Determining actions for autonomous vehicle in the presence of smart-type agents

Abstract

The invention relates to a method, a system and a computer readable medium. These aspects include determining, using at least one processor, an intentional action of the AV based on an environment in which the AV is in operation. These aspects include determining, using at least one processor, an agent prediction indicative of an agent's anticipated action by the AV based on an environment in which the AV is in operation. These aspects include determining, using at least one processor, actions used by the AV based on intent actions of the AV and agent predictions. These aspects also include providing, using at least one processor, operational data associated with proceeding of the action to cause the AV to operate based on the action used by the AV.

Description

BACKGROUND OF THE INVENTION

[0001] Human drivers signal to each other on the road and can determine whether intelligent agents such as other drivers are aware of their intentions. Similarly, networked vehicles can communicate their intentions to each other via their communication systems.

[0002] However, in the absence of a communication network used by networked vehicles, or when networked vehicles interact with non-networked vehicles or other agents in their environment, ensuring that the intentions of the vehicles are perceived by other agents can be problematic. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] Figure 1 is an example environment of a vehicle that can implement one or more components of an autonomous system;

[0004] Figure 2 is a diagram of one or more example systems of a vehicle that includes an autonomous system;

[0005] Figure 3 is Figure 1 and Figure 2 a diagram of one or more example devices and / or components of one or more example systems;

[0006] Figure 4 is a diagram of certain components of an example autonomous system;

[0007] Figure 5 is a diagram of an example implementation of a process for determining an action such as a signaling action.

[0008] Figure 6 is a diagram of an example vehicle that includes a planning system and a control system for determining an action.

[0009] Figure 7 is a diagram depicting an example determination of an action of an example vehicle.

[0010] Figure 8A 、 Figure 8B is a flowchart of an example determination of an action used by an autonomous vehicle.

[0011] Figure 9 is a flowchart of an example process for determining an action. DETAILED DESCRIPTION

[0012] 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.

[0013] In the drawings, for ease of description, specific arrangements or orderings of illustrative elements (such as those representing systems, devices, modules, instruction blocks, and / or data elements, etc.) are illustrated. However, those skilled in the art will understand that, unless explicitly described, the specific order or arrangement of 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.

[0014] Furthermore, in the drawings, connecting elements (such as solid lines, dashed lines, or arrows, etc.) are used to illustrate connections, relationships, or associations between two or more other illustrative elements, or within them. 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 than one signal path (e.g., a bus) that may be required to affect the communication.

[0015] 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.

[0016] The terms used in the specification of the various embodiments described herein are included only for the purpose of describing particular embodiments and are not intended to be limiting. As used in the specification 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 dictates 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 "comprises", "comprising", "includes", and / or "including" 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 groups thereof.

[0017] As used herein, the terms "communicate" and "communicating" refer to at least one of receiving, receipt, transmission, conveyance, and / or provision of 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 receive information from and / or send (e.g., transmit) information to the other unit directly or indirectly. This can refer to a direct or indirect connection that is inherently wired and / or wireless. Additionally, two units can communicate with each other even if the information transmitted between the first unit and the second unit is modified, processed, relayed, and / or routed. For example, even if the first unit receives information passively and does not actively transmit information to the second unit, the first unit can 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 can refer to a network packet (e.g., a data packet, etc.) that includes data.

[0018] 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, terms such as "have", "having", or "possess" 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".

[0019] "At least one" and "one or more than one" include a function being performed by one element, a function being performed by more than one element, e.g., in a distributed manner, a function being performed by one element for several functions, a function being performed by several elements for several functions, or any combination of the above.

[0020] Some embodiments of the present disclosure are described herein in connection with thresholds. As described herein, meeting (such as conforming to, etc.) a threshold may refer to a value being greater than the threshold, more than the threshold, higher than the threshold, greater than or equal to the threshold, less than the threshold, fewer than the threshold, lower than the threshold, less than or equal to the threshold, and / or equal to the threshold, etc.

[0021] 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.

[0022] General Overview

[0023] In some aspects and / or embodiments, the systems, methods, and computer program products described herein include and / or implement a method that includes: using at least one processor to obtain sensor data associated with the environment of an autonomous vehicle (AV) in operation. The environment includes at least one agent. The method includes: using at least one processor to determine an intended action of the AV based on the environment of the AV in operation. The method includes: using at least one processor to determine an agent prediction indicating an action that the agent expects the AV to take based on the environment of the AV in operation. The method includes: using at least one processor to determine an action used by the AV based on the intended action of the AV and the agent prediction. In one or more example embodiments or examples, the method includes: using at least one processor to provide operation data associated with the performance of the action to cause the AV to operate based on the action used by the AV.

[0024] By implementation of the systems, methods, and computer program products described herein, techniques are provided for determining an action used by an autonomous vehicle. Some of the advantages of these techniques are that even in the absence of a communication network used by connected vehicles, the AV can communicate an intention (such as an intended action, etc.) to other agents. The AV can determine and perform an action (which may or may not correspond to the intended action) based on its perception of the agent's confirmation of the intended action. The present disclosure allows for planning actions that affect the behavior of agents (such as actions that increase the likelihood that the agent is aware of the AV's intention, etc.). By implementation of the communication of the intended action between the AV and other agents, the AV can benefit from increased safety. The AV can be considered to interact more with the agents in its environment. Due to the AV's ability to infer the agent's confirmation of the intended action, the AV can advantageously perform maneuvers that are safer and result in more efficient driving (e.g., by allowing the AV to reach its destination in a shorter time and / or reducing the likelihood that the AV gets stuck in traffic). In other words, the AV can safely perform maneuvers that are less conservative compared to an AV not equipped with the systems, methods, and computers described herein. Additionally, since the AV can benefit from increased safety, can be considered to interact more with agents, and / or can drive more efficiently, the trust in the AV among road users can increase.

[0025] Now refer to Figure 1, an exemplary environment 100 is illustrated, in which vehicles including autonomous systems and vehicles not including autonomous systems operate. As illustrated, the 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. The 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, the objects 104a - 104n are interconnected with at least one of the 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.

[0026] The vehicles 102a - 102n (individually referred to as vehicle 102 and collectively referred to as vehicles 102) include at least one device configured to transport goods and / or people. In some embodiments, the vehicle 102 is configured to communicate with the V2I device 110, remote AV system 114, queue management system 116, and / or V2I system 118 via the network 112. In some embodiments, the vehicle 102 includes a car, a bus, a truck, and / or a train, etc. In some embodiments, the vehicle 102 is the same as or similar to the vehicle 200 described herein (see Figure 2 ). In some embodiments, the vehicles 200 in the set of vehicles 200 are associated with an autonomous queue manager. In some embodiments, as described herein, the vehicle 102 travels along the corresponding routes 106a - 106n (individually referred to as route 106 and collectively referred to 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 the autonomous system 202).

[0027] 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 (e.g., located at a fixed location and over a period of time) is stationary or (e.g., having a speed and associated with at least one trajectory) moving. In some embodiments, object 104 is associated with a corresponding location in region 108.

[0028] Routes 106a - 106n (individually referred to as route 106 and collectively as routes 106) are each associated with (e.g., specify) a sequence 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 goal 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 sequences of states (e.g., multiple sequences of spatio - temporal locations) 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 connecting roads indicating a direction change at a roadway intersection. Additionally or alternatively, route 106 can include more precise actions or states, such as, for example, 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 goal, where the combination of successive iterations of the finite - horizon state sequences cumulatively corresponds to multiple trajectories that together form a high - level route terminating at the final goal state or zone.

