Zero shot angle of arrival estimation with transformer

Abstract

Provided are methods and systems for Angle of Arrival estimation, which can include receiving radar signals from a MIMO radar array, generating virtual array signals and virtual array element positions based on the radar signals, generating encoded messages and positional encodings, generating decoded messages based on the encoded messages, positional encodings, and a set of learnable queries, mapping the decoded messages to a plurality of estimation outputs, generating a set of object detections based on the estimation outputs, and navigating a vehicle based on the object detections.

Description

Attorney Docket No. MOTN.155WO / I2024026 ZERO SHOT ANGLE OF ARRIVAL ESTIMATION WITH TRANSFORMER CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] Any and all applications for which a foreign or domestic priority claim is identified in the Application Data Sheet as filed with the present application are incorporated by reference under 37 CFR 1.57 and made a part of this specification. The present application claims priority to U.S. Provisional Application No.63 / 683611, filed on August 15, 2024, entitled “ZERO SHOT ANGLE OF ARRIVAL ESTIMATION WITH TRANSFORMER,” which is herein incorporated by reference in its entirety. BACKGROUND

[0002] Angle of Arrival estimation can be used to improve perception tasks for autonomous vehicles. BRIEF DESCRIPTION OF THE FIGURES

[0003] FIG. 1 is an example environment in which a vehicle including one or more components of an autonomous system can be implemented;

[0004] FIG. 2 is a diagram of one or more systems of a vehicle including an autonomous system;

[0005] FIG.3 is a diagram of components of one or more devices and / or one or more systems of FIGS.1 and 2;

[0006] FIG.4A is a diagram of certain components of an autonomous system;

[0007] FIG.4B is a diagram of an implementation of a neural network;

[0008] FIG.4C and 4D are diagrams illustrating example operation of a CNN;

[0009] FIG. 5 is a block diagram illustrating an example embodiment of the autonomous system;

[0010] FIG.6A illustrates an example scene observed by a vehicle;

[0011] FIG.6B illustrates a tagged radar map of an example scene;

[0012] FIG.7 is a flowchart of a process for Angle of Arrival estimation.Attorney Docket No. MOTN.155WO / I2024026 DETAILED DESCRIPTION

[0013] In the following description numerous specific details are set forth in order to provide a thorough understanding of the present disclosure for the purposes of explanation. It will be apparent, however, that the embodiments described by the present disclosure can 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.

[0014] Specific arrangements or orderings of schematic elements, such as those representing systems, devices, modules, instruction blocks, data elements, and / or the like are illustrated in the drawings for ease of description. However, it will be understood by those skilled in the art that the specific ordering or arrangement of the schematic elements in the drawings is not meant to imply that a particular order or sequence of processing, or separation of processes, is required unless explicitly described as such. Further, the inclusion of a schematic element in a drawing is not meant to imply that such element is required in all embodiments or that the features represented by such element may not be included in or combined with other elements in some embodiments unless explicitly described as such.

[0015] Further, where connecting elements such as solid or dashed lines or arrows are used in the drawings to illustrate a connection, relationship, or association between or among two or more other schematic elements, the absence of any such connecting elements is not meant 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 disclosure. In addition, for ease of illustration, a single connecting element can be used to represent multiple connections, relationships or associations between elements. For example, where a connecting element represents communication of signals, data, or instructions (e.g., “software instructions”), it should be understood by those skilled in the art that such element can represent one or multiple signal paths (e.g., a bus), as may be needed, to affect the communication.

[0016] Although the terms first, second, third, and / or the like are used to describe various elements, these elements should not be limited by these terms. The terms first,Attorney Docket No. MOTN.155WO / I2024026 second, third, and / or the like are used only to distinguish one element from another. For example, a first contact could be termed a second contact and, similarly, a second contact could be termed a first contact without departing from the scope of the described embodiments. The first contact and the second contact are both contacts, but they are not the same contact.

[0017] The terminology used in the description of the various described embodiments herein is included for the purpose of describing particular embodiments only and is not intended to be limiting. As used in the description of the various described embodiments and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well and can be used interchangeably with “one or more” or “at least one,” unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises,” and / or “comprising,” when used in this description specify the presence of 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.

