more than one function described as being performed by another component or another set of components of device 300.

[0064] Now referring to Figure 4A , an example block diagram of an autonomous vehicle computing 400 (sometimes referred to as an "AV stack") is illustrated. As illustrated, the autonomous vehicle computing 400 includes a perception system 402 (sometimes referred to as a perception module), a planning system 404 (sometimes referred to as a planning module), a positioning system 406 (sometimes referred to as a positioning module), a control system 408 (sometimes referred to as a control module), and a database 410. In some embodiments, the perception system 402, the planning system 404, the positioning system 406, the control system 408, and the database 410 are included in and / or implemented in an automatic navigation system of a vehicle (e.g., the autonomous vehicle computing 202f of vehicle 200). Additionally or alternatively, in some embodiments, the perception system 402, the planning system 404, the positioning system 406, the control system 408, and the database 410 are included in one or more than one independent system (e.g., one or more than one system the same or similar to the autonomous vehicle computing 400, etc.). In some examples, the perception system 402, the planning system 404, the positioning system 406, the control system 408, and the database 410 are included in one or more than one independent system located in a vehicle and / or at least one remote system as described herein. In some embodiments, any and / or all of the systems included in the autonomous vehicle computing 400 are implemented in software (e.g., software instructions stored in a memory), computer hardware (e.g., via a microprocessor, a microcontroller, an application specific integrated circuit (ASIC), and / or a field programmable gate array (FPGA), etc.), or a combination of computer software and computer hardware. It will also be understood that, in some embodiments, the autonomous vehicle computing 400 is configured to communicate with remote systems (e.g., an autonomous vehicle system the same or similar to the remote AV system 114, a queue management system the same or similar to the queue management system 116, and / or a V2I system the same or similar to the V2I system 118, etc.).

[0065] In some embodiments, the perception system 402 receives data associated with at least one physical object in the environment (e.g., data used by the perception system 402 to detect at least one physical object), and classifies the at least one physical object. In some examples, the perception system 402 receives image data captured by at least one camera (e.g., camera 202a), the image being associated with one or more physical objects within the field of view of the at least one camera (e.g., representing the one or more physical objects). In such examples, the perception system 402 classifies the at least one physical object based on one or more groupings of physical objects (e.g., bicycles, vehicles, traffic signs, and / or pedestrians, etc.). In some embodiments, based on the classification of the physical objects by the perception system 402, the perception system 402 transmits data associated with the classification of the physical objects to the planning system 404.

[0066] In some embodiments, the planning system 404 receives data associated with a destination, and generates data associated with at least one route (e.g., route 106) along which a vehicle (e.g., vehicle 102) can travel towards the destination. In some embodiments, the planning system 404 periodically or continuously receives data from the perception system 402 (e.g., the data associated with the classification of the physical objects described above), and the planning system 404 updates at least one trajectory or generates at least one different trajectory based on the data generated by the perception system 402. In other words, the planning system 404 can perform tasks related to the tactical functions required to operate the vehicle 102 in road traffic. Tactical efforts involve maneuvering the vehicle in traffic during the journey, which includes but is not limited to deciding whether and when to overtake another vehicle, change lanes, or select an appropriate speed, acceleration, deceleration, etc. In some embodiments, the planning system 404 receives data associated with the updated position of the vehicle (e.g., vehicle 102) from the positioning system 406, and the planning system 404 updates at least one trajectory or generates at least one different trajectory based on the data generated by the positioning system 406.

[0067] In some embodiments, the positioning system 406 receives data associated with (e.g., representing) the location of a vehicle (e.g., vehicle 102) in an area. In some examples, the positioning system 406 receives LiDAR data associated with at least one point cloud generated by at least one LiDAR sensor (e.g., LiDAR sensor 202b). In certain examples, the positioning system 406 receives data associated with at least one point cloud from multiple LiDAR sensors, and the positioning system 406 generates a combined point cloud based on the respective point clouds. In these examples, the positioning system 406 compares the at least one point cloud or the combined point cloud with a two-dimensional (2D) and / or three-dimensional (3D) map of the area stored in the database 410. Then, based on the positioning system 406 comparing the at least one point cloud or the combined point cloud with the map, the positioning system 406 determines the position of the vehicle in the area. In some embodiments, the map includes a combined point cloud of the area generated prior to the navigation of the vehicle. In some embodiments, the map includes, but is not limited to, a high-precision map of the roadway geometry, a map describing the connectivity of the road network, a map describing the physical properties of the roadways (such as traffic speed, traffic flow, the number of vehicle and bicycle traffic lanes, lane width, lane traffic direction or the type and location of lane markings, or a combination thereof, etc.), and a map describing the spatial location of road features (such as crosswalks, traffic signs or various types of other driving signal lights, etc.). In some embodiments, the map is generated in real time based on the data received by the perception system.

[0068] In another example, the positioning system 406 receives global navigation satellite system (GNSS) data generated by a global positioning system (GPS) receiver. In some examples, the positioning system 406 receives GNSS data associated with the location of a vehicle in an area, and the positioning system 406 determines the latitude and longitude of the vehicle in the area. In such examples, the positioning system 406 determines the position of the vehicle in the area based on the latitude and longitude of the vehicle. In some embodiments, the positioning system 406 generates data associated with the position of the vehicle. In some examples, based on the positioning system 406 determining the position of the vehicle, the positioning system 406 generates data associated with the position of the vehicle. In such examples, the data associated with the position of the vehicle includes data associated with one or more semantic properties corresponding to the position of the vehicle.

[0069] In some embodiments, the control system 408 receives data associated with at least one trajectory from the planning system 404, and the control system 408 controls the operation of the vehicle. In some examples, the control system 408 receives data associated with at least one trajectory from the planning system 404, and the control system 408 controls the operation of the vehicle by generating and transmitting control signals to cause the powertrain control system (e.g., the DBW system 202h and / or the powertrain control system 204, etc.), the steering control system (e.g., the steering control system 206), and / or the braking system (e.g., the braking system 208) to operate. For example, the control system 408 is configured to perform operational functions such as lateral vehicle motion control or longitudinal vehicle motion control. Lateral vehicle motion control causes the activities required to regulate the y-axis component of the vehicle motion. Longitudinal vehicle motion control causes the activities required to regulate the x-axis component of the vehicle motion. In an example, in the case where the trajectory includes a left turn, the control system 408 transmits a control signal to cause the steering control system 206 to adjust the steering angle of the vehicle 200, thereby causing the vehicle 200 to turn left. Additionally or alternatively, the control system 408 generates and transmits control signals to cause other devices of the vehicle 200 (e.g., headlights, turn signals, door locks, and / or windshield wipers, etc.) to change states.

[0070] In some embodiments, the perception system 402, the planning system 404, the positioning system 406, and / or the control system 408 implement at least one machine learning model (e.g., at least one multi-layer perceptron (MLP), at least one convolutional neural network (CNN), at least one recurrent neural network (RNN), at least one autoencoder, and / or at least one transformer, etc.). In some examples, the perception system 402, the planning system 404, the positioning system 406, and / or the control system 408 implement at least one machine learning model individually or in combination with one or more of the above systems. In some examples, the perception system 402, the planning system 404, the positioning system 406, and / or the control system 408 implement at least one machine learning model as part of a pipeline (e.g., a pipeline for identifying one or more objects located in the environment, etc.). The following are examples of Figures 4B to 4D the implementation of the machine learning model.

[0071] The database 410 stores data transmitted to, received from, and / or updated by the perception system 402, the planning system 404, the positioning system 406, and / or the control system 408. In some examples, the database 410 includes a storage component for storing operation-related data and / or software and using the autonomous vehicle computing 400 of at least one system (e.g., associated with Figure 3the same or similar storage components as the storage component 308). In some embodiments, the database 410 stores data associated with 2D and / or 3D maps of at least one area. In some examples, the database 410 stores data associated with 2D and / or 3D maps of a part of a city, multiple parts of multiple cities, multiple cities, counties, states, and / or countries (e.g., nations), etc. In such examples, a vehicle (e.g., a vehicle the same or similar to the vehicle 102 and / or the vehicle 200) can drive along one or more drivable areas (e.g., single-lane roads, multi-lane roads, highways, back roads, and / or off-road paths, etc.), and cause at least one LiDAR sensor (e.g., a LiDAR sensor the same or similar to the LiDAR sensor 202b) to generate data associated with an image representing the objects included in the field of view of the at least one LiDAR sensor.

[0072] In some embodiments, the database 410 can be implemented across multiple devices. In some examples, the database 410 is included in a vehicle (e.g., a vehicle the same or similar to the vehicle 102 and / or the vehicle 200), an autonomous vehicle system (e.g., an autonomous vehicle system the same or similar to the remote AV system 114), a queue management system (e.g., a queue management system the same or similar to Figure 1 the queue management system 116) and / or a V2I system (e.g., a V2I system the same or similar to Figure 1 the V2I system 118), etc.

[0073] Now refer to Figure 4B , a diagram illustrating the implementation of a machine learning model. More specifically, a diagram illustrating the implementation of a convolutional neural network (CNN) 420. For illustrative purposes, the following description of the CNN 420 will be with respect to implementing the CNN 420 via the perception system 402. However, it will be understood that in some examples, the CNN 420 (e.g., one or more components of the CNN 420) is implemented by other systems different from or in addition to the perception system 402, such as the planning system 404, the positioning system 406, and / or the control system 408, etc. Although the CNN 420 includes certain features as described herein, these features are provided for illustrative purposes and are not intended to limit the present disclosure.

[0074] The CNN 420 includes a plurality of convolutional layers including a first convolutional layer 422, a second convolutional layer 424, and a convolutional layer 426. In some embodiments, the CNN 420 includes a subsampling layer 428 (sometimes referred to as a pooling layer). In some embodiments, the subsampling layer 428 and / or other subsampling layers have dimensions smaller than the dimensions of the upstream system (i.e., the amount of nodes). By means of the subsampling layer 428 having dimensions smaller than the dimensions of the upstream layer, the CNN 420 combines the amount of data associated with the initial input and / or output of the upstream layer, thereby reducing the amount of computation required for the CNN 420 to perform downstream convolutional operations. Additionally or alternatively, by means of the subsampling layer 428 being associated with at least one subsampling function (e.g., configured to perform at least one subsampling function) (as described below with respect to Figure 4C and Figure 4D ), the CNN 420 combines the amount of data associated with the initial input.