[0029] Region 108 includes a physical region (e.g., a geographical 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 multiple states included in a country, etc.), at least a portion of a state, at least one city, at least a portion of a city, etc. In some embodiments, region 108 includes at least one named arterial road (referred to herein as a "road"), such as a highway, an interstate highway, a parkway, an urban street, etc. 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, etc. 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.

[0030] 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, etc. 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.

[0031] 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.

[0032] 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.

[0033] 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 ride-sharing 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.).

[0034] 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.).

[0035] In some embodiments, as Figure 9 illustrated, the device 300 is configured to execute software instructions for one or more steps of the disclosed method.

[0036] 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 a different arrangement. Additionally or alternatively, at least one element of the environment 100 may be described as being performed by Figure 1One or more functions performed by at least one different element. Additionally or alternatively, at least one set of elements of environment 100 may perform one or more functions described as being performed by at least one different set of elements of environment 100.

[0037] Now refer to Figure 2 , vehicle 200 (which may be the same as or similar to Figure 1 's vehicle 102) includes autonomous system 202, powertrain control system 204, steering control system 206, and braking system 208, or is associated with autonomous system 202, powertrain control system 204, steering control system 206, and braking system 208. In some embodiments, vehicle 200 is the same as or similar to vehicle 102 (see Figure 1 ). In some embodiments, autonomous system 202 is configured to endow vehicle 200 with autonomous driving capabilities (e.g., implement at least one of the following driving functions, features, and / or devices that are automatic or based on maneuvers, the at least one driving function, feature, and / or device that enables vehicle 200 to operate partially or fully without human intervention, including but not limited to fully autonomous vehicles (e.g., vehicles that abandon reliance on human intervention, such as level 5 ADS-operated vehicles, etc.), highly autonomous vehicles (e.g., vehicles that abandon reliance on human intervention in certain situations, such as level 4 ADS-operated vehicles, etc.), and / or conditionally autonomous vehicles (e.g., vehicles that abandon reliance on human intervention in limited situations, such as level 3 ADS-operated vehicles, etc.), etc.). In one embodiment, autonomous system 202 includes the operational or tactical functionality required to operate vehicle 200 in road traffic and continuously perform part or all of the dynamic driving task (DDT). In another embodiment, autonomous system 202 includes an advanced driver assistance system (ADAS) that includes driver support features. 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.

[0038] 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 can 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.

[0039] 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 as 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 an output. In some examples, the camera 202a generates camera data including image data associated with the image. In such an 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 (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 (e.g., up to 100 meters and / or up to 1 kilometer, etc.) relative to the camera 202a. 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.

[0040] 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 formats (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.

[0041] 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 that communicates 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.

[0042] 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.

[0043] 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 the 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 the 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.

[0044] 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 the 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).

[0045] 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, 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 the Figure 1 remote AV system 114), a queue management system (e.g., a queue management system the same or similar to the Figure 1 queue management system 116), a V2I device (e.g., a V2I device the same or similar to the Figure 1 V2I device 110), and / or a V2I system (e.g., a V2I system the same or similar to the Figure 1communicates with a V2I system 118 that is the same as or similar to the V2I system).

[0046] 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.

[0047] 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.).

[0048] 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. In other words, the steering control system 206 causes the activities required to regulate the y-axis component of the vehicle movement.

[0049] 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.

[0050] The braking system 208 includes at least one device configured to actuate one or more brakes to decelerate and / or hold the vehicle 200 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 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.

[0051] 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 speed sensor, a wheel brake pressure sensor, a wheel torque sensor, an engine torque sensor, and / or a steering angle sensor. Although the braking system 208 is illustrated as being located Figure 2 proximal to the vehicle 200 in, the braking system 208 can be located anywhere in the vehicle 200.

[0052] Now refer to Figure 3, A schematic diagram of an exemplary device 300. As illustrated, 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, device 300 corresponds to: at least one device of vehicle 102 (e.g., at least one device of a system of vehicle 102); at least one device of remote AV system 114, queue management system 116, V2I system 118; and / or one or more devices of network 112 (e.g., one or more devices of a system of network 112). In some embodiments, one or more devices of vehicle 102 (e.g., one or more devices of a system of vehicle 102 (such as at least one device of remote AV system 114, queue management system 116, and V2I system 118, etc.)) and / or one or more devices of network 112 (e.g., one or more devices of a system of network 112) include at least one device 300 and / or at least one component of device 300. As Figure 3 shown, device 300 includes a bus 302, a processor 304, a memory 306, a storage component 308, an input interface 310, an output interface 312, and a communication interface 314.

[0053] 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.).

[0054] 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 a corresponding drive.

[0055] The input interface 310 includes components of the enabling device 300 that receive information via a user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, buttons, switches, a microphone, and / or a camera, etc.). Additionally or alternatively, in some embodiments, the 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.). The output interface 312 includes components for providing output information from the device 300 (e.g., a display, a speaker, and / or one or more Light Emitting Diodes (LEDs), etc.).

[0056] In some embodiments, the communication interface 314 includes transceiver-like components (e.g., a transceiver and / or separate receivers and transmitters, etc.) that enable the 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, the communication interface 314 enables the device 300 to receive information from another device and / or provide information to another device. In some examples, the 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.

[0057] In some embodiments, the device 300 performs one or more of the processes described herein. The device 300 performs these processes based on software instructions stored in a computer-readable medium such as the memory 306 and / or the storage component 308, which are executed by the processor 304. 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.

[0058] 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 the communication interface 314. When executed, the software instructions stored in the memory 306 and / or the storage component 308 cause the processor 304 to perform one or more of the processes described herein. Additionally or alternatively, hardwired circuitry is used instead of or in combination with software instructions to perform one or more of the processes described herein. Thus, unless otherwise explicitly stated, the embodiments described herein are not limited to any particular combination of hardware circuitry and software.

[0059] Memory 306 and / or storage component 308 includes a data store or at least one data structure (e.g., a database, etc.). Device 300 is capable of receiving information from the data store or at least one data structure in memory 306 or storage component 308, storing information in the data store or at least one data structure, communicating information to the data store or at least one data structure, or searching for information stored in the data store or at least one data structure. In some examples, the information includes network data, input data, output data, or any combination thereof.

[0060] In some embodiments, device 300 is configured to execute software instructions stored in memory 306 and / or the memory of another device (e.g., another device that is the same as or similar to device 300). As used herein, the term "module" refers to at least one instruction stored in memory 306 and / or the memory of another device, which, when executed by processor 304 and / or the processor of another device (e.g., another device that is the same as or similar to device 300), causes device 300 (e.g., at least one component of device 300) to perform one or more processes described herein. In some embodiments, the module is implemented in software, firmware, and / or hardware, etc.

[0061] Provided Figure 3 The number and arrangement of the illustrated components are provided as an example. In some embodiments, compared to Figure 3 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 components) may perform one or more functions described as being performed by another component or another set of components of device 300.

[0062] Now refer Figure 4, 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 the vehicle's automatic navigation system (e.g., the autonomous vehicle computing 202f of the 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 independent systems (e.g., one or more systems identical 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 independent systems located in the 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 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 identical or similar to the remote AV system 114, a queue management system identical or similar to the queue management system 116, and / or a V2I system identical or similar to the V2I system 118, etc.).

[0063] 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.

[0064] 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.

[0065] 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 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 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 connection nature of the road network, a map describing the physical properties of the roadway (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 other driving signals, etc.). In some embodiments, the map is generated in real time based on the data received by the perception system.

[0066] 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.