[0018] As used herein, the terms “communication” and “communicate” refer to at least one of the reception, receipt, transmission, transfer, provision, and / or the like of information (or information represented by, for example, data, signals, messages, instructions, commands, and / or the like). For one unit (e.g., a device, a system, a component of a device or system, combinations thereof, and / or the like) to be in communication with another unit means that the one unit is able to directly or indirectly receive information from and / or send (e.g., transmit) information to the other unit. This may refer to a direct or indirect connection that is wired and / or wireless in nature. Additionally, two units may be in communication with each other even though the information transmitted may be modified, processed, relayed, and / or routed between the first and second unit. For example, a first unit may be in communication with a second unit even though the first unit passively receives information and does not actively transmit information to the second unit. As another example, a first unit may be in communication with a second unit if at least one intermediary unit (e.g., a third unit locatedAttorney Docket No. MOTN.155WO / I2024026 between the first unit and the second unit) processes information received from the first unit and transmits the processed information to the second unit. In some embodiments, a message may refer to a network packet (e.g., a data packet and / or the like) that includes data.

[0019] As used herein, the term “if” is, optionally, construed to mean “when”, “upon”, “in response to determining,” “in response to detecting,” and / or the like, depending on the context. Similarly, the phrase “if it is determined” or “if [a stated condition or event] is detected” is, optionally, construed to mean “upon determining,” “in response to determining,” “upon detecting [the stated condition or event],” “in response to detecting [the stated condition or event],” and / or the like, depending on the context. Also, as used herein, the terms “has”, “have”, “having”, or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise.

[0020] Reference will now be made in detail to 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 can 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. General Overview

[0021] As the automotive industry progresses towards commercialization of Advanced Driver Assistance Systems (ADAS) and Autonomous Vehicles (AV), there is an increasing adoption of Multiple-input Multiple-output (MIMO) radar technology. Compared to lidar systems, radars offer significant advantages in terms of cost-effectiveness, resilience to adverse weather conditions, and extended detection range. However, the conventional radar data representation, primarily point clouds extracted through Fast Fourier Transform (FFT) and Constant False Alarm Rate (CFAR) processing, presents challenges. These point clouds often suffer from sparsity and a lack of semanticAttorney Docket No. MOTN.155WO / I2024026 information, which ultimately hinders the performance of downstream tasks such as object detection and segmentation.

[0022] In contrast to point cloud representations, several low level radar data formats may be available at various stages of the radar signal processing chain. These can include Analog-to-Digital Converter (ADC) data, Range-Doppler (RD) cubes, and Range- Angle-Doppler (RAD) cubes or radar images. While these low-level representations may result in usage of more sophisticated processing algorithms and incur higher storage costs, they can yield improved performance in downstream perception tasks.

[0023] Within the radar signal processing chain, the Range-Doppler (RD) cube can undergo Direction of Arrival (DOA) (also referred to herein as Angle of Arrival (AOA)), to generate the Range-Angle-Doppler (RAD) cube. The efficacy of the AOA algorithm may influence the quality and resolution of the resulting RAD cube, which can subsequently be projected into a Bird’s-Eye-View (BEV) representation for downstream tasks. Conventional approaches to AOA estimation are often constrained by either high computational demands or usage of multiple temporal snapshots.

[0024] Some aspects of the present disclosure address some or all of the issues noted above, among others, by leveraging a transformer-based machine learning model trained on a realistic simulated dataset for AOA estimation. In some embodiments, an AOA estimator may include a machine learning model trained to estimate AOA of objects detected by one or more radar sensors. The model may include multiple stages, such as an embedding stage, an encoding stage, a decoding stage, and a mapping stage. The embedding stage may involve identifying virtual array signals and virtual array positions based on radar signals received from the one or more radar sensors. The encoding stage may involve processing the virtual array signals and virtual array positions through layer normalization and self-attention mechanisms to generate one or more encoded messages. The decoding stage may involve decoding the one or more encoded messages, the virtual array positions, and a set of angle queries through layer normalization, self-attention, cross-attention mechanisms, and feed-forward networks. The mapping stage may involve mapping the set of angle queries to an output space including an estimated AOA, an estimated amplitude, and a confidence level.Attorney Docket No. MOTN.155WO / I2024026

[0025] Referring now to FIG. 1, illustrated is example environment 100 in which vehicles that include autonomous systems, as well as vehicles that do not, are operated. As illustrated, environment 100 includes vehicles 102a–102n, objects 104a–104n, routes 106a–106n, area 108, vehicle-to-infrastructure (V2I) device 110, network 112, remote autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118. Vehicles 102a–102n, vehicle-to-infrastructure (V2I) device 110, network 112, autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118 interconnect (e.g., establish a connection to communicate and / or the like) via wired connections, wireless connections, or a combination of wired or wireless connections. In some embodiments, objects 104a–104n interconnect with at least one of vehicles 102a– 102n, vehicle-to-infrastructure (V2I) device 110, network 112, autonomous vehicle (AV) system 114, fleet management system 116, and V2I system 118 via wired connections, wireless connections, or a combination of wired or wireless connections.