[0075] Based on the perception system 402 providing corresponding inputs and / or outputs associated with the first convolutional layer 422, the second convolutional layer 424, and the convolutional layer 426 respectively to generate corresponding outputs, the perception system 402 performs convolutional operations. In some examples, based on the perception system 402 providing data as inputs to the first convolutional layer 422, the second convolutional layer 424, and the convolutional layer 426, the perception system 402 implements the CNN 420. In such examples, based on the perception system 402 receiving data from one or more different systems (e.g., one or more systems of a vehicle the same or similar to the vehicle 102, a remote AV system the same or similar to the remote AV system 114, a queue management system the same or similar to the queue management system 116, and / or a V2I system the same or similar to the V2I system 118, etc.), the perception system 402 provides the data as inputs to the first convolutional layer 422, the second convolutional layer 424, and the convolutional layer 426. The following is a detailed description of Figure 4C including convolutional operations.

[0076] In some embodiments, the perception system 402 provides data associated with an input (referred to as an initial input) to the first convolutional layer 422, and the perception system 402 uses the first convolutional layer 422 to generate data associated with an output. In some embodiments, the perception system 402 provides the output generated by a convolutional layer as an input to a different convolutional layer. For example, the perception system 402 provides the output of the first convolutional layer 422 as an input to the subsampling layer 428, the second convolutional layer 424, and / or the convolutional layer 426. In such an example, the first convolutional layer 422 is referred to as an upstream layer, and the subsampling layer 428, the second convolutional layer 424, and / or the convolutional layer 426 are referred to as downstream layers. Similarly, in some embodiments, the perception system 402 provides the output of the subsampling layer 428 to the second convolutional layer 424 and / or the convolutional layer 426, and in this example, the subsampling layer 428 will be referred to as an upstream layer, and the second convolutional layer 424 and / or the convolutional layer 426 will be referred to as downstream layers.

[0077] In some embodiments, before the perception system 402 provides an input to the CNN 420, the perception system 402 processes data associated with the input provided to the CNN 420. For example, based on the perception system 402 normalizing sensor data (such as, for example, image data, LiDAR data, and / or Radar data, etc.), the perception system 402 processes data associated with the input provided to the CNN 420.

[0078] In some embodiments, based on the perception system 402 performing convolution operations associated with each convolutional layer, the CNN 420 generates an output. In some examples, based on the perception system 402 performing convolution operations associated with each convolutional layer and the initial input, the CNN 420 generates an output. In some embodiments, the perception system 402 generates an output and provides the output to the fully connected layer 430. In some examples, the perception system 402 provides the output of the convolutional layer 426 to the fully connected layer 430, where the fully connected layer 430 includes data associated with a plurality of eigenvalues referred to as F1, F2,..., FN. In this example, the output of the convolutional layer 426 includes data associated with a plurality of output eigenvalues representing predictions.

[0079] In some embodiments, the perception system 402 identifies an eigenvalue associated with the highest likelihood of being the correct prediction among a plurality of predictions, and the perception system 402 identifies a prediction from the plurality of predictions. For example, in the case where the fully connected layer 430 includes eigenvalues F1, F2, ..., FN and F1 is the largest eigenvalue, the perception system 402 identifies the prediction associated with F1 as the correct prediction among the plurality of predictions. In some embodiments, the perception system 402 trains the CNN 420 to generate predictions. In some examples, the perception system 402 trains the CNN 420 to generate predictions based on the perception system 402 providing training data associated with the predictions to the CNN 420.

[0080] Now refer to Figure 4C and Figure 4D , a diagram illustrating an example operation of the CNN 440 that utilizes the perception system 402. In some embodiments, the CNN 440 (e.g., one or more components of the CNN 440) is the same as or similar to the CNN 420 (e.g., one or more components of the CNN 420) (see Figure 4B ).

[0081] In step 450, the perception system 402 provides data associated with an image as an input to the CNN 440 (step 450). For example, as illustrated, the perception system 402 provides data associated with an image to the CNN 440, where the image is a grayscale image represented as values stored in a two-dimensional (2D) array. In some embodiments, the data associated with the image may include data associated with a color image, which is represented as values stored in a three-dimensional (3D) array. Additionally or alternatively, the data associated with the image may include data associated with an infrared image and / or a Radar image, etc.

[0082] In step 455, the CNN 440 performs a first convolution function. For example, based on the CNN 440 providing the values representing the image as inputs to one or more neurons (not explicitly illustrated) included in the first convolutional layer 442, the CNN 440 performs the first convolution function. In this example, the values representing the image may correspond to the values of a region (sometimes referred to as a receptive field) representing the image. In some embodiments, each neuron is associated with a filter (not explicitly illustrated). The filter (sometimes referred to as a kernel) may be represented as an array of values corresponding in size to the values provided as inputs to the neuron. In one example, the filter may be configured to identify edges (e.g., horizontal lines, vertical lines, and / or straight lines, etc.). In successive convolutional layers, the filters associated with the neurons may be configured to successively identify more complex patterns (e.g., arcs and / or objects, etc.).

[0083] In some embodiments, based on CNN 440, the values provided as input to each of the one or more neurons included in the first convolutional layer 442 are multiplied by the values of the filters corresponding to each of the one or more neurons, and CNN 440 performs a first convolutional function. For example, CNN 440 may multiply the values provided as input to each of the one or more neurons included in the first convolutional layer 442 by the values of the filters corresponding to each of the one or more neurons to generate a single value or an array of values as output. In some embodiments, the collective output of the neurons of the first convolutional layer 442 is referred to as a convolutional output. In some embodiments, when each neuron has the same filter, the convolutional output is referred to as a feature map.

[0084] In some embodiments, CNN 440 provides the output of each neuron of the first convolutional layer 442 to the neurons of a downstream layer. For clarity, an upstream layer may be a layer that transmits data to a different layer (referred to as a downstream layer). For example, CNN 440 may provide the output of each neuron of the first convolutional layer 442 to the corresponding neurons of a subsampling layer. In an example, CNN 440 provides the output of each neuron of the first convolutional layer 442 to the corresponding neurons of the first subsampling layer 444. In some embodiments, CNN 440 adds a bias value to the aggregated set of all values provided to each neuron of the downstream layer. For example, CNN 440 adds a bias value to the aggregated set of all values provided to each neuron of the first subsampling layer 444. In such an example, CNN 440 determines the final value to be provided to each neuron of the first subsampling layer 444 based on the aggregated set of all values provided to each neuron and the activation function associated with each neuron of the first subsampling layer 444.

[0085] In step 460, CNN 440 performs a first subsampling function. For example, based on CNN 440 providing the values output by the first convolutional layer 442 to the corresponding neurons of the first subsampling layer 444, CNN 440 may perform a first subsampling function. In some embodiments, CNN 440 performs the first subsampling function based on an aggregation function. In an example, based on CNN 440 determining the maximum input among the values provided to a given neuron (referred to as a max pooling function), CNN 440 performs the first subsampling function. In another example, based on CNN 440 determining the average input among the values provided to a given neuron (referred to as an average pooling function), CNN 440 performs the first subsampling function. In some embodiments, based on CNN 440 providing values to each neuron of the first subsampling layer 444, CNN 440 generates an output that is sometimes referred to as a subsampled convolutional output.

[0086] At step 465, the CNN 440 performs a second convolution function. In some embodiments, the CNN 440 performs the second convolution function in a manner similar to how the CNN 440 performs the first convolution function as described above. In some embodiments, the CNN 440 performs the second convolution function based on the values output by the first subsampling layer 444 being provided as inputs to one or more neurons (not explicitly illustrated) included in the second convolution layer 446. In some embodiments, as described above, each neuron of the second convolution layer 446 is associated with a filter. As described above, the (one or more) filters associated with the second convolution layer 446 may be configured to identify more complex patterns compared to the filters associated with the first convolution layer 442.

[0087] In some embodiments, the CNN 440 performs the second convolution function based on multiplying the values provided as inputs to each of the one or more neurons included in the second convolution layer 446 by the values of the filters corresponding to each of the one or more neurons. For example, the CNN 440 may multiply the values provided as inputs to each of the one or more neurons included in the second convolution layer 446 by the values of the filters corresponding to each of the one or more neurons to generate a single value or an array of values as output.

[0088] In some embodiments, the CNN 440 provides the output of each neuron of the second convolution layer 446 to the neurons of a downstream layer. For example, the CNN 440 may provide the output of each neuron of the first convolution layer 442 to the corresponding neurons of the subsampling layer. In an example, the CNN 440 provides the output of each neuron of the first convolution layer 442 to the corresponding neurons of the second subsampling layer 448. In some embodiments, the CNN 440 adds a bias value to the aggregated set of all values provided to each neuron of the downstream layer. For example, the CNN 440 adds a bias value to the aggregated set of all values provided to each neuron of the second subsampling layer 448. In such an example, the CNN 440 determines the final value provided to each neuron of the second subsampling layer 448 based on the aggregated set of all values provided to each neuron and the activation function associated with each neuron of the second subsampling layer 448.

[0089] In step 470, the CNN 440 performs a second subsampling function. For example, based on the values output by the second convolutional layer 446 being provided to the respective neurons of the second subsampling layer 448 by the CNN 440, the CNN 440 may perform the second subsampling function. In some embodiments, based on the CNN 440 using an aggregation function, the CNN 440 performs the second subsampling function. In an example, as described above, based on the CNN 440 determining the maximum input or average input among the values provided to a given neuron, the CNN 440 performs the first subsampling function. In some embodiments, based on the CNN 440 providing values to the respective neurons of the second subsampling layer 448, the CNN 440 generates an output.

[0090] In step 475, the CNN 440 provides the output of each neuron of the second subsampling layer 448 to the fully connected layer 449. For example, the CNN 440 provides the output of each neuron of the second subsampling layer 448 to the fully connected layer 449 such that the fully connected layer 449 generates an output. In some embodiments, the fully connected layer 449 is configured to generate an output associated with a prediction (sometimes referred to as classification). The prediction may include an indication that the object(s) included in the image provided as input to the CNN 440 include an object and / or a set of objects, etc. In some embodiments, the perception system 402 performs one or more operations and / or provides data associated with the prediction to different systems described herein.