[0067] 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 operating functions such as lateral vehicle motion control or longitudinal vehicle motion control. Lateral vehicle motion control causes activities required to regulate the y-axis component of the vehicle motion. Longitudinal vehicle motion control causes 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.

[0068] 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.).

[0069] 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, unpaved 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.

[0070] 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.

[0071] The present disclosure relates to systems, methods, and computer program products for determining and performing actions (e.g., signaling actions, decelerating, accelerating actions, activation of flashing lights, moving forward, yielding, blocking actions, or any other suitable actions) used by an autonomous vehicle based at least on the intended actions of the autonomous vehicle and on the predicted internal state of agents based on the autonomous vehicle. In some example embodiments or examples, the determination of the actions used by the AV is further based on agent profiles that can be estimated for each tracked agent. A probability model for agent prediction can be provided to guide the prediction of agent behavior.

[0072] Now refer to Figure 5 , a diagram illustrating a system 500 for determining actions. In some embodiments, the system 500 is connected to and / or incorporated into a vehicle (e.g., an autonomous vehicle the same or similar to the vehicle 102, 200, 600 respectively of Figure 1 , Figure 2 and Figure 6 ). In one or more embodiments or examples, the system 500 is associated with an AV (e.g., such as Figure 2The illustrated autonomous system 202, Figure 3 device 300, etc.), AV system, AV computing (such as Figure 2 AV computing 202f and / or Figure 4 AV computing 400, etc.), remote AV system (such as Figure 1 remote AV system 114, etc.), queue management system (such as Figure 1 queue management system 116, etc.) and V2I system (such as Figure 1 V2I system 118, etc.) and / or be part of them. The system 500 can be used to operate a vehicle. In one or more examples, the system 500 can be used to operate an autonomous vehicle.

[0073] In one or more embodiments or examples, the system 500 communicates with one or more of the following: a device (such as Figure 3 device 300, etc.), a positioning system (such as Figure 4 positioning system 406, etc.), a planning system (such as Figure 4 planning system 404, etc.), a perception system (such as Figure 4 perception system 402, etc.) and a control system (such as Figure 4 control system 408, etc.). In one or more embodiments or examples, the system 500 includes one or more of the following: a planning system 504, a perception system 502, and a control system 511 that are the same as or similar to the planning system 404, the perception system 402, and the control system 408 of Figure 4 respectively.

[0074] The system 500 is disclosed. The system 500 includes at least one processor. The at least one processor can be included in the AV computing 540. The system 500 includes at least one memory on which instructions are stored, and when executed by the at least one processor, these instructions cause the at least one processor to perform operations, including: obtaining sensor data 502 associated with the environment in which the autonomous vehicle (AV) is operating. The environment can include agents. As used herein, an "agent" can represent an element belonging to the environment in which the AV is operating and having the ability to perceive actions from the AV. In one or more examples, an agent has dynamic behavior and / or is capable of performing dynamic behavior. An agent is, for example, one or more of the following: an actor (such as another vehicle, etc.) and a road user. In one or more embodiments or examples, the sensor data 502 is generated by at least one sensor of the autonomous vehicle operating in the environment. A perception system (such as Figure 4 perception system 402, etc.) can be configured to obtain the sensor data 502.

[0075] These operations include: using at least one processor to determine an intended action 505 of the AV based on the environment in which the AV is operating. In one or more example embodiments or examples, the intended action 505 is associated with intended action data. The intended action data may indicate a high-level intention of the AV, such as one or more of the following: a lane change, a maneuver to park in a parking space, a maneuver to pull over, a maneuver to "go next" at a stop sign, and any other suitable high-level intention of the AV. As used herein, "a high-level intention of the AV" may represent the intended action 505 of the AV, which includes a maneuver expected to be performed by the AV within its visible range within a specified time frame. In one or more examples or embodiments, the intended action 505 is any action (e.g., a dynamic action) that the AV is capable of taking within a specified time frame.

[0076] These operations include: using at least one processor to determine an agent prediction 506 indicating an action that the agent expects the AV to perform based on the environment of the AV during operation. In one or more example embodiments or examples, the agent prediction 506 is an AV estimated state indicating an estimate of the information that the agent has regarding the intended action 505 of the AV. In an example, the AV estimated state is a representation of high-level information of the agent regarding the intended action 505 of the AV, such as a probabilistic "hidden knowledge state" (HKS). The HKS may represent what the AV believes the agent knows regarding the intended action 505 of the AV. The system 500 uses, for example, the planning system 504 (similar to Figure 4 the planning system 404) for the agent prediction 506.

[0077] These operations include: using at least one processor to determine an action to be taken by the AV based on the AV's intended action 505 and agent prediction 506. In one or more example embodiments or examples, the action to be taken by the AV is an action or operation to be performed by the AV. The action or operation to be performed by the AV can be one or more of the following: a signaling action, a deceleration action, an acceleration action, an action to activate a flashing light, a forward movement action, a yielding action, an action to actively block a road, and any other suitable action. The action of the AV can be associated with action data. These operations include: using at least one processor to provide operation data associated with the performance of the action, so that the AV can operate based on the action to be taken by the AV. In other words, the system 500 determines, for example, the action that the AV is going to take (e.g., the intended action 505). Then, the system determines, for example, whether other vehicles or pedestrians (e.g., agents) (e.g., by means of agent prediction 506) understand that the AV is going to take the intended action 505. Based on this determination, the system 500 can be configured to determine the action to be taken by the AV (this action may or may not be the same as the AV's intended action 505) and take that action.

[0078] In one or more example embodiments or examples, these operations include: obtaining an agent profile 507 for the agent. As used herein, an "agent profile" can represent a profile indicating the behavior pattern of the agent. In one or more example embodiments or examples, the agent profile 507 is one or more of the following: a passive profile and an aggressive profile.

[0079] In one or more example embodiments or examples, obtaining the agent profile 507 includes: estimating the agent profile 507 based on sensor data. In other words, in one or more example embodiments or examples, at least one processor uses the sensor data 502 to evaluate the agent profile 507.

[0080] In one or more example embodiments or examples, determining the action to be taken by the AV includes: determining the action based on the AV's intended action 505, agent prediction 506, and agent profile 507. By considering the agent profile 507 in determining the action to be taken by the AV, the action to be taken by the AV can be more accurately customized for the environment in which the AV operates. For example, the AV takes a specific action based on the determined or estimated agent profile 507 to best respond to the agents present in the environment.

[0081] In one or more example embodiments or examples, these operations further include: predicting an agent trajectory 509 based on sensor data. In one or more example embodiments or examples, determining the actions used by the AV includes: determining the actions used by the AV based on the intended actions 505 of the AV, the agent prediction 506, and the predicted agent trajectory 509. By considering the predicted agent trajectory 509 in determining the actions used by the AV, the actions used by the AV can be more accurately customized for the environment in which the AV operates. For example, the AV takes a specific action based on the predicted agent trajectory 509 to best respond to agents present in the environment.

[0082] In one or more example embodiments or examples, these operations further include: after the actions used by the AV are performed by the AV, obtaining further sensor data associated with the environment. In one or more example embodiments or examples, these operations include: updating the agent prediction 506 based on the further sensor data. Thus, the agent prediction 506 can be updated based on the response of the agent to the actions performed. In an example, the actions used by the AV include using a signaling action to select a trajectory, and the updated agent prediction 506 includes an estimate based on the expected observation of the agent of the AV's trajectory and signaling action, and the AV's estimate of the agent's knowledge of the AV's subsequent intentions. For example, the AV can perform an action of signaling a change in trajectory, and the agent is determined to decelerate in response to such signaling. Then, as further sensor data captures the agent's response, the system 500 can update the agent prediction 506.