[0026] Vehicles 102a–102n (referred to individually as vehicle 102 and collectively as vehicles 102) include at least one device configured to transport goods and / or people. In some embodiments, vehicles 102 are configured to be in communication with V2I device 110, remote AV system 114, fleet management system 116, and / or V2I system 118 via network 112. In some embodiments, vehicles 102 include cars, buses, trucks, trains, and / or the like. In some embodiments, vehicles 102 are the same as, or similar to, vehicles 200, described herein (see FIG.2). In some embodiments, a vehicle 200 of a set of vehicles 200 is associated with an autonomous fleet manager. In some embodiments, vehicles 102 travel along respective routes 106a–106n (referred to individually as route 106 and collectively as routes 106), as described herein. In some embodiments, one or more vehicles 102 include an autonomous system (e.g., an autonomous system that is the same as or similar to autonomous system 202).

[0027] Objects 104a–104n (referred to individually as object 104 and collectively as objects 104) include, for example, at least one vehicle, at least one pedestrian, at least one cyclist, at least one structure (e.g., a building, a sign, a fire hydrant, etc.), and / or the like. Each object 104 is stationary (e.g., located at a fixed location for a period of time) or mobile (e.g., having a velocity and associated with at least one trajectory). In some embodiments, objects 104 are associated with corresponding locations in area 108.Attorney Docket No. MOTN.155WO / I2024026

[0028] Routes 106a–106n (referred to individually as route 106 and collectively as routes 106) are each associated with (e.g., prescribe) a sequence of actions (also known as a trajectory) connecting states along which an AV can navigate. Each route 106 starts at an initial state (e.g., a state that corresponds to a first spatiotemporal location, velocity, and / or the like) and ends at a final goal state (e.g., a state that corresponds to a second spatiotemporal location that is different from the first spatiotemporal location) or goal region (e.g. a subspace of acceptable states (e.g., terminal states)). In some embodiments, the first state includes a location at which an individual or individuals are to be picked-up by the AV and the second state or region includes a location or locations at which the individual or individuals picked-up by the AV are to be dropped-off. In some embodiments, routes 106 include a plurality of acceptable state sequences (e.g., a plurality of spatiotemporal location sequences), the plurality of state sequences associated with (e.g., defining) a plurality of trajectories. In an example, routes 106 include only high level actions or imprecise state locations, such as a series of connected roads dictating turning directions at roadway intersections. Additionally, or alternatively, routes 106 may include more precise actions or states such as, for example, specific target lanes or precise locations within the lane areas and targeted speed at those positions. In an example, routes 106 include a plurality of precise state sequences along the at least one high level action sequence with a limited lookahead horizon to reach intermediate goals, where the combination of successive iterations of limited horizon state sequences cumulatively correspond to a plurality of trajectories that collectively form the high level route to terminate at the final goal state or region.

[0029] Area 108 includes a physical area (e.g., a geographic region) within which vehicles 102 can navigate. In an example, area 108 includes at least one state (e.g., a country, a province, an individual state of a plurality of states included in a country, etc.), at least one portion of a state, at least one city, at least one portion of a city, etc. In some embodiments, area 108 includes at least one named thoroughfare (referred to herein as a “road”) such as a highway, an interstate highway, a parkway, a city street, etc. Additionally, or alternatively, in some examples area 108 includes at least one unnamed road such as a driveway, a section of a parking lot, a section of a vacant and / or undeveloped lot, a dirt path, etc. In some embodiments, a road includes at least one laneAttorney Docket No. MOTN.155WO / I2024026 (e.g., a portion of the road that can be traversed by vehicles 102). In an example, a road includes at least one lane associated with (e.g., identified based on) at least one lane marking.