[0091] Due to inconsistent conditions within the lane change trajectory, a lane change may be prone to instability. For example, if an autonomous vehicle receives an indication of an intention to change lanes and the autonomous vehicle determines that the lane is clear, the autonomous vehicle may initiate a lane change. However, in some instances, an agent such as another vehicle may enter the lane change trajectory after the autonomous vehicle has initiated a lane change but before the autonomous vehicle has completed the lane change. In some such instances, the autonomous vehicle may determine that an undesired lane change condition (e.g., an unsafe / uncomfortable lane change condition) has been detected. Due to the undesired lane change condition, the planning system 404 may determine not to change lanes. In some instances, the planning system may determine that the lane change trajectory is desirable based on data received from the perception system 402 after determining the undesired lane change condition. Thus, the vehicle may determine to change lanes due to safe lane change conditions. Since roadway conditions can change smoothly, in some examples, the roadway conditions fluctuate such that the planning system 404 continuously fluctuates between a lane change indication and a maintain lane indication. This fluctuation between the lane change indication and the maintain lane indication may result in uncomfortable and / or unsafe conditions for the passengers of the autonomous vehicle 200 and the vehicles surrounding the autonomous vehicle 200. Therefore, an intention determination system and / or a lane change system may be used to provide a desired level of roadway condition certainty prior to physically initiating a lane change.

[0092] Lane Change System

[0093] Figure 5 is a block diagram illustrating an example of a lane change system 500. The lane change system 500 may be a subsystem of the planning system 404 and may provide a mechanism for an autonomous vehicle 200 to confirm an intended action to be taken by the autonomous vehicle 200. The lane change system 500 may provide confirmation of the vehicle action intention for the autonomous vehicle 200 and increase trajectory determination stability. The lane change system 500 may further receive and validate vehicle trajectory options to determine whether to initiate and / or terminate an operating state within the planning system 404.

[0094] At Figure 5In the example shown, the lane change system 500 includes a safety trajectory generator 502, an input trajectory generator 504, a trajectory selector 506, a trajectory intention selector 508, a collective intention selector 510, and a state manager 512. The trajectory selector 506 may receive data associated with the trajectories generated by the safety trajectory generator 502 and / or the input trajectory generator 504. The trajectory intention selector 508 may receive from the trajectory selector 506 data associated with the selected trajectory. The collective intention selector 510 may receive from the trajectory intention selector 508 data associated with the intention of the trajectory. The state manager 512 may receive from the collective intention selector 510 data associated with the selected intention. The state manager 512 may generate or include instructions to cause the lane change system 500 to initiate one of three states: a ready-to-act state, an initiate-act state, and an act-disabled state.

[0095] The safety trajectory generator 502 generates a safety trajectory (also referred to herein as a safety stop option) based on a safety trajectory policy for the autonomous vehicle 200. For example, the safety trajectory generator 502 may determine a trajectory that includes a collision probability with an agent that meets a probability threshold (e.g., below a specific collision probability), or select from a set of trajectories the one with the lowest collision probability with the agent. For example, the safety trajectory may be a trajectory that causes the autonomous vehicle 200 to maintain the lane in which it is set or a trajectory that causes the autonomous vehicle 200 to change lanes to the lane that is farthest from nearby agents. In some examples, the safety trajectory may include vehicle actions that cause the autonomous vehicle 200 to accelerate, slow down, or stop.

[0096] The input trajectory generator 504 generates a trajectory based on an input into the lane change system 500. In some examples, the input trajectory generator 504 generates a trajectory based on an input from a user. For example, the user may input instructions to follow a specific route. In some examples, the user may input a path instruction that includes a preselected route determined by a GPS navigation system. The user may also manually input a route by entering a destination or path input before or during operation of the autonomous vehicle 200. In some examples, the user input is based on a steering input. In some examples, the route may be input by a portion of the planning system 404 that is separate from the lane change system 500. For example, the planning system 404 may determine that a trajectory should be followed to cause the autonomous vehicle 200 to follow a route specified by the GPS navigation system. Then, the input trajectory generator 504 may generate a trajectory based on the input from the GPS navigation system to cause the autonomous vehicle 200 to follow the route determined by the input trajectory generator 504 based on the data from the GPS navigation system.

[0097] The input trajectory generator 504 may also generate a trajectory based on an object or an agent in the vehicle scenario. For example, when the autonomous vehicle 200 is navigating, the perception system 402 may sense the environment of the vehicle (e.g., the vehicle scenario) and identify an object or an agent in the vehicle scenario. Based on the environment and the object or the agent in the vehicle scenario, the input trajectory generator 504 may generate a trajectory that enables the autonomous vehicle 200 to navigate the scenario (e.g., without colliding with the object or the agent).

[0098] The trajectory selector 506 selects a trajectory generated from the input trajectory generator 504 and / or the safety trajectory generator 502. For example, the trajectory selector 506 may determine whether one or more input trajectories from the input trajectory generator 504 meet a safety threshold and / or a desired criterion, such as a comfort criterion, an efficiency criterion, or an average speed criterion, etc. If the input trajectory meets the safety threshold and / or the desired criterion, the trajectory selector 506 may select the input trajectory. However, if the input trajectory does not meet the safety threshold and / or the desired criterion, the trajectory selector 506 may select a safety trajectory.

[0099] The trajectory intention selector 508 determines a trajectory intention based on the trajectory selected by the trajectory selector 506. The trajectory intention may be an intended action for the autonomous vehicle 200 to follow the selected trajectory. For example, the trajectory intention selector 508 may determine whether the selected trajectory includes a lane change intention or an intention to maintain a lane position. If the trajectory intention selector 508 determines that the trajectory selected by the trajectory selector 506 includes a lane change intention, the trajectory intention selector 508 may determine the lane change intention. If the trajectory intention selector 508 does not determine that the trajectory determined by the trajectory selector 506 includes a lane change, the trajectory intention selector 508 may determine an intention to maintain the current lane.

[0100] In some cases, the trajectory intention selector 508 may determine the intention of a trajectory based on the movement (e.g., lateral movement) and / or the orientation associated with the trajectory. For example, if the trajectory includes a lateral movement greater than a threshold amount (e.g., greater than 6 feet), but ends with the same orientation (or substantially the same orientation), the trajectory intention selector 508 may determine that the trajectory intention is a lane change. Similarly, if the trajectory includes adjusting the orientation (or the steering wheel) by a threshold degree (e.g., 15 degrees) for a period of time and then returning to the original orientation (or the steering wheel position), the trajectory intention selector 508 may determine that the trajectory intention is a lane change.

[0101] As another example, if the trajectory includes a lateral movement that is less than a threshold amount (e.g., less than 4 feet) and ends in the same orientation (or substantially the same orientation), the trajectory intent selector 508 may determine that the trajectory intent is to stay in the same lane. As yet another example, if the trajectory includes an orientation change that is greater than a threshold amount (e.g., an orientation change greater than 45 degrees), the trajectory intent selector 508 may determine that the trajectory intent is to turn. Thus, it will be understood that the trajectory intent selector 508 may use various mechanisms to determine the intent of a trajectory. In some cases, this may be referred to as classifying a trajectory between different actions or different intents, such as maintaining a lane, changing a lane, turning, and the like.

[0102] The collective intent selector 510 groups multiple trajectory intents selected by the trajectory intent selector 508 over time. The collective intent selector 510 may determine a collective intent based on a set of trajectory intents selected by the trajectory intent selector 508. The collective intent may be a determination of the majority or a threshold number of expected trajectories collected over time. In some examples, the collective intent selector 510 may place vehicle motion intents together with a set of vehicle motion intents taken over a period of time in a data buffer to determine a collective intent based on scenario data. For example, the collective intent selector 510 may determine a collective intent based on trajectory intents collected over a period of time (e.g., 2 seconds, 3 seconds, 5 seconds, 10 seconds, etc.). For example, the planning system 404 may use trajectory intents collected every 0.2 seconds (or some other frequency) for a 5-second period (or some other period) to determine a collective intent. In other examples, the planning system 404 may determine a collective intent over any desired period of time (e.g., 10 seconds, 20 seconds, 30 seconds, 1 minute, 3 minutes, etc.).

[0103] In some examples, the collective intent selector 510 may determine a collective intent based on a threshold number (e.g., a majority, a largest percentage, etc.) of the trajectory intents collected that have the same intent. For example, if a majority of the collected trajectory intents have a "change lane" intent, the collective intent selector 510 may determine that the collective intent is "change lane". In some cases, the collective intent is binary: change lane or maintain lane. For example, in a case where the planning system 404 determines that there is a first lane in which the autonomous vehicle 200 is traveling and a second lane adjacent to the lane in which the autonomous vehicle 200 is traveling, the collective intent may indicate whether the autonomous vehicle 200 should stay in the first lane or move from the first lane of the scenario to the second lane. In certain cases, the collective intent may have more than two options.

[0104] The status manager 512 can be configured to operate the lane change system 500 in at least one of a plurality of states related to vehicle maneuvers. In the illustrated example, the states include a ready-to-act state 514, a start-act state 516, a pause-act state 518, and an act-disabled state 520. However, it will be understood that the status manager 512 may include fewer or more states depending on the desire. For example, the start-act state 516 and the pause-act state 518 may be combined into a start-act state 516.

[0105] In the ready-to-act state 514, the planning system 404 causes the sensing system 402 to obtain the vehicle trajectory and determine (collectively) the vehicle maneuver intent and select a vehicle maneuver based on the vehicle trajectory. In some cases, the ready-to-act state 514 includes a waiting period during which the planning system 404 may collect the trajectory, determine the vehicle maneuver intent based on the trajectory, and use the set of vehicle maneuver intents to determine the collective vehicle maneuver intent (also referred to herein as the collective intent). If the vehicle maneuver (or collective intent) is confirmed during (or after) the waiting period, the planning system 404 may move from the ready-to-act state 514 to the start-act state 516. If the vehicle maneuver is not confirmed during (or after) the waiting period, the planning system 404 may move from the ready-to-act state 514 to the pause-act state 518.

[0106] In the start-act state 516, the planning system 404 initiates an action in the autonomous vehicle based on the selected vehicle maneuver (or selected collective intent). Additionally, in the start-act state 516, the planning system 404 may confirm the vehicle maneuver (or collective intent). If the planning system 404 confirms the vehicle maneuver (e.g., the collective intent has not changed), the planning system 404 may complete the vehicle maneuver and move from the start-act state 516 to the act-disabled state 520. If the planning system 404 does not confirm the vehicle maneuver (e.g., the collective intent has changed), the planning system 404 may move from the start-act state 516 to the pause-act state 518.

[0107] In the action disabled state 520, the planning system 404 can cause the autonomous vehicle 200 to maintain its current trajectory or operate in a trajectory maintenance state, and thus not operate in the ready-to-act state 514 or the initiate-action state 516. In the action disabled state 520, the autonomous vehicle can maintain a previously generated or current trajectory and can determine one or more vehicle action intentions or collective intentions. If the collective intention changes (e.g., from maintaining a lane to changing a lane), then the planning system 404 can move from the action disabled state 520 to the ready-to-act state 514. However, if the collective intention does not change (e.g., stays in the lane maintenance), then the planning system 404 can stay in the action disabled state 520.