[0083] In one or more example embodiments or examples, these operations further include: updating the predicted agent trajectory 509 based on the update of the agent prediction 506. Thus, subsequent determination of the actions used by the AV can be based on the updated agent prediction 506 and the updated predicted agent trajectory 509.

[0084] In one or more example embodiments or examples, the operations further include predicting a change in the agent prediction 506 based on one or more of the following: the agent prediction 506, the action used by the AV, the agent profile 507, and the predicted agent trajectory 509. The change in the agent prediction 506 may be represented by quantifying the amount of change in the agent prediction 506, such as a percentage change, etc. In one or more example embodiments or examples, the operations include determining a utility score 510 associated with the predicted change in the agent prediction 506 based on one or more of the following: the agent prediction 506, the action used by the AV, the agent profile 507, and the predicted agent trajectory 509. In other words, one or more of the following inputs may be provided to the at least one processor: the current agent prediction 506, the action used by the AV (such as a signaling action, etc.), the agent profile 507, and the predicted agent trajectory 509. The at least one processor may output a predicted change in the agent prediction 506 and a utility score 510 associated with such a change. The utility score 510 may indicate how useful a change in the agent prediction 506 is relative to the criteria selected for optimization.

[0085] In one or more exemplary embodiments or examples, predicting changes in the agent prediction 506 includes determining a transition function between a current state and a next state. In one or more exemplary embodiments or examples, the current state represents one or more of the following: the agent prediction 506, the action used by the AV, the agent profile 507, and the predicted agent trajectory 509. The transition function is determined, for example, using one or more of the following: machine learning and neural networks. In one or more exemplary embodiments or examples, the operations include providing a game tree representing the interaction between the AV and the agent, and deducing the game tree. For example, a game tree can be relied upon as a way to generate probabilities of possible outcomes in a specific (e.g., turn-based) interaction model between the AV and one or more agents. In other words, the game tree can be used to determine or estimate the impact that the action used by the AV will have on the agent prediction 506 and on the potential reactions of other agents. Therefore, a tree of possible outcomes for such an action used by the AV (optionally followed by a subtree of possible actions that other agents may take) can be deduced. The tree (and its subtrees) can reach arbitrary depth, and from the tree (and its subtrees), the probabilities of various outcomes starting from the actions taken by the AV can be estimated (e.g., the probability of the agent yielding to the AV's lane-changing maneuver). In other words, in some examples, the game tree is a tool for estimating the probabilities of outcomes resulting from the actions taken by the AV. Such probabilities can be used to update a model of predictions for one or more agents.

[0086] In one or more example embodiments or examples, these operations further include: determining an AV trajectory 508 based on a utility score 510. Since the utility score 510 represents the utility of changes in the agent prediction 506 (e.g., the utility of the actions used by the agent prediction 506 to determine the AV), the utility score 510 can be used to determine the AV trajectory 508 corresponding to the actions used by the AV (which are based on agent predictions 506 having a utility score 510 higher than the utility threshold). In this way, the utility score 510 can be incorporated into the cost structure of the trajectory planner to allow actions used by the AV with a high utility score 510. In other words, the utility score 510 can be regarded as a quantitative measure of desired behavior (such as the behavior of an agent that is beneficial to the AV, etc.). The isolation of the modeled interactions can allow the search space to be discretized into a classical tree structure.

[0087] In one or more example embodiments or examples, the environment includes multiple agents. In one or more example embodiments or examples, these operations further include: filtering agents among the multiple agents based on criteria. In one or more example embodiments or examples, these operations include: filtering a subset of agents among the multiple agents based on criteria. In one or more example embodiments or examples, the criteria are based on one or more of the following: the position of the agent relative to the AV, the agent that constrains the actions used by the AV, the difference between the intended action 505 of the AV and the agent prediction 506, and any other suitable criteria. The criteria can allow filtering of one or more agents that are most relevant to the AV, the situation of the AV, and the intended action 505 of the AV. In other words, for example, when expanding the tree that models the interaction between the AV and multiple agents, if a particular agent is considered not worthy of attention according to heuristic or learned criteria, these particular agents can be filtered out.

[0088] In one or more example embodiments or examples, determining the intended action 505 of the AV and the agent prediction 506 includes: obtaining an AV internal state that includes the intended action 505 of the AV and the agent prediction 506. The AV internal state can be regarded as the state of the AV that can be used to determine the actions used by the AV. In one or more example embodiments or examples, the AV internal state further includes an agent profile 507 in addition to the intended action 505 of the AV and the agent prediction 506.

[0089] In one or more example embodiments or examples, the actions used by the AV include one or more of the following: signaling actions, speed actions, and maneuvering actions. The signaling actions can be one or more of the following: activation of a flashing signal light, activation of a turn signal light, activation of a strobe light, and any other suitable signaling action. The speed actions can be one or more of the following: deceleration action, acceleration action, and any other suitable speed action. The maneuvering actions can be one or more of the following: forward movement, movement toward the edge of a lane, yielding action, blocking action, and any other suitable maneuvering action.

[0090] Now refer to Figure 6 , in one or more embodiments or examples, operation data 606 (such as the operation data mentioned regarding Figure 5 ) is transmitted from the planning system 604a to the control system 604b in the AV 600. The planning system 604a and the control system 604b can be the same as or similar to the planning system 504 and the control system 508 of Figure 5 respectively. The planning system 604a can include at least one processor, such as at least one processor of the embodiment or example of Figure 5 etc. As indicated for the embodiment or example of Figure 5 , at least one processor is used (that is, relying on the sensor data 614 obtained by using at least one processor) to provide operation data 616. The operation data 616 is, for example, intended to operate the AV based on the actions used by the AV. In certain examples, Figure 6 the control system 604b of

[0091] is intended to control such operations according to the operation data.

[0092] Control data can be generated for the control system of an autonomous vehicle. The control data can be provided to the control system of an autonomous vehicle. The control data can be transmitted to, for example, the control system of an autonomous vehicle and / or an external system. The control system (of the autonomous vehicle and / or the external system) can be controlled based on the control data.

[0093] The sensor(s) can be one or more sensors, such as a first on-board sensor, etc. The sensor(s) can be associated with an autonomous vehicle. The autonomous vehicle can include one or more sensors that can be configured to monitor the environment of the autonomous vehicle's operation via sensor data 614. For example, the monitoring can provide sensor data 614 that indicates what is happening in the environment around the autonomous vehicle, such as for determining the trajectory of the autonomous vehicle, etc. The sensor(s) can include Figure 2 one or more of the sensors illustrated in (such as camera 202a, LiDAR sensor 202b, Radar sensor 202c, and microphone 202d, etc.).

[0094] Now referring to Figure 7 , the first vehicle 702 is an AV configured to perform one or more of the methods disclosed herein, such as via a system 500 including Figure 5 . The first vehicle 702 determines an intended action, i.e., to change lanes from the left lane of a two-lane road to the right lane. Using at least one processor, the intended action is determined based on the environment in which the AV is operating (such as based on high-density traffic in the left lane or the need to change to the right lane to subsequently turn right at an intersection, etc.).