[0030] 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 be in communication with vehicles 102 and / or V2I infrastructure system 118. In some embodiments, V2I device 110 is configured to be in communication with vehicles 102, remote AV system 114, fleet management system 116, and / or V2I system 118 via network 112. In some embodiments, V2I device 110 includes a radio frequency identification (RFID) device, signage, cameras (e.g., two-dimensional (2D) and / or three- dimensional (3D) cameras), lane markers, streetlights, parking meters, etc. In some embodiments, V2I device 110 is configured to communicate directly with vehicles 102. Additionally, or alternatively, in some embodiments V2I device 110 is configured to communicate with vehicles 102, remote AV system 114, and / or fleet 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., the public switched telephone network (PSTN), a private network, an ad hoc network, an intranet, the Internet, a fiber optic-based network, a cloud computing network, etc., a combination of some or all of these networks, and / or the like.

[0032] Remote AV system 114 includes at least one device configured to be in communication with vehicles 102, V2I device 110, network 112, fleet management system 116, and / or V2I system 118 via network 112. In an example, remote AV system 114 includes a server, a group of servers, and / or other like devices. In some embodiments, remote AV system 114 is co-located with the fleet management system 116. In some embodiments, remote AV system 114 is involved in the installation of someAttorney Docket No. MOTN.155WO / I2024026 or all of the components of a vehicle, including an autonomous system, an autonomous vehicle compute, software implemented by an autonomous vehicle compute, and / or the like. In some embodiments, remote AV system 114 maintains (e.g., updates and / or replaces) such components and / or software during the lifetime of the vehicle.

[0033] Fleet management system 116 includes at least one device configured to be in communication with vehicles 102, V2I device 110, remote AV system 114, and / or V2I infrastructure system 118. In an example, fleet management system 116 includes a server, a group of servers, and / or other like devices. In some embodiments, fleet management system 116 is associated with a ridesharing company (e.g., an organization that controls operation of multiple vehicles (e.g., vehicles that include autonomous systems and / or vehicles that do not include autonomous systems) and / or the like).

[0034] In some embodiments, V2I system 118 includes at least one device configured to be in communication with vehicles 102, V2I device 110, remote AV system 114, and / or fleet management system 116 via network 112. In some examples, V2I system 118 is configured to be in communication with V2I device 110 via a connection different from network 112. In some embodiments, V2I system 118 includes a server, a group of servers, and / or other like devices. In some embodiments, V2I system 118 is associated with a municipality or a private institution (e.g., a private institution that maintains V2I device 110 and / or the like).

[0035] The number and arrangement of elements illustrated in FIG.1 are provided as an example. There can be additional elements, fewer elements, different elements, and / or differently arranged elements, than those illustrated in FIG. 1. Additionally, or alternatively, at least one element of environment 100 can perform one or more functions described as being performed by at least one different element of FIG.1. Additionally, or alternatively, at least one set of elements of environment 100 can perform one or more functions described as being performed by at least one different set of elements of environment 100.

[0036] Referring now to FIG.2, vehicle 200 (which may be the same as, or similar to vehicles 102 of FIG.1) includes or is associated with autonomous system 202, powertrain control system 204, steering control system 206, and brake system 208. In some embodiments, vehicle 200 is the same as or similar to vehicle 102 (see FIG.1). In someAttorney Docket No. MOTN.155WO / I2024026 embodiments, autonomous system 202 is configured to confer vehicle 200 autonomous driving capability (e.g., implement at least one driving automation or maneuver-based function, feature, device, and / or the like that enable vehicle 200 to be partially or fully operated without human intervention including, without limitation, fully autonomous vehicles (e.g., vehicles that forego reliance on human intervention such as Level 5 ADS- operated vehicles), highly autonomous vehicles (e.g., vehicles that forego reliance on human intervention in certain situations such as Level 4 ADS-operated vehicles), conditional autonomous vehicles (e.g., vehicles that forego reliance on human intervention in limited situations such as Level 3 ADS-operated vehicles) and / or the like. In one embodiment, autonomous system 202 includes operational or tactical functionality required to operate vehicle 200 in on-road traffic and perform part or all of Dynamic Driving Task (DDT) on a sustained basis. 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's standard J3016: Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems, which is incorporated by reference in its entirety. In some embodiments, vehicle 200 is associated with an autonomous fleet manager and / or a ridesharing company.