[0108] In the paused-action state 518, the planning system reviews the collective intention of the vehicle. If, during a threshold time period, the collective intention is to not take a particular action (e.g., maintain a lane instead of changing a lane), then the planning system 404 can move from the paused-action state 518 to the action disabled state 520. If, during the threshold time period, the collective vehicle action intention confirms a vehicle action (e.g., the collective intention is to change a lane or becomes to change a lane), then the planning system 404 can move from the paused-action state 518 to the initiate-action state 516.

[0109] In some examples, when the collective intention selector 510 determines a collective intention to take an action, the state manager 512 can be determined to operate in the ready-to-act state 514. For example, when the collective intention is to change a lane, the state manager 512 can be determined to operate in the ready-to-act state 514.

[0110] As described above, the state manager 512 can determine in which state to cause the planning system 404 to operate based on data received from the collective intention selector 510 associated with the collective intention. For example, after the collective intention selector 510 evaluates a first selected intention, the collective intention selector 510 can be determined to operate in the ready-to-act state 514. In some examples, when the collective intention selector 510 determines a collective intention to take an action (e.g., change a lane) after a predetermined time interval, the state manager 512 can be determined to operate in the initiate-action state 516.

[0111] In some examples, when the collective intent selector 510 determines that the collective intent is to take no action (e.g., stay in the current lane), the state manager 512 may determine to operate in the action disabled state 520. In some examples, the collective intent selector 510 determines that the collective intent is to take no action after the state manager 512 has previously initiated the ready action state 514. In this case, the action disabled state 520 may take precedence over the ready action state 514. Accordingly, the state manager 512 may initiate the action disabled state 520 and terminate the ready action state 514. Then, the lane change system 500 may restart the time interval for determining the collective intent before re-evaluating whether to move to the ready action state 514 again.

[0112] Figure 6 is a flowchart of an example process 600 for vehicle trajectory intent determination. In some examples, one or more than one of the steps described with respect to process 600 are performed by the lane change system 500 (e.g., fully and / or partially, etc.) (e.g., where the lane change system 500 is implemented by the planning system 404 and where the planning system 404 is implemented by the autonomous system 202). In some examples, one or more than one of the steps described with respect to process 600 are performed by the planning system 404 (e.g., fully and / or partially, etc.) (e.g., where the planning system 404 is implemented by the autonomous system 202). Additionally or alternatively, in some examples, one or more than one of the steps described with respect to process 600 are performed by another device or group of devices (such as the perception system 402, etc.) that is separate from or includes the planning system 404 (e.g., fully and / or partially, etc.) (e.g., where the perception system 402 is implemented by the autonomous system 202).

[0113] At block 602, the planning system 404 receives / obtains scene data (e.g., semantic image data) associated with the environment or scenario of the vehicle. In some examples, where the scene data is semantic image data, the scene data may identify at least one physical object in the environment. For example, the planning system 404 may receive semantic image data for identifying cars, pedestrians, road features, and traffic signals, etc. in the environment around the autonomous vehicle 200.

[0114] In some examples, the scenario data identifies agents in the environment based on semantic image data received from the perception system 402. As described herein, in some examples, the perception system 402 may implement at least one machine learning model as part of a pipeline for classifying one or more objects located in the environment. The planning system 404 may identify these objects from the semantic image data based on the classification of the various objects. For example, the planning system 404 may identify one or more cars, pedestrians, road features, or traffic signals as corresponding objects based on the data received from the perception system 402. In some examples, the scenario data may identify the lanes of a road. For example, the perception system 402 may detect at least two lanes, such as the lane in which the autonomous vehicle 200 is located and the lane adjacent to the lane in which the detected autonomous vehicle 200 is located, etc.

[0115] At block 604, the planning system 404 generates a trajectory for the autonomous vehicle 200 based on the scenario data received from the perception system 402. For example, the scenario data may be generated based on at least one object / agent identified by the perception system 402 in the scenario. The planning system 404 may also determine the trajectory at least in part based on the position of the autonomous vehicle relative to at least one object / agent identified in the scenario. In some examples, the planning system 404 may determine the distance of the autonomous vehicle from the object.

[0116] Additionally or alternatively, the planning system 404 may determine the orientation of the autonomous vehicle relative to the object. In some examples, the planning system 404 may generate at least one trajectory based on the detected at least two lanes and the determined position of the autonomous vehicle 200 relative to the at least two lanes. Thus, in some examples, the planning system 404 may determine a lane change trajectory based on the position of the autonomous vehicle 200 relative to the agents and other objects in the scenario.

[0117] At block 606, the planning system 404 selects a trajectory from the trajectories generated by the planning system 404. In some examples, the planning system 404 may determine multiple potential trajectories for the autonomous vehicle 200 and compare the multiple potential trajectories of the autonomous vehicle 200. Then, the planning system 404 may be based on, as described above regarding Figure 5The described criteria or evaluations are used to select a desired trajectory. In some examples, the planning system 404 selects a trajectory based on a vehicle planning strategy. For example, the planning system 404 can select a desired trajectory based on safety (e.g., avoiding collisions or near-collisions), regulatory compliance (e.g., obeying traffic laws), or comfort priorities (not decelerating / accelerating more than a threshold amount or not adjusting the orientation more than a threshold amount within a threshold time period). In some examples, the planning system 404 can run a safety simulation, rank the safety of detailed trajectories, and select a detailed trajectory having a safety ranking that meets a safety threshold and / or having the highest safety ranking.

[0118] At block 608, the planning system 404 determines the vehicle action intent. The planning system 404 determines the intended action based on the data generated regarding the trajectory. As described herein, the planning system 404 can determine whether the trajectory results in or is likely to cause a lane change. For example, the determined trajectory can include portions where the autonomous vehicle 200 maintains its lane position. Alternatively or additionally, the determined trajectory can include a lane change. Thus, the vehicle action intent can be at least partially based on the determined trajectory and cause the autonomous vehicle 200 to follow the determined trajectory. For example, if a trajectory including a lane change is selected, determining the vehicle action intent can include determining that the selected trajectory includes a lane change. As described herein, in some cases, the planning system 404 uses one or more of the following to determine the trajectory intent: the lateral movement amount from the start to the end of the trajectory, the change in orientation during the trajectory (e.g., adjusting the orientation by a threshold number of degrees and then returning to the original orientation), etc.

[0119] At block 610, the planning system 404 combines the vehicle action intent with a previously generated set of vehicle action intents. The planning system 404 can combine the vehicle action intents to reduce the probability of aborting an initiated action due to changes in the conditions in the scene around the autonomous vehicle 200. In some examples, the planning system 404 can determine the vehicle action intent multiple times to confirm that the vehicle action intent remains the same over time. For example, the planning system 404 can determine the vehicle action intent at a predetermined time interval (e.g., 1 second, 2 seconds, 5 seconds, 10 seconds, etc.) over a predetermined time period (e.g., 3 seconds, 5 seconds, 10 seconds, 20 seconds, etc.) to confirm the vehicle action intent over time. The planning system 404 can also evaluate a set of vehicle action intents obtained over a period of time relative to each other to determine whether the majority or a predetermined number of vehicle action intents indicate a consistent intent to change lanes. In some examples, the planning system 404 can place the vehicle action intent in a data buffer (e.g., a first-in-first-out buffer) together with the determined set of vehicle action intents to combine the vehicle action intent with the set of vehicle action intents.

[0120] At block 612, the planning system 404 selects a vehicle action (or collective intent). In some examples, the vehicle action is selected based on a combination of individual vehicle action intents. In some examples, the planning system 404 determines the collective intent of the autonomous vehicle 200 based on multiple vehicle action intents as described herein and uses the collective intent to select the vehicle action. In some examples, the planning system 404 may select a vehicle action (or collective intent for selecting the vehicle action) corresponding to a threshold amount of vehicle action intent. In some examples, the vehicle action (or collective intent for selecting the vehicle action) may be selected based on a ratio of vehicle action intents. For example, the planning system 404 may select a vehicle action based on a majority or a plurality of individual vehicle action intents over a period of time. For example, if a set of individual vehicle action intents over a predetermined period of time includes three vehicle action intents to change lanes and two vehicle action intents to maintain lane position, the planning system 404 may select a vehicle action to change lanes based on the majority of the vehicle action intents. In other examples, the vehicle action may be selected based on a consensus determination of vehicle action intents over a period of time or corresponding vehicle action intents for a threshold number over a period of time, regardless of the majority of vehicle action intents.

[0121] At block 614, the planning system 404 causes the autonomous vehicle 200 to perform an action corresponding to the selected vehicle action. For example, if the selected vehicle action is to change lanes, the planning system 404 may cause the autonomous vehicle 200 to change lanes. The determined vehicle action may cause the autonomous vehicle 200 to initiate performance of the vehicle action such that the autonomous vehicle 200 remains in the first lane for a threshold period of time. Alternatively or additionally, the determined vehicle action may cause the autonomous vehicle 200 to move from the first lane to the second lane when the threshold period of time expires.

[0122] In some examples, the planning system 404 can cause the autonomous vehicle 200 to initiate the performance of vehicle actions by keeping the autonomous vehicle 200 in a first lane for a threshold period of time (e.g., a waiting period). In some examples, the planning system 404 can cause the autonomous vehicle 200 to generate a second plurality of vehicle action intentions during the threshold period of time. The planning system 404 can cause the autonomous vehicle 200 to move from the first lane to the second lane based on determining that the second plurality of vehicle action intentions correspond to the first plurality of vehicle action intentions. For example, the planning system 404 can cause the autonomous vehicle 200 to move from the first lane to the second lane when the threshold period of time expires based on determining that a threshold amount of the second plurality of vehicle action intentions corresponds to the first plurality of vehicle action intentions (e.g., indicating a lane change).

[0123] The planning system 404 can transmit instructions to the drive-by-wire system 202h, which transmits instructions to at least one of the powertrain control system 204, the steering control system 206, and the braking system 208 to cause the autonomous vehicle 200 to perform the selected vehicle actions. For example, the planning system 404 can send instructions to cause the powertrain control system 204 to accelerate and cause the autonomous vehicle 200 to move toward the second lane, etc. The planning system 404 can send instructions to cause the steering control system 206 to navigate the autonomous vehicle 200 into the second lane. The planning system 404 can send instructions to cause the braking system 208 to slow down the autonomous vehicle 200 to merge into the second lane, etc.