[0095] The first vehicle 702 uses at least one processor to determine an agent prediction for a second vehicle 702A (which is an agent) based on the environment in which the first vehicle 702 is operating. The agent prediction indicates the first vehicle 702's estimate of the action (such as a maneuvering action, etc.) that the first vehicle 702 expects the second vehicle 702A to perform. In other words, the prediction of the first vehicle 702 for the second vehicle 702A indicates what the first vehicle 702 predicts regarding the second vehicle 702A's knowledge of the first vehicle 702's intention to perform a maneuvering action. In Figure 7 , the prediction of the first vehicle 702 for the second vehicle 702A is that the second vehicle 702A is unlikely to know the first vehicle 702's intention to change to the right lane. As a result, as Figure 7 shown (upper left corner), the intention of the first vehicle 702 conflicts with the intention of the second vehicle 702A.

[0096] To change the second vehicle 702A's understanding of the intention to perform a maneuver with respect to the first vehicle 702 (and thus change the prediction for the second vehicle 702A), the first vehicle determines an action consisting of micro-moving to the edge of the left lane and activating the right turn signal. The first vehicle 702 operates based on such an action (i.e., the first vehicle 702 performs the action), for example, via a control system provided with operation data associated with the performance of the action. This is shown in Figure 7 (bottom). Accordingly, at least one processor of the first vehicle 702 updates the prediction for the second vehicle 702A. At the moment shown in Figure 7 (bottom), the prediction of the first vehicle 702 for the second vehicle 702A is that the second vehicle is likely to understand the intention of the first vehicle 702 to change to the right lane.

[0097] At Figure 7 (top right), the second vehicle 702A is decelerating to yield. This action is sensed by the first vehicle 702 (e.g., using at least one processor that can process sensor data associated with the environment in which the first vehicle 702 is operating). As a result, at least one processor of the first vehicle 702 updates the prediction for the second vehicle 702A. At the moment shown in Figure 7 (top right), the prediction of the first vehicle 702 for the second vehicle 702A is that the second vehicle most likely does understand the intention of the first vehicle 702 to change to the right lane. Then, the first vehicle 702 can determine an action to change to the right lane based on the intended action of the first vehicle 702 and the updated prediction for the second vehicle 702A. This action can also be performed by the first vehicle 702 using the control system.

[0098] Now referring to Figure 8A and Figure 8B , a flowchart of an example determination of an action used by an AV is provided.

[0099] In the example of Figure 8A , at step 801, at least one processor of the AV determines an intended action such as a maneuver. At such a moment, as elaborated with reference to Figure 7 , the agent prediction is that the agent is unlikely to understand the intention of the AV to perform a maneuver.

[0100] As a result of such determination from the agent prediction, at least one processor of the AV determines an action, such as activation of a turn signal, based on the intended action of the AV and the agent prediction. When the AV operates based on such an action at step 802 (e.g., when the turn signal is activated), at least one processor of the AV updates the agent prediction. At such a moment, the agent prediction is that the agent is more likely to understand the intention of the AV to make a maneuver.

[0101] If the agent yields, at least one processor of the AV updates the agent prediction. At such a moment, the agent prediction is that the agent is highly likely to understand the intention of the AV to make a maneuver. Then, the AV can determine an action to make a maneuver based on the intended action of the AV and the updated agent prediction. At step 803, this action can also be performed by the AV using the control system.

[0102] If the agent does not yield, at least one processor of the AV updates the agent prediction. At such a moment, the agent prediction is that the agent is less likely to understand the intention of the AV to make a maneuver, that is, at step 804, the AV estimates that the agent may or may not understand the intention of the AV. As a result of such an update of the agent prediction, at least one processor of the AV determines a further action (such as slightly shifting towards the edge of the lane along which it is circulating) based on the intended action of the AV and the updated agent prediction. At step 805, this further action can also be performed by the AV using the control system. When the AV operates based on such an action (e.g., when the AV slightly shifts towards the edge of the lane along which it is circulating), at least one processor of the AV updates the agent prediction. At such a moment, the agent prediction is that the agent is even more likely to understand the intention of the AV to make a maneuver.

[0103] When the agent yields, at least one processor of the AV updates the agent prediction again. At such a moment, the agent prediction is that the agent almost certainly understands the intention of the AV to make a maneuver. Then, the AV can determine an action to make a maneuver based on the intended action of the AV and the updated agent prediction. At step 806, this action can also be performed by the AV using the control system.

[0104] When the agent does not yield, at least one processor determines an action to stay in the current lane, that is, no intended action is taken at step 807.

[0105] Now refer to Figure 8B, Note that the intended actions of the AV based on the environment in which the AV operates can be based on the identified agent intention 810. At least one processor of the AV can obtain sensor data indicating the identified agent intention. The identified agent intention is, for example, the intention to merge in. Considering the identified agent intention, the intended actions of the AV based on the identified agent intention can be divided into yielding actions 811 and attempting to resist actions 812. As used herein, "yielding actions" can be regarded as actions in which the AV adapts to the identified agent intention to allow for merging in. As used herein, "attempting to resist actions" can be regarded as actions in which the AV forces the agent to modify the identified agent intention to avoid merging in.

[0106] The yielding actions 811 can further be divided into yielding passively (813) (that is, without a change in behavior) or actively (814) (that is, with a change in behavior, such as an intended action in which the AV makes space for the agent, etc.) to the identified agent intention. Similarly, the attempting to resist actions can further be divided into resisting passively (815) (i.e., without a change in behavior) or actively (816) (i.e., with a change in behavior, such as an intended action in which the AV reduces the available space of the agent, etc.) to the identified agent intention.

[0107] At least one processor processes the intended actions of the AV together with the agent prediction (as set forth in exemplary embodiments or examples provided herein, which can be determined by at least one processor) to determine the actions used by the AV. Especially when the agent prediction indicates the fact that the agent is highly likely to understand the intended actions of the AV, the actions used by the AV can correspond to the intended actions of the AV indicated in Figure 8A .

[0108] Now refer to Figure 9 , a flowchart of a method or process 900 for determining the actions used by the AV (such as for operating and / or controlling the AV, etc.). The method 900 can be performed by any suitable system. The method 900 can be performed by any system disclosed herein, such as one or more of the following: Figure 2 AV computing 202f of Figure 4 AV computing 400 of Figure 1 vehicle 102 of Figure 2 vehicle 200 of Figure 3 device 300 of Figure 5 AV computing 540 of Figure 6 , Figure 7 , Figure 8A and Figure 8BImplementation. The disclosed system may include at least one processor that may be configured to perform one or more of the operations of method 900. Method 900 may be performed by another device or group of devices (e.g., fully and / or partially, etc.) separate from or including the system disclosed herein.

[0109] In one or more example embodiments or examples, method 900 includes: at step 902, using at least one processor to obtain sensor data associated with the environment in which an autonomous vehicle (AV) is operating. In one or more example embodiments or examples, the environment includes agents. In one or more example embodiments or examples, method 900 includes: at step 904, using at least one processor to determine an intended action of the AV based on the environment in which the AV is operating. In one or more example embodiments or examples, method 900 includes: at step 906, using at least one processor to determine an agent prediction indicating an action that an agent expects the AV to take based on the environment in which the AV is operating. In one or more example embodiments or examples, method 900 includes: at step 908, using at least one processor to determine an action to be taken by the AV based on the intended action of the AV and the agent prediction. In one or more example embodiments or examples, method 900 includes: at step 910, using at least one processor to provide operation data associated with the performance of the action to cause the AV to operate based on the action taken by the AV.