[0037] Autonomous system 202 includes a sensor suite that includes one or more devices such as cameras 202a, LiDAR sensors 202b, radar sensors 202c, and microphones 202d. In some embodiments, autonomous system 202 can include more or fewer devices and / or different devices (e.g., ultrasonic sensors, inertial sensors, GPS receivers (discussed below), odometry sensors that generate data associated with an indication of a distance that vehicle 200 has traveled, and / or the like). In some embodiments, autonomous system 202 uses the one or more devices included in autonomous system 202 to generate data associated with environment 100, described herein. The data generated by the one or more devices of autonomous system 202 can be used by one or more systems described herein to observe the environment (e.g., environment 100) in which vehicle 200 is located. In some embodiments, autonomousAttorney Docket No. MOTN.155WO / I2024026 system 202 includes communication device 202e, autonomous vehicle compute 202f, drive-by-wire (DBW) system 202h, and safety controller 202g.

[0038] Cameras 202a include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG.3). Cameras 202a include at least one camera (e.g., a digital camera using a light sensor such as a Charge-Coupled Device (CCD), a thermal camera, an infrared (IR) camera, an event camera, and / or the like) to capture images including physical objects (e.g., cars, buses, curbs, people, and / or the like). In some embodiments, camera 202a generates camera data as output. In some examples, camera 202a generates camera data that includes image data associated with an image. In this example, the image data may specify at least one parameter (e.g., image characteristics such as exposure, brightness, etc., an image timestamp, and / or the like) corresponding to the image. In such an example, the image may be in a format (e.g., RAW, JPEG, PNG, and / or the like). In some embodiments, camera 202a includes a plurality of independent cameras configured on (e.g., positioned on) a vehicle to capture images for the purpose of stereopsis (stereo vision). In some examples, camera 202a includes a plurality of cameras that generate image data and transmit the image data to autonomous vehicle compute 202f and / or a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG. 1). In such an example, autonomous vehicle compute 202f determines depth to one or more objects in a field of view of at least two cameras of the plurality of cameras based on the image data from the at least two cameras. In some embodiments, cameras 202a is configured to capture images of objects within a distance from cameras 202a (e.g., up to 100 meters, up to a kilometer, and / or the like). Accordingly, cameras 202a include features such as sensors and lenses that are optimized for perceiving objects that are at one or more distances from cameras 202a.

[0039] In an embodiment, 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, camera 202a generates traffic light data associated with one or more images. In someAttorney Docket No. MOTN.155WO / I2024026 examples, camera 202a generates TLD (Traffic Light Detection) data associated with one or more images that include a format (e.g., RAW, JPEG, PNG, and / or the like). In some embodiments, camera 202a that generates TLD data differs from other systems described herein incorporating cameras in that camera 202a can include one or more cameras with a wide field of view (e.g., a wide-angle lens, a fish-eye lens, a lens having a viewing angle of approximately 120 degrees or more, and / or the like) to generate images about as many physical objects as possible.

[0040] Light Detection and Ranging (LiDAR) sensors 202b include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG.3). LiDAR sensors 202b include a system configured to transmit light from a light emitter (e.g., a laser transmitter). Light emitted by LiDAR sensors 202b include light (e.g., infrared light and / or the like) that is outside of the visible spectrum. In some embodiments, during operation, light emitted by LiDAR sensors 202b encounters a physical object (e.g., a vehicle) and is reflected back to LiDAR sensors 202b. In some embodiments, the light emitted by LiDAR sensors 202b does not penetrate the physical objects that the light encounters. LiDAR sensors 202b also include at least one light detector which detects the light that was emitted from the light emitter after the light encounters a physical object. In some embodiments, at least one data processing system associated with LiDAR sensors 202b generates an image (e.g., a point cloud, a combined point cloud, and / or the like) representing the objects included in a field of view of LiDAR sensors 202b. In some examples, the at least one data processing system associated with LiDAR sensor 202b generates an image that represents the boundaries of a physical object, the surfaces (e.g., the topology of the surfaces) of the physical object, and / or the like. In such an example, the image is used to determine the boundaries of physical objects in the field of view of LiDAR sensors 202b.