[0124] Lane change system

[0125] Figure 7 is a state diagram that illustrates examples of different states of a lane change system (such as lane change system 500, etc.) that is part of a lane change process. As described herein, the lane change system 500 can form at least a part of the planning system 404 and operate in multiple states during various points in a lane change sequence. The states can provide a routine to the lane change system 500 that includes intermediate steps between a lane change indication, a lane change initiation, and a lane change completion.

[0126] The states and routines can provide a more stable lane change sequence and avoid jerky behavior that may occur due to the vehicle repeatedly initiating and aborting lane changes (or other actions). In some or all states, the lane change system 500 can perform or execute decision logic that causes the lane change system 500 to progress through different states, which in turn can cause the autonomous vehicle 200 to move through the lane change sequence towards lane change initiation or towards restarting the lane change sequence based on intent-based confirmation. Thus, the lane change system 500 can confirm the vehicle action intent and prepare for lane change initiation without causing the autonomous vehicle 200 to make a physical action.

[0127] In the illustrated example, the lane change system 700 includes the following states: an action disabled state 702, a prepare action state 704, an initiate action state 706, and a pause action state 708. However, it will be understood that the lane change system 500 can include fewer or more states. For example, in some cases, the initiate action state 706 and the pause action state 708 can be combined into one state.

[0128] When in the action disabled state 702, the lane change system 500 can keep the autonomous vehicle in the current lane. For example, if the autonomous vehicle 200 is traveling in the first lane and the lane change system 500 is in the action disabled state 702, the lane change system 500 can cause the autonomous vehicle 200 to continue traveling in the first lane. The lane change system 500 can also check whether it should participate in a safety stop option (e.g., whether the vehicle should participate in an emergency stop, etc.).

[0129] Additionally, in the action disabled state 702, the lane change system 500 uses one or more vehicle action intents to determine the intent (or collective intent) of the vehicle. For example, as described herein at least with reference to Figure 5 and Figure 6 the lane change system 500 can determine the collective intent based on one or more trajectories and / or one or more vehicle action intents. However, if the lane change system 500 determines that the (collective) intent is to change lanes, the lane change system 500 can move to the prepare action state 704.

[0130] In the prepare action state 704, the autonomous vehicle 200 can remain in its lane but signal the lane change (e.g., activate a turn signal, wirelessly communicate the lane change intent to other vehicles such as the autonomous vehicle, etc.). As described herein at least with reference to Figure 5As described above, the lane change system 500 may also check for a safe trajectory or a safe stop option to determine whether a safe stop option is desirable (e.g., determined to be safer) on a lane change or a lane change trajectory. Additionally, in the ready-to-act state 704, the lane change system 500 may wait for a threshold time period (also referred to herein as a wait period).

[0131] In some cases, at the end of the wait period, the lane change system 500 checks the (collective) intent of the vehicle. The size of the wait period may be adjusted such that some or all of the vehicle action intents used to determine the collective intent for moving the lane change system 500 from the action-disabled state 702 to the ready-to-act state 704 are not used to determine the collective intent at the end of the wait period. For example, if a data buffer for collecting vehicle action intents stores vehicle action intents for two seconds, the wait period may be greater than two seconds such that all vehicle action intents used to move the lane change system 500 to the ready-to-act state 704 are not used at the end of the wait period, or the wait period may be 0.5 seconds such that approximately 75% of the vehicle action intents used to move the lane change system 500 to the ready-to-act state 704 are used at the end of the wait period (or the wait period may be 1 second such that approximately 50% of the vehicle action intents used to move the lane change system 500 to the ready-to-act state 704 are used at the end of the wait period), and so on.

[0132] If (at the end of the wait period) the lane change system 500 determines that the (collective) intent is to change lanes, the lane change system 500 may operate (or move to) the initiating-action state 706. If the lane change system 500 determines that the intent is to maintain the lane, the lane change system 500 operates (or changes to) the paused-action state 708.

[0133] In the initiating-action state 706, the lane change system 500 causes the planning system 404 to initiate a lane change. As part of initiating the lane change, the lane change system 500 may cause the vehicle to start moving into a different lane (e.g., by adjusting the steering wheel or the orientation of the vehicle, etc.).

[0134] When the lane change system 500 initiates a lane change, the lane change system 500 may check whether a safe stop option is more desirable compared to the lane change trajectory (e.g., determined that the vehicle should participate in an emergency stop, etc.). Additionally, the lane change system 500 may check the collective intent to determine whether the collective intent has changed (e.g., from changing lanes to maintaining the lane). In some such cases, the lane change system 500 may not use the wait period before checking the (collective) intent of the vehicle.

[0135] If the collective intent is (or remains) to change lanes, lane change system 500 may cause autonomous vehicle 200 to complete a lane change. For example, lane change system 500 may cause autonomous vehicle 200 to complete its movement to another lane.

[0136] If the (collective) intent is to maintain the lane, lane change system 500 may enter a pause action state 708. In pause action state 708, lane change system 500 may cause autonomous vehicle 200 to maintain its current lane (and / or move back to the center of the current lane) and start a timer. Lane change system 500 may also check whether a safe stop option is more desirable than a lane change.

[0137] Additionally, in pause action state 708, lane change system 500 may check the (collective) intent of the vehicle to determine whether the (collective) intent is to change lanes or maintain the lane. If the (collective) intent is to change lanes (or changes to changing lanes), lane change system 500 may move to an initiate action state 706. If the (collective) intent is (or remains) to maintain the lane for a threshold time period (e.g., 3 seconds, 5 seconds, 10 seconds), lane change system 500 may move to an action disabled state 702. When moving to action disabled state 702, lane change system 500 may prevent fluctuations between initiating a lane change and aborting a lane change.

[0138] Figure 8 is a block diagram illustrating an example of vehicle 802 using lane change system 500 to change lanes. Figure 8 Illustrates vehicle 802 performing a lane change sequence while avoiding agent 804 in an adjacent lane. Vehicle 802 (substantially similar to autonomous vehicle 200) is disposed in a first lane, and agent 804 is disposed in a second lane adjacent to the first lane. The perception system 402 of autonomous vehicle 802 obtains data associated with the vehicle scenario at five consecutive time intervals, including an indication of the second lane. The planning system 404 determines one or more trajectories at each time interval based on the data provided by the perception system 402 and generates a vehicle action intent according to the lane trajectories.

[0139] At a first time interval T1, agent 804 does not obstruct the lane change trajectory, and lane change system 500 (e.g., based on the vehicle action intent at or before T1) determines that the collective intent is to change lanes. Assuming that lane change system 500 is in action disabled state 702 at T1, lane change system 500 may move from action disabled state 702 to a ready action state 704.

[0140] During a second time interval T2, the agent 804 obstructs a lane change trajectory, and the lane change system 500 determines the vehicle motion intention during T2 to be maintaining the lane. In the case where it is assumed that T2 is during the waiting period of the ready-to-act state 704, the lane change system 500 may collect the vehicle motion intention but may not take action on it.

[0141] During a third time interval T3, the agent 804 does not obstruct the lane change trajectory, and the lane change system 500 determines the vehicle motion intention during T3 to be changing the lane. In the case where it is assumed that T3 is at the end of the waiting period, the lane change system 500 may determine the collective intention based on the vehicle motion intention collected during part or all of T2 and part, all, or none of T1. Based on the vehicle motion intention of maintaining the lane collected during T2, the lane change system 500 may determine that the (collective) intention is to maintain the lane. Thus, the lane change system 500 may move from the ready-to-act state 704 to the paused-act state 708, and continue to monitor the vehicle motion intention and determine the collective intention.

[0142] During a fourth time interval T4, the agent 804 is determined to be in the second lane and does not obstruct the lane change trajectory, and the lane change system 500 determines that the vehicle motion intention during T4 is to change the lane. In the case where it is assumed that the lane change system 500 is in the paused-act state 708 during T4, the lane change system 500 may determine the collective intention based on the vehicle motion intention collected during T3, part, all, or none of T2, and / or part, all, or none of T1. In the case where it is assumed that the lane change system 500 determines the collective intention to be changing the lane, the lane change system 500 may move to the initiate-act state 706.

[0143] During a fifth time interval T5 (and in the case where the lane change system 500 is still in the initiate-act state 706), the lane change system 500 continues to collect the vehicle motion intention and determine the collective intention. Depending on the amount of vehicle motion intention used to determine the collective intention, the lane change system 500 may determine the collective intention based on the vehicle motion intention collected during part or all of T4, part, all, or none of T3, and / or part, all, or none of T2. Based on the collected vehicle motion intention, the lane change system 500 determines that the collective intention is to change the lane, causing the autonomous vehicle 802 to complete the lane change from the first lane to the second lane, and move to the act-disabled state 702.

[0144] Figure 9FIG. is a flow diagram illustrating an example of process 900 for vehicle lane change. In some examples, one or more of the steps described with respect to process 900 are performed by lane change system 500 (e.g., fully and / or partially, etc.) (e.g., where lane change system 500 is implemented by planning system 404, and where planning system 404 is implemented by autonomous system 202). Additionally or alternatively, in some examples, one or more of the steps described with respect to process 900 are performed by another device or group of devices (such as sensing system 402, etc.) separate from or including planning system 404 (e.g., fully and / or partially, etc.) (e.g., where sensing system 402 is implemented by autonomous vehicle computing 400).

[0145] At block 902, planning system 404 receives / obtains a first plurality of lane change indications. The first plurality of lane change indications can be vehicle action intentions as described above with respect to Figure 6 the vehicle. In some examples, the lane change indication can be a manual indication by a user, such as pressing a button or issuing any other user input to indicate an intention to change lanes, etc. In some examples, the lane change intention is determined by planning system 404 as a determination to meet lane change criteria such as safety and the user's intention to change lanes. In some examples, as described above with respect to Figure 5 the vehicle, the first plurality of lane change indications are continuously determined over a certain time period.

[0146] At block 904, planning system 404 determines to change lanes based on the lane change indications. In some examples, a specific number of consecutive lane change indications indicate a lane change intention. In other examples, a specific majority of the lane change indications can confirm a lane change. For example, lane change system 500 can use a plurality of vehicle action intentions (e.g., a majority or multiple) to determine a collective intention to change lanes, and based on that collective intention, determine to change lanes.

[0147] At block 906, planning system 404 initiates a waiting period or hold period. The waiting period can be the time period between determining to change lanes and when planning system 404 initiates a lane change as described herein. In some cases, the waiting period can be a period sufficient to provide a desired probability of a change condition in a potential lane change trajectory.