[0110] In one or more examples, an agent has dynamic behavior and / or is capable of having dynamic behavior. An agent is, for example, one or more of the following: an actor (such as another vehicle, etc.) and a road user. In one or more embodiments or examples, the sensor data is generated by at least one sensor of an autonomous vehicle operating in the environment. A perception system (such as Figure 4The perception system 402, etc.) can be configured to obtain sensor data. In one or more example embodiments or examples, the intended action is associated with intended action data. The intended action data can indicate one or more of the following actions: the high-level intention of the AV, lane change, the maneuver of parking in a space, the maneuver of pulling over, the maneuver of "next forward" at a stop sign, and any other suitable actions. In one or more examples or embodiments, the intended action is any action (e.g., a dynamic action) that the AV can take within a specified time frame. In one or more example embodiments or examples, the agent prediction is the AV estimated state that indicates the AV's estimate of the information that the agent has about the AV's intended action. In an example, the AV estimated state is a representation of the high-level information of the agent about the AV's intended action, such as a probabilistic "hidden knowledge state" (HKS), etc. The HKS can represent what the AV believes the agent knows about the AV's intended action. The action used by the AV is the action or operation to be performed by the AV. The action or operation to be performed by the AV can be one or more of the following: signaling action, deceleration action, acceleration action, action of activating a flashing light, forward movement action, yielding action, actively blocking the road action, and any other suitable actions. The action of the AV can be associated with action data.

[0111] In one or more example embodiments or examples, method 900 includes: using at least one processor to obtain an agent profile. In one or more example embodiments or examples, the agent profile is one or more of the following: a passive profile and an aggressive profile.

[0112] In one or more example embodiments or examples, using at least one processor to obtain an agent profile includes: estimating the agent profile based on sensor data. In other words, in one or more example embodiments or examples, at least one processor utilizes the sensor data to evaluate the agent profile.

[0113] In one or more example embodiments or examples, using at least one processor to determine the action used by the AV at step 908 includes: determining the action used by the AV based on the AV's intended action, the agent prediction, and the agent profile. By considering the agent profile to determine the action used by the AV, the action used by the AV can be more accurately customized for the environment in which the AV operates. For example, the AV takes a specific action based on the determined or estimated agent profile to best respond to the agents present in the environment.

[0114] In one or more example embodiments or examples, method 900 includes: using at least one processor to predict an agent's trajectory based on sensor data. In one or more example embodiments or examples, at step 908, using at least one processor to determine the actions used by the AV includes: determining the actions used by the AV based on the intended actions of the AV, the agent prediction, and the predicted agent trajectory. By considering the predicted agent trajectory in determining the actions used by the AV, the actions used by the AV can be more accurately customized for the environment in which the AV operates. For example, the AV takes a specific action based on the predicted agent trajectory to best respond to agents present in the environment.

[0115] In one or more example embodiments and examples, method 900 includes: using at least one processor to obtain further sensor data associated with the environment after an action is taken by the AV. In one or more embodiments and examples, method 900 includes: using at least one processor to update the agent prediction based on the further sensor data. Thus, the agent prediction can be updated based on the agent's reaction to the actions taken. In an example, the actions used by the AV include: using a signaling action to select a trajectory, and based on the agent's expected observation of the AV's trajectory and signaling action, the updated agent prediction includes an estimate of the AV's understanding of the agent's subsequent intent regarding the AV. For example, the AV can take an action of signaling a change in trajectory, and the agent is determined to decelerate in response to such signaling. As further sensor data captures the agent's response, the agent prediction is updated.

[0116] In one or more example embodiments or examples, method 900 includes: using at least one processor to update the predicted agent trajectory based on the update of the agent prediction. Thus, subsequent determination of the actions used by the AV can be based on the updated agent prediction and the updated predicted agent trajectory.

[0117] In one or more example embodiments or examples, method 900 includes: using at least one processor to predict a change in an agent prediction based on one or more of the following: the agent prediction, actions used by the AV, the agent profile, and the predicted agent trajectory. In one or more example embodiments or examples, method 900 includes: using at least one processor to determine a utility score associated with the predicted change in the agent prediction based on one or more of the following: the agent prediction, actions used by the AV, the agent profile, and the predicted agent trajectory. In other words, one or more of the following inputs can be provided to the at least one processor: the current agent prediction, actions used by the AV (such as signaling actions, etc.), the agent profile, and the predicted agent trajectory. The at least one processor can output the predicted change in the agent prediction and the utility score associated with such a change. The utility score can indicate how useful the change in the agent prediction is relative to the criterion selected for optimization.

[0118] In one or more example embodiments or examples, predicting a change in the agent prediction includes: determining a transition function between a current state and a next state. In one or more example embodiments or examples, the current state represents one or more of the following: the agent prediction, actions used by the AV, and the agent profile. The transition function is determined, for example, using one or more of the following: machine learning and neural networks. In one or more example embodiments or examples, the operations include: providing a game tree representing the interaction between the AV and the agent, and reasoning about the game tree.

[0119] In one or more example embodiments or examples, method 900 includes: using at least one processor to determine an AV trajectory based on the utility score. Since the utility score represents the utility of the change in the agent prediction (e.g., the utility of the agent prediction for determining the actions used by the AV), the utility score can be used to determine the AV trajectory corresponding to the actions used by the AV (which are based on agent predictions having a utility score higher than a utility threshold). Thus, the utility score can be incorporated into the cost structure of the trajectory planner to allow actions used by the AV with high utility scores. In other words, the utility score can be regarded as a quantitative measure of desired behavior (such as the behavior of an agent that is beneficial to the AV, etc.). The isolation of the modeled interaction can allow the search space to be discretized into a classical tree structure.

[0120] In one or more example embodiments or examples, the environment includes a plurality of agents. In one or more example embodiments or examples, method 900 includes: using at least one processor to filter agents among the plurality of agents based on criteria. In one or more example embodiments or examples, the operation includes: filtering a subset of agents among the plurality of agents based on criteria. In one or more example embodiments or examples, the criteria are based on one or more of the following: the position of the agent relative to the AV, the difference between the agent-constrained intended AV trajectory, the intended action, and the agent prediction, and any other suitable criteria. The criteria may allow filtering of one or more agents that are most relevant to the AV, the situation of the AV, and the intended action of the AV. In other words, for example, when expanding a tree that models the interaction between the AV and the plurality of agents, if a particular agent is considered not worthy of attention according to heuristic or learned criteria, these particular agents can be filtered out.

[0121] In one or more example embodiments or examples, using at least one processor to determine the intended action and the agent prediction at steps 904 and 906 includes: obtaining an AV internal state that includes the intended action and the agent prediction. The AV internal state can be regarded as the state of the AV that can be used to determine the action used by the AV. In one or more example embodiments or examples, the AV internal state includes an agent profile in addition to the intended action of the AV and the agent prediction.

[0122] In one or more example embodiments or examples, the actions used by the AV include one or more of the following: signaling actions, speed actions, and maneuvering actions. The signaling action can be one or more of the following: activation of a flashing signal light, activation of a turn signal light, activation of a strobe light, and any other suitable signaling action. The speed action can be one or more of the following: deceleration action, acceleration action, and any other suitable speed action. The maneuvering action can be one or more of the following: moving forward, moving towards the edge of the lane, yielding action, blocking action, and any other suitable maneuvering action.

[0123] 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 invention, and what the applicant desires to be the scope of the invention, is the literal and equivalent scope of the claims issued from this application in the specific form of the issued 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 comprising" 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.

[0124] A non-transitory computer-readable medium is disclosed, including instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform one or more operations in accordance with a method disclosed herein.

[0125] Methods, non-transitory computer-readable media, and systems according to any of the following are also disclosed.