[0041] Radio Detection and Ranging (radar) sensors 202c include at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG.3). Radar sensors 202c include a system configured to transmit radio waves (either pulsed or continuously). The radio waves transmitted by radarAttorney Docket No. MOTN.155WO / I2024026 sensors 202c include radio waves that are within a predetermined spectrum In some embodiments, during operation, radio waves transmitted by radar sensors 202c encounter a physical object and are reflected back to radar sensors 202c. In some embodiments, the radio waves transmitted by radar sensors 202c are not reflected by some objects. In some embodiments, at least one data processing system associated with radar sensors 202c generates signals representing the objects included in a field of view of radar sensors 202c. For example, the at least one data processing system associated with radar sensor 202c generates an image that represents the boundaries of a physical object, the surfaces (e.g., the topology of the surfaces) of the physical object, and / or the like. In some examples, the image is used to determine the boundaries of physical objects in the field of view of radar sensors 202c.

[0042] Microphones 202d includes at least one device configured to be in communication with communication device 202e, autonomous vehicle compute 202f, and / or safety controller 202g via a bus (e.g., a bus that is the same as or similar to bus 302 of FIG. 3). Microphones 202d include one or more microphones (e.g., array microphones, external microphones, and / or the like) that capture audio signals and generate data associated with (e.g., representing) the audio signals. In some examples, microphones 202d include transducer devices and / or like devices. In some embodiments, one or more systems described herein can receive the data generated by microphones 202d and determine a position of an object relative to vehicle 200 (e.g., a distance and / or the like) based on the audio signals associated with the data.

[0043] Communication device 202e includes at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, autonomous vehicle compute 202f, safety controller 202g, and / or DBW (Drive-By-Wire) system 202h. For example, communication device 202e may include a device that is the same as or similar to communication interface 314 of FIG.3. In some embodiments, communication device 202e includes a vehicle-to-vehicle (V2V) communication device (e.g., a device that enables wireless communication of data between vehicles).

[0044] Autonomous vehicle compute 202f include at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c,Attorney Docket No. MOTN.155WO / I2024026 microphones 202d, communication device 202e, safety controller 202g, and / or DBW system 202h. In some examples, autonomous vehicle compute 202f includes a device such as a client device, a mobile device (e.g., a cellular telephone, a tablet, and / or the like), a server (e.g., a computing device including one or more central processing units, graphical processing units, and / or the like), and / or the like. In some embodiments, autonomous vehicle compute 202f is the same as or similar to autonomous vehicle compute 400, described herein. Additionally, or alternatively, in some embodiments autonomous vehicle compute 202f is configured to be in communication with an autonomous vehicle system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114 of FIG. 1), a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG.1), a V2I device (e.g., a V2I device that is the same as or similar to V2I device 110 of FIG.1), and / or a V2I system (e.g., a V2I system that is the same as or similar to V2I system 118 of FIG.1).

[0045] Safety controller 202g includes at least one device configured to be in communication with cameras 202a, LiDAR sensors 202b, radar sensors 202c, microphones 202d, communication device 202e, autonomous vehicle computer 202f, and / or DBW system 202h. In some examples, safety controller 202g includes one or more controllers (electrical controllers, electromechanical controllers, and / or the like) that are configured to generate and / or transmit control signals to operate one or more devices of vehicle 200 (e.g., powertrain control system 204, steering control system 206, brake system 208, and / or the like). In some embodiments, safety controller 202g is configured to generate control signals that take precedence over (e.g., overrides) control signals generated and / or transmitted by autonomous vehicle compute 202f.

[0046] DBW system 202h includes at least one device configured to be in communication with communication device 202e and / or autonomous vehicle compute 202f. In some examples, DBW system 202h includes one or more controllers (e.g., electrical controllers, electromechanical controllers, and / or the like) that are configured to generate and / or transmit control signals to operate one or more devices of vehicle 200 (e.g., powertrain control system 204, steering control system 206, brake system 208, and / or the like). Additionally, or alternatively, the one or more controllers of DBW systemAttorney Docket No. MOTN.155WO / I2024026 202h are configured to generate and / or transmit control signals to operate at least one different device (e.g., a turn signal, headlights, door locks, windshield wipers, and / or the like) of vehicle 200.

[0047] Powertrain control system 204 includes at least one device configured to be in communication with DBW system 202h. In some examples, powertrain control system 204 includes at least one controller, actuator, and / or the like. In some embodiments, powertrain control system 204 receives control signals from DBW system 202h and powertrain control system 204 causes vehicle 200 to make longitudinal vehicle motion, such as start moving forward, stop moving forward, start moving backward, stop moving backward, accelerate in a direction, decelerate in a direction or to make lateral vehicle motion such as performing a left turn, performing a right turn, and / or the like. In an example, powertrain control system 204 causes the energy (e.g., fuel, electricity, and / or the like) provided to a motor of the vehicle to increase, remain the same, or decrease, thereby causing at least one wheel of vehicle 200 to rotate or not rotate.