[0148] During the waiting period, the planning system 404 can activate the turn signal to allow the surrounding traffic to respond to the turn signal. For example, the planning system 404 can initiate a five-second waiting period and activate the turn signal during the waiting period. During the five-second waiting period, the planning system 404 can allow the traffic around the autonomous vehicle 200 to respond to the turn signal and evaluate the lane change trajectory, vehicle motion intent, and collective intent based on any adjustments made by the surrounding traffic.

[0149] At block 908, the planning system 404 obtains a second plurality of lane change indications. As described above with respect to Figure 5 the second plurality of lane change indications can be sequential indications based on a plurality of vehicle motion intents. In some examples, the planning system 404 can cause the autonomous vehicle 200 to generate the second plurality of lane change indications during the waiting period. In some cases, the second plurality of lane change indications includes some or all of the first plurality of lane change indications. In certain cases, the second plurality of lane change indications does not include any of the first plurality of lane change indications.

[0150] At block 910, the planning system 404 causes the autonomous vehicle 200 to change lanes based on the second plurality of lane change indications. In some cases, the planning system 404 can cause the autonomous vehicle 200 to move from a first lane to a second lane based on determining that the second plurality of lane change indications is consistent with the first plurality of lane change indications. For example, the planning system 404 can cause the autonomous vehicle 200 to move from the first lane to the second lane when the waiting period expires based on determining that a threshold amount of the second plurality of lane change indications corresponds to the first plurality of lane change indications and indicates a lane change. In some cases, the planning system 404 can cause the autonomous vehicle 200 to move from the first lane to the second lane based on the collective intent determined using the second plurality of lane change indications. For example, if the plurality of lane change indications are vehicle motion intents, the planning system 404 can use the second plurality of vehicle motion intents to determine the collective intent. Based on determining that the collective intent is to change lanes (similar to the determination made at block 904), the planning system 404 can cause the vehicle to change lanes.

[0151] To cause the vehicle to change lanes, the planning system 404 may transmit an instruction to the steer-by-wire system 202h, which transmits an instruction to at least one of the powertrain control system 204, the steering control system 206, and the braking system 208 to cause the autonomous vehicle 200 to follow the selected path. For example, the planning system 404 may send an instruction to cause the powertrain control system 204 to change direction and move the autonomous vehicle 200 toward the second lane, send an instruction to cause the steering control system 206 to navigate the autonomous vehicle 200 into the second lane, and / or send an instruction to cause the braking system 208 to slow the autonomous vehicle 200 to merge into the second lane.

[0152] Figure 6 and Figure 9 The flowcharts illustrated in Figure 6 and Figure 9 are for illustrative purposes only. It will be understood that one or more than one of the steps of the routines illustrated in Figure 6 may be removed, or the order of the steps may be changed. Additionally, it will be understood that one or more than one step from Figure 9 may be combined with one or more than one step from

[0153] For the purpose of illustration of clear examples, one or more specific system components are described in the context of performing various operations during the respective data flow phases. However, other system arrangements and distributions of processing steps across system components may be used.

[0154] In the foregoing description, aspects and embodiments of the present disclosure have been described with reference to numerous specific details, which may vary depending on the implementation. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indication of the scope of the invention, and what the applicant desires to be the scope of the invention, is the literal and equivalent scope of the claims that issue from this application in the specific form of the granted patent claims, including any subsequent amendments. Any definition expressly set forth herein for terms to be included in such claims shall govern the meaning of such terms as used in the claims. Additionally, when the term "further comprising" is used in the foregoing specification or the appended claims, the text following that phrase may be additional steps or entities, or sub-steps / sub-entities of the previously recited steps or entities.

[0155] Various additional example embodiments of the present disclosure may be described by the following clauses:

[0156] Clause 1. A method for operating an autonomous vehicle, the method comprising: obtaining a first plurality of consecutive lane change indications, wherein each lane change indication in the first plurality of consecutive lane change indications is generated based on corresponding scene data associated with a scene of the autonomous vehicle, and wherein each lane change indication in the first plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in a first lane of the scene or should move from the first lane to a second lane of the scene; determining, based on the first plurality of consecutive lane change indications, to move the autonomous vehicle from the first lane to the second lane; initiating a waiting period based on the determination to move the vehicle from the first lane to the second lane; obtaining a second plurality of consecutive lane change indications during the waiting period, wherein each lane change indication in the second plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane or should move from the first lane to the second lane; and moving the autonomous vehicle from the first lane to the second lane based on the second plurality of consecutive lane change indications.

[0157] Clause 2. The method according to Clause 1, further comprising: generating a plurality of trajectories according to first scene data; selecting a first trajectory from the plurality of trajectories; and generating a lane change indication in the first plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication in the first plurality of consecutive lane change indications corresponds to a respective trajectory generated from corresponding scene data.

[0158] Clause 3. The method according to Clause 1, wherein obtaining the first plurality of consecutive lane change indications includes: obtaining the first plurality of consecutive lane change indications, wherein each consecutive lane change indication in the first plurality of consecutive lane change indications is generated at a different time.

[0159] Clause 4. The method according to Clause 1, wherein determining to move the autonomous vehicle from the first lane to the second lane includes: changing the state of the autonomous vehicle to a ready lane change state.

[0160] Clause 5. The method according to Clause 1, wherein determining to move the autonomous vehicle from the first lane to the second lane includes: determining to move the autonomous vehicle from the first lane to the second lane based on a threshold amount of lane change indications among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicating that the autonomous vehicle should move from the first lane of the scenario to the second lane of the scenario.

[0161] Clause 6. The method according to Clause 1, wherein determining to move the autonomous vehicle from the first lane to the second lane includes: determining to move the autonomous vehicle from the first lane to the second lane based on a majority of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicating that the autonomous vehicle should move from the first lane of the scenario to the second lane of the scenario.

[0162] Clause 7. The method according to Clause 1, wherein obtaining at least one lane change indication among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications includes: obtaining consecutive lane change indications within a predetermined time range.

[0163] Clause 8. The method according to Clause 1 further includes: generating a plurality of trajectories from first scenario data; selecting a first trajectory from the plurality of trajectories; and generating a lane change indication in the second plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication in the second plurality of consecutive lane change indications corresponds to a respective trajectory generated from the respective scenario data.

[0164] Clause 9. The method according to Clause 1, wherein moving the autonomous vehicle from the first lane to the second lane includes: moving the autonomous vehicle from the first lane to the second lane based on a threshold amount of lane change indications among the second plurality of consecutive lane change indications indicating that the autonomous vehicle should move from the first lane of the scenario to the second lane of the scenario.

[0165] Clause 10. The method according to Clause 1, wherein causing the autonomous vehicle to move from the first lane to the second lane based on the second plurality of consecutive lane change indications includes: causing the autonomous vehicle to move from the first lane to the second lane based on at least one lane change indication of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications.

[0166] Clause 11. A system, comprising: at least one processor; and at least one non-transitory storage medium storing instructions that, when executed by the at least one processor, cause the at least one processor to: obtain a first plurality of consecutive lane change indications, wherein each lane change indication of the first plurality of consecutive lane change indications is generated based on corresponding scenario data associated with a scenario of an autonomous vehicle, and wherein each lane change indication of the first plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in a first lane of the scenario or should move from the first lane to a second lane of the scenario; determine, based on the first plurality of consecutive lane change indications, to cause the autonomous vehicle to move from the first lane to the second lane; initiate a waiting period based on determining to cause the vehicle to move from the first lane to the second lane; obtain a second plurality of consecutive lane change indications during the waiting period, wherein each lane change indication of the second plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane or should move from the first lane to the second lane; and cause the autonomous vehicle to move from the first lane to the second lane based on the second plurality of consecutive lane change indications.

[0167] Clause 12. The system according to Clause 11, wherein the at least one processor is further configured to: generate a plurality of trajectories from first scenario data; select a first trajectory of the plurality of trajectories; and generate a lane change indication of the first plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication of the first plurality of consecutive lane change indications corresponds to a corresponding trajectory generated from corresponding scenario data.

[0168] Clause 13. The system according to Clause 11 or 12, wherein the at least one processor is further configured to generate a plurality of trajectories from first scenario data, wherein obtaining the first plurality of consecutive lane change indications includes: obtaining a first plurality of consecutive lane change indications, wherein each of the consecutive lane change indications of the first plurality of consecutive lane change indications is generated at different times.

[0169] Clause 14. The system according to any one of Clauses 11 to 13, wherein the at least one processor is further configured to instruct the autonomous vehicle to move from the first lane of the scenario to the second lane of the scenario based on a lane change indication determined to be a threshold amount of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications, and cause the autonomous vehicle to move from the first lane to the second lane.

[0170] Clause 15. The system according to any one of Clauses 11 to 14, wherein determining to cause the autonomous vehicle to move from the first lane to the second lane includes: determining to cause the autonomous vehicle to move from the first lane to the second lane of the scenario based on a majority of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicating that the autonomous vehicle should move from the first lane to the second lane of the scenario.

[0171] Clause 16. At least one non-transitory storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to: obtain a first plurality of consecutive lane change indications, wherein each lane change indication in the first plurality of consecutive lane change indications is generated based on corresponding scenario data associated with a scenario of an autonomous vehicle, and wherein each lane change indication in the first plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in a first lane of the scenario or move from the first lane to a second lane of the scenario; determine, based on the first plurality of consecutive lane change indications, to cause the autonomous vehicle to move from the first lane to the second lane; initiate a waiting period based on determining to cause the vehicle to move from the first lane to the second lane; obtain a second plurality of consecutive lane change indications during the waiting period, wherein each lane change indication in the second plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane or move from the first lane to the second lane; and cause the autonomous vehicle to move from the first lane to the second lane based on the second plurality of consecutive lane change indications.

[0172] Clause 17. The at least one non-transitory storage medium according to Clause 16, wherein the at least one processor is further configured to: generate a plurality of trajectories from first scenario data; select a first trajectory from the plurality of trajectories; and generate a lane change indication in the first plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication in the first plurality of consecutive lane change indications corresponds to a respective trajectory generated from the corresponding scenario data.

[0173] Clause 18. The at least one non-transitory storage medium according to Clause 16 or 17, wherein the at least one processor is further configured to generate a plurality of trajectories from first scenario data, wherein obtaining the first plurality of consecutive lane change indications includes: obtaining the first plurality of consecutive lane change indications, wherein each consecutive lane change indication in the first plurality of consecutive lane change indications is generated at a different time.