[0126] Item 1. A method, comprising:

[0127] Using at least one processor, obtaining sensor data associated with an environment in which an autonomous vehicle, i.e., an AV, is operating, wherein the environment includes agents;

[0128] Using the at least one processor, determining an intended action of the AV based on the environment in which the AV is operating;

[0129] Using the at least one processor, determining an agent prediction indicating an action that the agent expects the AV to perform based on the environment in which the AV is operating;

[0130] Using the at least one processor, determining an action used by the AV based on the intended action of the AV and the agent prediction; and

[0131] Using the at least one processor, providing operation data associated with the performance of the action to cause the AV to operate based on the action used by the AV.

[0132] Item 2. The method according to item 1, the method further comprising:

[0133] Using the at least one processor, obtaining an agent profile.

[0134] Item 3. The method according to item 2, wherein obtaining the agent profile using the at least one processor comprises:

[0135] Estimate the agent profile based on the sensor data.

[0136] Item 4. The method according to item 2 or 3, wherein determining the action used by the AV using the at least one processor includes:

[0137] Determine the action based on the intended action of the AV, the agent prediction, and the agent profile.

[0138] Item 5. The method according to any one of the preceding items, the method further comprising:

[0139] Using the at least one processor, predict an agent trajectory based on the sensor data,

[0140] wherein determining the action used by the AV using the at least one processor includes: determining the action based on the intended action of the AV, the agent prediction, and the predicted agent trajectory.

[0141] Item 6. The method according to any one of the preceding items, the method further comprising:

[0142] Using the at least one processor, after performing the action used by the AV by the AV, obtain further sensor data associated with the environment; and

[0143] Using the at least one processor, update the agent prediction based on the further sensor data.

[0144] Item 7. The method according to items 5 and 6, the method comprising:

[0145] Using the at least one processor, update the predicted agent trajectory based on the updated agent prediction.

[0146] Item 8. The method according to any one of items 5 to 7, the method comprising:

[0147] Using the at least one processor, predict a change in the agent prediction based on one or more of the following: the agent prediction, the action used by the AV, the agent profile, and the predicted agent trajectory; and

[0148] Using the at least one processor, determine a utility score associated with the predicted change in the agent prediction based on one or more of the following: the agent prediction, the action used by the AV, the agent profile, and the predicted agent trajectory.

[0149] Item 9. The method according to item 8, wherein predicting the change predicted by the agent includes:

[0150] Determine a transfer function between the current state and the next state, where the current state represents one or more of the following items: the agent prediction, the actions used by the AV, and the agent profile.

[0151] Item 10. The method according to item 9, the method further includes:

[0152] Using the at least one processor, determine an AV trajectory based on the utility score.

[0153] Item 11. The method according to any one of the preceding items, wherein the environment includes a plurality of agents, and the method further includes:

[0154] Using the at least one processor, filter out agents among the plurality of agents based on criteria, where the criteria are based on one or more of the following items: the position of the agent relative to the AV, the agent that constrains the intended AV trajectory, and the difference between the intended action and the agent prediction.

[0155] Item 12. The method according to any one of the preceding items, wherein using the at least one processor to determine the intended action and the agent prediction includes:

[0156] Obtain an AV internal state including the intended action and the agent prediction.

[0157] Item 13. The method according to any one of the preceding items, wherein the actions used by the AV include one or more of the following items: signaling actions, speed actions, and maneuvering actions.

[0158] Item 14. A non-transitory computer-readable medium, including instructions stored thereon, which when executed by at least one processor, cause the at least one processor to perform operations, and the operations include:

[0159] Obtain sensor data associated with the environment in which an autonomous vehicle, i.e., an AV, operates, where the environment includes agents;

[0160] Determine the intended action of the AV based on the environment in which the AV operates;

[0161] Determine an agent prediction indicating the actions that the agent expects the AV to perform based on the environment in which the AV operates;

[0162] Determine the actions used by the AV based on the intended action of the AV and the agent prediction; and

[0163] Provide operation data associated with the performance of the action, so that the AV operates based on the action used by the AV.

[0164] Item 15. The non-transitory computer-readable medium according to item 14, wherein the operation further includes:

[0165] Obtain an agent profile.

[0166] Item 16. The non-transitory computer-readable medium according to item 15, wherein obtaining the agent profile includes:

[0167] Estimate the agent profile based on the sensor data.

[0168] Item 17. The non-transitory computer-readable medium according to item 15 or 16, wherein determining the action used by the AV includes:

[0169] Determine the action used by the AV based on the intended action of the AV, the agent prediction, and the agent profile.

[0170] Item 18. The non-transitory computer-readable medium according to any one of items 14 to 17, wherein the operation further includes:

[0171] Predict an agent trajectory based on the sensor data,

[0172] wherein determining the action used by the AV includes: determining the action based on the intended action of the AV, the agent prediction, and the predicted agent trajectory.

[0173] Item 19. The non-transitory computer-readable medium according to any one of items 14 to 18, wherein the operation further includes:

[0174] After the action is performed by the AV, obtain further sensor data associated with the environment; and

[0175] Update the agent prediction based on the further sensor data.

[0176] Item 20. The non-transitory computer-readable medium according to item 18 or 19, wherein the operation includes:

[0177] Update the predicted agent trajectory based on the update of the agent prediction.

[0178] Item 21. The non-transitory computer-readable medium according to any one of items 18 to 20, wherein the operation includes:

[0179] Predicting a change in the agent prediction based on one or more of the following: the agent prediction, the actions used by the AV, the agent profile, and the predicted agent trajectory; and

[0180] Determining a utility score associated with the predicted change in the agent prediction based on one or more of the following: the agent prediction, the actions used by the AV, the agent profile, and the predicted agent trajectory.

[0181] Item 22. The non-transitory computer-readable medium according to item 21, wherein predicting the change in the agent prediction includes:

[0182] Determining a transfer function between a current state and a next state, where the current state represents one or more of the following: the agent prediction, the actions used by the AV, and the agent profile.

[0183] Item 23. The non-transitory computer-readable medium according to item 22, the non-transitory computer-readable medium further comprising:

[0184] Determining an AV trajectory based on the utility score.

[0185] Item 24. The non-transitory computer-readable medium according to any one of items 14 to 23, wherein the environment includes multiple agents, and the operations further include:

[0186] Filtering agents among the multiple agents based on criteria, where the criteria are based on one or more of the following: the position of the agent relative to the AV, the agent's constraint on the intended AV trajectory, and the difference between the intended action and the agent prediction.

[0187] Item 25. The non-transitory computer-readable medium according to any one of items 14 to 24, wherein determining the intended action and the agent prediction includes:

[0188] Obtaining an AV internal state including the intended action and the agent prediction.

[0189] Item 26. The non-transitory computer-readable medium according to any one of items 14 to 25, wherein the actions include one or more of the following: signaling actions, speed actions, and maneuvering actions.

[0190] Item 27. A system, comprising at least one processor and at least one memory, instructions being stored on the at least one memory, and when the instructions are executed by the at least one processor, causing the at least one processor to perform operations, the operations including:

[0191] Obtain sensor data associated with the environment in which an autonomous vehicle, i.e., an AV, operates, where the environment includes agents;

[0192] Determine an intended action of the AV based on the environment in which the AV operates;

[0193] Determine an agent prediction indicating an action that the agent expects the AV to perform based on the environment in which the AV operates;

[0194] Determine an action used by the AV based on the intended action of the AV and the agent prediction; and

[0195] Provide operation data associated with the performance of the action to cause the AV to operate based on the action used by the AV.