[0174] Clause 19. The at least one non-transitory storage medium according to any one of Clauses 16 to 18, wherein the at least one processor is further configured to move the autonomous vehicle from the first lane to the second lane of the scenario based on determining that a threshold amount of lane change indications among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicate that the autonomous vehicle should move from the first lane to the second lane of the scenario.

[0175] Clause 20. The at least one non-transitory storage medium according to any one of Clauses 16 to 19, wherein determining to move the autonomous vehicle from the first lane to the second lane includes: determining to move the autonomous vehicle from the first lane to the second lane based on determining that a majority of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicate that the autonomous vehicle should move from the first lane to the second lane of the scenario.

[0176] Clause 21. A method for operating an autonomous vehicle, the method comprising: obtaining, by at least one processor, first scenario data associated with a scenario of the autonomous vehicle; generating, based on the first scenario data, a plurality of trajectories for the autonomous vehicle; selecting a trajectory from the plurality of trajectories; determining a vehicle action intention of the selected trajectory; combining the vehicle action intention of the selected trajectory with a set of vehicle action intentions to form a plurality of vehicle action intentions, wherein the set of vehicle action intentions corresponds to a set of trajectories generated from second scenario data before the selected trajectory; selecting, based on the plurality of vehicle action intentions, a vehicle action for the autonomous vehicle; and causing the autonomous vehicle to initiate performance of the vehicle action based on selecting the vehicle action.

[0177] Clause 22. The method according to Clause 21, wherein generating the plurality of trajectories includes: generating the plurality of trajectories based on at least one object identified in the scenario and a determined position of the autonomous vehicle relative to the at least one object.

[0178] Clause 23. The method according to Clause 21, wherein generating the plurality of trajectories includes: generating the plurality of trajectories based on at least two detected lanes and the determined position of the autonomous vehicle relative to the at least two lanes.

[0179] Clause 24. The method according to Clause 21, wherein selecting the trajectory includes: selecting the trajectory based on a vehicle planning strategy.

[0180] Clause 25. The method according to Clause 21, wherein determining the vehicle action intention includes: determining that the selected trajectory includes a lane change.

[0181] Clause 26. The method according to Clause 21, wherein combining the vehicle action intention with the set of vehicle action intentions includes: placing the vehicle action intention together with the set of vehicle action intentions in a buffer.

[0182] Clause 27. The method according to Clause 21, wherein selecting a vehicle action for the autonomous vehicle based on the plurality of vehicle action intentions includes: selecting a vehicle action corresponding to a threshold amount of vehicle action intentions among the vehicle action intentions.

[0183] Clause 28. The method according to Clause 21, wherein selecting a vehicle action for the autonomous vehicle based on the plurality of vehicle action intentions includes: selecting a vehicle action corresponding to the majority of the vehicle action intentions.

[0184] Clause 29. The method according to Clause 21, wherein the vehicle action is a lane change, and wherein causing the autonomous vehicle to initiate the performance of the vehicle action includes: causing the autonomous vehicle to change lanes.

[0185] Clause 30. The method according to Clause 21, wherein the vehicle action is a lane change, and wherein causing the autonomous vehicle to initiate the performance of the vehicle action includes: causing the autonomous vehicle to remain in a first lane for a threshold time period, and causing the autonomous vehicle to move from the first lane to a second lane when the threshold time period expires.

[0186] Clause 31. The method according to Clause 21, wherein the vehicle action is a lane change, and wherein causing the autonomous vehicle to initiate the performance of the vehicle action includes: causing the autonomous vehicle to remain in a first lane for a threshold time period, and causing the autonomous vehicle to move from the first lane to a second lane when the threshold time period expires.

[0187] Clause 32. The method according to Clause 21, wherein the vehicle action is a lane change, wherein the plurality of vehicle action intents are a first plurality of vehicle action intents, and wherein causing the autonomous vehicle to initiate the performance of the vehicle action includes: causing the autonomous vehicle to remain in a first lane for a threshold time period; generating a second plurality of vehicle action intents during the threshold time period; and causing the autonomous vehicle to move from the first lane to a second lane when the threshold time period expires based on determining that a threshold amount of the vehicle action intents in the second plurality of vehicle action intents indicates a lane change.

[0188] Clause 33. A system, comprising: at least one processor; and at least one non-transitory storage medium storing instructions that, when executed by the at least one processor, cause the at least one processor to: obtain first scene data associated with a scene of an autonomous vehicle using the at least one processor; generate a plurality of trajectories for the autonomous vehicle based on the first scene data; select a trajectory from the plurality of trajectories; determine a vehicle action intent of the selected trajectory; combine the vehicle action intent of the selected trajectory with a set of vehicle action intents to form a plurality of vehicle action intents, wherein the set of vehicle action intents corresponds to a set of trajectories generated from second scene data prior to the selected trajectory; select a vehicle action for the autonomous vehicle based on the plurality of vehicle action intents; and cause the autonomous vehicle to initiate the performance of the vehicle action based on selecting the vehicle action.

[0189] Clause 34. The system according to Clause 33, wherein the at least one processor generates the plurality of trajectories based on at least one object identified in the scene and a determined position of the autonomous vehicle relative to the at least one object.

[0190] Clause 35. The system according to Clause 33 or 34, wherein the at least one processor generates the plurality of trajectories based on at least two detected lanes and a determined position of the autonomous vehicle relative to the at least two lanes.

[0191] Clause 36. The system according to any one of Clauses 33 to 35, wherein the at least one processor selects the trajectory based on a vehicle planning strategy.

[0192] Clause 37. At least one non-transitory storage medium storing instructions which, when executed by at least one processor, cause the at least one processor to: obtain, using the at least one processor, first scenario data associated with a scenario of an autonomous vehicle; generate, based on the first scenario data, multiple trajectories for the autonomous vehicle; select a trajectory from the multiple trajectories; determine a vehicle motion intention of the selected trajectory; combine the vehicle motion intention of the selected trajectory with a set of vehicle motion intentions to form multiple vehicle motion intentions, wherein the set of vehicle motion intentions corresponds to a set of trajectories generated from second scenario data prior to the selected trajectory; select, based on the multiple vehicle motion intentions, a vehicle motion for the autonomous vehicle; and cause the autonomous vehicle to initiate performance of the vehicle motion based on selection of the vehicle motion.

[0193] Clause 38. The at least one non-transitory storage medium according to clause 37, wherein the at least one processor generates the multiple trajectories based on at least one object identified in the scenario and a determined position of the autonomous vehicle relative to the at least one object.

[0194] Clause 39. The at least one non-transitory storage medium according to clause 37 or 38, wherein the at least one processor generates the multiple trajectories based on at least two detected lanes and a determined position of the autonomous vehicle relative to the at least two lanes.

[0195] Clause 40. The at least one non-transitory storage medium according to any one of clauses 37 to 39, wherein the at least one processor selects the trajectory based on a vehicle planning strategy.

[0196] In the foregoing description, aspects and embodiments of the present disclosure have been described with reference to numerous specific details, which may vary depending on the implementation. Accordingly, the specification and drawings are to be regarded as illustrative rather than restrictive in a limiting sense. The sole and exclusive indication of the scope of the present invention, and what the applicant desires to be the scope of the present invention, is the literal and equivalent scope of the claims as issued from this application in the specific form of the granted claims, including any subsequent amendments. Any definition of terms expressly set forth herein for inclusion in such claims shall be construed to have the meaning such terms have as used in the claims. Additionally, when the term "further comprises" is used in the foregoing specification or the appended claims, the text following such phrase may be additional steps or entities, or sub-steps / sub-entities of the previously recited steps or entities.

Claims

1. A method for operating an autonomous vehicle, the method comprising: obtaining, using at least one processor, a first plurality of consecutive lane change indications, wherein each lane change indication in the first plurality of consecutive lane change indications is generated based on corresponding scene data associated with a scene of the autonomous vehicle, wherein each lane change indication in the first plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in a first lane of the scene or should move from the first lane to a second lane of the scene; determining, using the at least one processor, to move the autonomous vehicle from the first lane to the second lane based on the first plurality of consecutive lane change indications; initiating, using the at least one processor, a waiting period based on determining to move the vehicle from the first lane to the second lane; obtaining, using the at least one processor, a second plurality of consecutive lane change indications during the waiting period, wherein each lane change indication in the second plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane or should move from the first lane to the second lane; and causing, using the at least one processor, the autonomous vehicle to move from the first lane to the second lane based on the second plurality of consecutive lane change indications.

2. The method according to claim 1, further comprising: generating a plurality of trajectories based on first scene data; selecting a first trajectory from the plurality of trajectories; and generating a lane change indication based on the first trajectory, wherein the lane change indication is one of the lane change indications in the first plurality of consecutive lane change indications, and wherein each lane change indication in the first plurality of consecutive lane change indications corresponds to a respective trajectory generated from corresponding scene data.

3. The method according to claim 1 or 2, wherein Obtaining the first plurality of consecutive lane change indications includes: obtaining the first plurality of consecutive lane change indications, wherein each consecutive lane change indication in the first plurality of consecutive lane change indications is generated at different time steps.

4. The method according to any one of claims 1 to 3, wherein Determining to move the autonomous vehicle from the first lane to the second lane includes: changing the state of the autonomous vehicle to a ready lane change state.

5. The method according to any one of claims 1 to 4, wherein Determining to move the autonomous vehicle from the first lane to the second lane includes: determining to move the autonomous vehicle from the first lane to the second lane based on a threshold amount of lane change indications in the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicating that the autonomous vehicle should move from the first lane of the scene to the second lane of the scene.

6. The method according to any one of claims 1 to 5, wherein Determining to move the autonomous vehicle from the first lane to the second lane includes: Based on determining that a majority of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicate that the autonomous vehicle should move from the first lane of the scenario to the second lane of the scenario, determine to move the autonomous vehicle from the first lane to the second lane.

7. The method according to any one of claims 1 to 6, wherein, Obtaining at least one lane change indication among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications includes: obtaining consecutive lane change indications within a predetermined time range.

8. The method according to any one of claims 1 to 7, further comprising: Generating a plurality of trajectories from first scenario data; Selecting a first trajectory from the plurality of trajectories; And Generating a lane change indication among the second plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication among the second plurality of consecutive lane change indications corresponds to a respective trajectory generated from the corresponding scenario data.

9. The method according to any one of claims 1 to 8, wherein Moving the autonomous vehicle from the first lane to the second lane includes: moving the autonomous vehicle from the first lane to the second lane based on determining that a threshold amount of lane change indications among the second plurality of consecutive lane change indications indicate that the autonomous vehicle should move from the first lane of the scenario to the second lane of the scenario.

10. The method according to any one of claims 1 to 9, wherein, Moving the autonomous vehicle from the first lane to the second lane based on the second plurality of consecutive lane change indications includes: moving the autonomous vehicle from the first lane to the second lane based on at least one lane change indication among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications.

11. A system, comprising: At least one processor; And At least one non-transitory storage medium storing instructions that, when executed by the at least one processor, cause the at least one processor to: Obtain a first plurality of consecutive lane change indications, wherein each lane change indication among the first plurality of consecutive lane change indications is generated based on corresponding scenario data associated with a scenario of the autonomous vehicle, wherein each lane change indication among the first plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane of the scenario or should move from the first lane to the second lane of the scenario; Based on the first plurality of consecutive lane change indications, determine to move the autonomous vehicle from the first lane to the second lane; Initiate a waiting period based on determining to move the vehicle from the first lane to the second lane; Obtain a second plurality of consecutive lane change indications during the waiting period, wherein each lane change indication among the second plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane or should move from the first lane to the second lane; and Based on the second plurality of consecutive lane change indications, move the autonomous vehicle from the first lane to the second lane.

12. The system according to claim 11, wherein, The at least one processor is further configured to: Generate a plurality of trajectories from first scenario data; Select a first trajectory among the plurality of trajectories; and Generate a lane change indication among the first plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication among the first plurality of consecutive lane change indications corresponds to a respective trajectory generated from respective scenario data.

13. The system according to claim 11 or 12, wherein, The at least one processor is further configured to generate a plurality of trajectories from first scenario data, wherein obtaining the first plurality of consecutive lane change indications includes: obtaining the first plurality of consecutive lane change indications, wherein each consecutive lane change indication among the first plurality of consecutive lane change indications is generated at different time steps.

14. The system according to any one of claims 11 to 13, wherein The at least one processor is further configured to cause the autonomous vehicle to move from the first lane to the second lane of the scenario based on lane change indications determined to be a threshold amount among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications that indicate the autonomous vehicle should move from the first lane to the second lane of the scenario.

15. The system according to any one of claims 11 to 14, wherein, Determining to cause the autonomous vehicle to move from the first lane to the second lane includes: determining to cause the autonomous vehicle to move from the first lane to the second lane based on a majority of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications that indicate the autonomous vehicle should move from the first lane to the second lane of the scenario.

16. At least one non-transitory storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to: Obtain a first plurality of consecutive lane change indications, Among them, wherein each lane change indication among the first plurality of consecutive lane change indications is generated based on respective scenario data associated with a scenario of an autonomous vehicle, wherein each lane change indication among the first plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in a first lane of the scenario or should move from the first lane to a second lane of the scenario; Determine to cause the autonomous vehicle to move from the first lane to the second lane based on the first plurality of consecutive lane change indications; Initiate a waiting period based on determining to cause the vehicle to move from the first lane to the second lane; Obtain a second plurality of consecutive lane change indications during the waiting period, wherein each lane change indication among the second plurality of consecutive lane change indications is for indicating whether the autonomous vehicle should remain in the first lane or should move from the first lane to the second lane; and Cause the autonomous vehicle to move from the first lane to the second lane based on the second plurality of consecutive lane change indications.

17. The at least one non-transitory storage medium according to claim 16, wherein, The at least one processor is further configured to: Generate a plurality of trajectories from first scenario data; Select a first trajectory among the plurality of trajectories; and Generate a lane change indication among the first plurality of consecutive lane change indications based on the first trajectory, wherein each lane change indication among the first plurality of consecutive lane change indications corresponds to a respective trajectory generated from respective scene data.

18. The at least one non-transitory storage medium according to claim 16 or 17, wherein the at least one processor is further configured to generate a plurality of trajectories from first scenario data, wherein, Obtaining the first plurality of consecutive lane change indications includes: obtaining the first plurality of consecutive lane change indications, wherein each consecutive lane change indication among the first plurality of consecutive lane change indications has been generated at different time steps.

19. The at least one non-transitory storage medium according to any one of claims 16 to 18, wherein, The at least one processor is further configured to move the autonomous vehicle from the first lane to the second lane of the scene based on determining that a threshold amount of lane change indications among the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicate that the autonomous vehicle should move from the first lane to the second lane of the scene.

20. The at least one non-transitory storage medium according to any one of claims 16 to 19, wherein, Determining to move the autonomous vehicle from the first lane to the second lane includes: determining to move the autonomous vehicle from the first lane to the second lane based on determining that a majority of the first plurality of consecutive lane change indications and the second plurality of consecutive lane change indications indicate that the autonomous vehicle should move from the first lane to the second lane of the scene.

21. A method for operating an autonomous vehicle, the method comprising: Using at least one processor, obtain first scene data associated with a scene of the autonomous vehicle; Using the at least one processor, generate a plurality of trajectories for the autonomous vehicle based on the first scene data; Select a trajectory from the plurality of trajectories; Using the at least one processor, determine a vehicle motion intention of the selected trajectory; Using the at least one processor, combine the vehicle motion intention of the selected trajectory with a set of vehicle motion intentions to form a plurality of vehicle motion intentions, wherein the set of vehicle motion intentions corresponds to a set of trajectories generated from second scene data prior to the selected trajectory; Using the at least one processor, select a vehicle motion for the autonomous vehicle based on the plurality of vehicle motion intentions; and Using the at least one processor, cause the autonomous vehicle to initiate performance of the vehicle motion based on selecting the vehicle motion.

22. The method according to claim 21, wherein, Generating the plurality of trajectories includes: generating the plurality of trajectories based on at least one object identified in the scene and the determined position of the autonomous vehicle relative to the at least one object.

23. The method according to claim 21 or 22, wherein Generating the plurality of trajectories includes: generating the plurality of trajectories based on at least two detected lanes and the determined position of the autonomous vehicle relative to the at least two lanes.

24. The method according to any one of claims 21 to 23, wherein, Selecting the trajectory includes: selecting the trajectory based on a vehicle planning strategy.

25. The method according to any one of claims 21 to 24, wherein Determining the vehicle motion intention includes: determining that the selected trajectory includes a lane change.

26. The method according to any one of claims 21 to 25, wherein Combining the vehicle motion intention with the set of vehicle motion intentions includes: placing the vehicle motion intention together with the set of vehicle motion intentions in a buffer.

27. The method according to any one of claims 21 to 26, wherein, Selecting a vehicle motion for the autonomous vehicle based on the plurality of vehicle motion intents includes: selecting a vehicle motion corresponding to a threshold amount of the vehicle motion intents among the vehicle motion intents.

28. The method according to any one of claims 21 to 27, wherein Selecting a vehicle motion for the autonomous vehicle based on the plurality of vehicle motion intents includes: selecting a vehicle motion corresponding to a majority of the vehicle motion intents.

29. The method according to any one of claims 21 to 28, wherein The vehicle motion is a lane change, and wherein causing the autonomous vehicle to initiate the vehicle motion includes: causing the autonomous vehicle to change lanes.

30. The method according to any one of claims 21 to 29, wherein The vehicle motion is a lane change, and wherein causing the autonomous vehicle to initiate the vehicle motion includes: causing the autonomous vehicle to remain in a first lane for a threshold time period.

31. The method according to any one of claims 21 to 30, wherein The vehicle motion is a lane change, and wherein causing the autonomous vehicle to initiate the vehicle motion includes: causing the autonomous vehicle to remain in a first lane for a threshold time period, and causing the autonomous vehicle to move from the first lane to a second lane when the threshold time period expires.

32. The method according to any one of claims 21 to 31, wherein, The vehicle motion is a lane change, wherein the plurality of vehicle motion intents are a first plurality of vehicle motion intents, and wherein causing the autonomous vehicle to initiate the vehicle motion includes: causing the autonomous vehicle to remain in a first lane for a threshold time period; generating a second plurality of vehicle motion intents during the threshold time period; and causing the autonomous vehicle to move from the first lane to a second lane when the threshold time period expires based on determining that a threshold amount of the vehicle motion intents among the second plurality of vehicle motion intents indicate a lane change.

33. A system, comprising: at least one processor; and at least one non-transitory storage medium storing instructions that, when executed by the at least one processor, cause the at least one processor to: obtain first scene data associated with a scene of an autonomous vehicle using at least one processor; generate a plurality of trajectories for the autonomous vehicle based on the first scene data; select a trajectory from the plurality of trajectories; determine a vehicle motion intent of the selected trajectory; combine the vehicle motion intent of the selected trajectory with a set of vehicle motion intents to form a plurality of vehicle motion intents, wherein the set of vehicle motion intents corresponds to a set of trajectories generated from second scene data prior to the selected trajectory; select a vehicle motion for the autonomous vehicle based on the plurality of vehicle motion intents; and cause the autonomous vehicle to initiate the vehicle motion based on selecting the vehicle motion.

34. The system according to claim 33, wherein, The at least one processor generates the plurality of trajectories based on at least one object identified in the scene and a determined position of the autonomous vehicle relative to the at least one object.

35. The system according to claim 33 or 34, wherein, The at least one processor generates the plurality of trajectories based on the at least two detected lanes and the determined position of the autonomous vehicle relative to the at least two lanes.

36. The system according to any one of claims 33 to 35, wherein The at least one processor selects the trajectory based on a vehicle planning strategy.

37. At least one non-transitory storage medium storing instructions that, when executed by at least one processor, cause the at least one processor to: Obtain first scene data associated with a scene of an autonomous vehicle using at least one processor; Generate a plurality of trajectories for the autonomous vehicle based on the first scene data; Select a trajectory from the plurality of trajectories; Determine a vehicle motion intention of the selected trajectory; Combine the vehicle motion intention of the selected trajectory with a set of vehicle motion intentions to form a plurality of vehicle motion intentions, wherein the set of vehicle motion intentions corresponds to a set of trajectories generated from second scene data prior to the selected trajectory; Select a vehicle motion for the autonomous vehicle based on the plurality of vehicle motion intentions; and Cause the autonomous vehicle to initiate performance of the vehicle motion based on selection of the vehicle motion.

38. The at least one non-transitory storage medium according to claim 37, wherein, The at least one processor generates the plurality of trajectories based on at least one object identified in the scene and the determined position of the autonomous vehicle relative to the at least one object.

39. The at least one non-transitory storage medium according to claim 37 or 38, wherein, The at least one processor generates the plurality of trajectories based on the at least two detected lanes and the determined position of the autonomous vehicle relative to the at least two lanes.

40. The at least one non-transitory storage medium according to any one of claims 37 to 39, wherein, The at least one processor selects the trajectory based on a vehicle planning strategy.

Images