[0196] Item 28. The system according to item 27, wherein the operation includes:

[0197] Obtain an agent profile.

[0198] Item 29. The system according to item 28, wherein obtaining the agent profile includes:

[0199] Estimate the agent profile based on the sensor data.

[0200] Item 30. The system according to item 28 or 29, wherein determining the action used by the AV includes:

[0201] Determine the action used by the AV based on the intended action of the AV, the agent prediction, and the agent profile.

[0202] Item 31. The system according to any one of items 27 to 30, wherein the operation further includes:

[0203] Predict an agent trajectory based on the sensor data;

[0204] wherein determining the action used by the AV includes: determining the action used by the AV based on the intended action of the AV, the agent prediction, and the predicted agent trajectory.

[0205] Item 32. The system according to any one of items 27 to 31, wherein the operation further includes:

[0206] After the action is performed by the AV, obtain further sensor data associated with the environment; and

[0207] Update the agent prediction based on the further sensor data.

[0208] Item 33. The system according to item 31 or 32, the operation further includes:

[0209] Updating the predicted agent trajectory based on the update of the agent prediction.

[0210] Item 34. The system according to any one of items 31 to 33, the operation further includes:

[0211] Predicting a change in the agent prediction based on one or more of the following: the agent prediction, the actions used by the AV, the agent profile, and the predicted agent trajectory; and

[0212] Determining a utility score associated with the predicted change in the agent prediction based on one or more of the following: the agent prediction, the actions used by the AV, the agent profile, and the predicted agent trajectory.

[0213] Item 35. The system according to item 34, wherein predicting the change in the agent prediction includes:

[0214] Determining a transfer function between the current state and the next state, where the current state represents one or more of the following: the agent prediction, the actions used by the AV, and the agent profile.

[0215] Item 36. The system according to item 35, the operation further includes:

[0216] Determining the AV trajectory based on the utility score.

[0217] Item 37. The system according to any one of items 27 to 36, wherein the environment includes multiple agents, the operation further includes:

[0218] Filtering agents among the multiple agents based on criteria, where the criteria are based on one or more of the following: the position of the agent relative to the AV, the agent's constraint on the intended AV trajectory, and the difference between the intended action and the agent prediction.

[0219] Item 38. The system according to any one of items 27 to 37, wherein determining the intended action and the agent prediction includes:

[0220] Obtaining an AV internal state including the intended action and the agent prediction.

[0221] Item 39. The system according to any one of items 27 to 38, wherein the action includes one or more of the following: signaling action, speed action, and maneuvering action.

Claims

1. A method, comprising: using at least one processor to obtain sensor data associated with the environment in which an autonomous vehicle, i.e., an AV, is operating, wherein the environment includes agents; using the at least one processor to determine an intended action of the AV based on the environment in which the AV is operating; using the at least one processor to determine an agent prediction indicating an action that the agent expects the AV to take based on the environment in which the AV is operating; using the at least one processor to determine an action to be taken by the AV based on the intended action of the AV and the agent prediction; and using the at least one processor to provide operation data associated with the performance of the action to enable the AV to operate based on the action to be taken by the AV.

2. The method according to claim 1, the method further comprising: using the at least one processor to obtain an agent profile.

3. The method according to claim 2, wherein using the at least one processor to obtain the agent profile includes: estimating the agent profile based on the sensor data.

4. The method according to any one of claims 2 to 3, wherein using the at least one processor to determine the action to be taken by the AV includes: determining the action based on the intended action of the AV, the agent prediction, and the agent profile.

5. The method according to any one of the preceding claims, the method further comprising: using the at least one processor to predict an agent trajectory based on the sensor data, wherein using the at least one processor to determine the action to be taken by the AV includes: determining the action based on the intended action of the AV, the agent prediction, and the predicted agent trajectory.

6. The method according to any one of the preceding claims, the method further comprising: using the at least one processor to obtain further sensor data associated with the environment after the AV performs the action to be taken by the AV; and using the at least one processor to update the agent prediction based on the further sensor data.

7. The method according to claim 5 or 6, the method comprising: using the at least one processor to update the predicted agent trajectory based on the updated agent prediction.

8. The method according to any one of claims 5 to 7, the method comprising: using the at least one processor to predict a change in the agent prediction based on one or more of: the agent prediction, the action to be taken by the AV, the agent profile, and the predicted agent trajectory; and using the at least one processor to determine a utility score associated with the predicted change in the agent prediction based on one or more of: the agent prediction, the action to be taken by the AV, the agent profile, and the predicted agent trajectory.

9. The method according to claim 8, wherein predicting the change in the agent prediction includes: Determine a transition function between a current state and a next state, where the current state represents one or more of the following: the agent prediction, the actions used by the AV, and the agent profile.

10. The method according to claim 9, the method further comprises: Using the at least one processor, determine an AV trajectory based on the utility score.

11. The method according to any one of the preceding claims, wherein, the environment includes a plurality of agents, and the method further comprises: Using the at least one processor, filter agents among the plurality of agents based on criteria, where the criteria are based on one or more of the following: the agent position relative to the AV, the agent that constrains the intended AV trajectory, and the difference between the intended action and the agent prediction.

12. The method according to any one of the preceding claims, wherein, Using the at least one processor to determine the intended action and the agent prediction includes: Obtain an AV internal state including the intended action and the agent prediction.

13. The method according to any one of the preceding claims, wherein, The actions used by the AV include one or more of the following: signaling actions, speed actions, and maneuvering actions.

14. A system comprising at least one processor and at least one memory, instructions are stored on the at least one memory, and when the instructions are executed by the at least one processor, the at least one processor is caused to perform operations, the operations comprise: Obtain sensor data associated with the environment in which an autonomous vehicle, i.e., an AV, operates, where the environment includes agents; Determine the intended action of the AV based on the environment in which the AV operates; Determine an agent prediction indicating the actions that the agents expect the AV to perform based on the environment in which the AV operates; Determine the actions used by the AV based on the intended action of the AV and the agent prediction; and Provide operation data associated with the performance of the actions to cause the AV to operate based on the actions used by the AV.

15. The system according to claim 14, the operations comprise: Obtain an agent profile.

16. The system according to claim 15, wherein, Obtaining the agent profile includes: Estimate the agent profile based on the sensor data.

17. The system according to any one of claims 14 to 16, the operations further comprise: Predict an agent trajectory based on the sensor data; wherein determining the actions used by the AV includes: determining the actions used by the AV based on the intended action of the AV, the agent prediction, and the predicted agent trajectory.

18. The system according to any one of claims 14 to 17, the operations further comprise: Obtain further sensor data associated with the environment after the AV performs the actions; and Update the agent prediction based on the further sensor data.

19. The system according to claim 17 or 18, the operations further comprise: Update the predicted agent trajectory based on the update of the agent prediction; Determine a utility score associated with a change in the predicted agent prediction based on one or more of: the agent prediction, the actions used by the AV, the agent profile, and the predicted agent trajectory.

20. A non-transitory computer-readable medium comprising instructions stored thereon that, when executed by at least one processor, cause the at least one processor to perform operations that comprise: Obtain sensor data associated with the environment in which an autonomous vehicle, i.e., an AV, is operating, wherein the environment includes agents; Determine an intended action of the AV based on the environment in which the AV is operating; Determine an agent prediction indicative of an action that the agent expects the AV to take based on the environment in which the AV is operating; Actuate the AV based on the intended action of the AV and the agent prediction; and Provide operational data associated with the performance of the action to cause the AV to operate based on the actions used by the AV.

Images