[0048] Steering control system 206 includes at least one device configured to rotate one or more wheels of vehicle 200. In some examples, steering control system 206 includes at least one controller, actuator, and / or the like. In some embodiments, steering control system 206 causes the front two wheels and / or the rear two wheels of vehicle 200 to rotate to the left or right to cause vehicle 200 to turn to the left or right. In other words, steering control system 206 causes activities necessary for the regulation of the y-axis component of vehicle motion.

[0049] Brake system 208 includes at least one device configured to actuate one or more brakes to cause vehicle 200 to reduce speed and / or remain stationary. In some examples, brake system 208 includes at least one controller and / or actuator that is configured to cause one or more calipers associated with one or more wheels of vehicle 200 to close on a corresponding rotor of vehicle 200. Additionally, or alternatively, in some examples brake system 208 includes an automatic emergency braking (AEB) system, a regenerative braking system, and / or the like.

[0050] In some embodiments, vehicle 200 includes at least one platform sensor (not explicitly illustrated) that measures or infers properties of a state or a condition of vehicle 200. In some examples, vehicle 200 includes platform sensors such as a globalAttorney Docket No. MOTN.155WO / I2024026 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, a steering angle sensor, and / or the like. Although brake system 208 is illustrated to be located in the near side of vehicle 200 in FIG. 2, brake system 208 may be located anywhere in vehicle 200.

[0051] Referring now to FIG.3, illustrated is a schematic diagram of a device 300. As illustrated, device 300 includes processor 304, memory 306, storage component 308, input interface 310, output interface 312, communication interface 314, and bus 302. In some embodiments, device 300 corresponds to at least one device of vehicles 102 (e.g., at least one device of a system of vehicles 102), at least one device of the remote AV system 114, at least one device of the fleet management system 116, at least one device of the vehicle-to-infrastructure 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 vehicles 102 (e.g., one or more devices of a system of vehicles 102), at least one device of the remote AV system 114, at least one device of the fleet management system 116, at least one device of the vehicle-to-infrastructure system 118, 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 shown in FIG.3, device 300 includes bus 302, processor 304, memory 306, storage component 308, input interface 310, output interface 312, and communication interface 314.

[0052] Bus 302 includes a component that permits communication among the components of device 300. In some cases, the processor 304 includes a processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), and / or the like), a microphone, a digital signal processor (DSP), and / or any processing component (e.g., a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), and / or the like) that can be programmed to perform at least one function. Memory 306 includes random access memory (RAM), read- only memory (ROM), and / or another type of dynamic and / or static storage device (e.g., flash memory, magnetic memory, optical memory, and / or the like) that stores data and / or instructions for use by processor 304.Attorney Docket No. MOTN.155WO / I2024026

[0053] 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-optic disk, a solid state disk, and / or the like), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, a CD-ROM, RAM, PROM, EPROM, FLASH-EPROM, NV-RAM, and / or another type of computer readable medium, along with a corresponding drive.

[0054] Input interface 310 includes a component that permits device 300 to receive information, such as via user input (e.g., a touchscreen display, a keyboard, a keypad, a mouse, a button, a switch, a microphone, a camera, and / or the like). Additionally or alternatively, in some embodiments input interface 310 includes a sensor that senses information (e.g., a global positioning system (GPS) receiver, an accelerometer, a gyroscope, an actuator, and / or the like). Output interface 312 includes a component that provides output information from device 300 (e.g., a display, a speaker, one or more light- emitting diodes (LEDs), and / or the like).

[0055] In some embodiments, communication interface 314 includes a transceiver-like component (e.g., a transceiver, a separate receiver and transmitter, and / or the like) that permits device 300 to communicate with other devices via a wired connection, a wireless connection, or a combination of wired and wireless connections. In some examples, communication interface 314 permits device 300 to receive information from another device and / or provide information to another device. In some examples, communication interface 314 includes an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi®interface, a cellular network interface, and / or the like.

[0056] In some embodiments, device 300 performs one or more processes described herein. Device 300 performs these processes based on processor 304 executing software instructions stored by a computer-readable medium, such as memory 305 and / or storage component 308. A computer-readable medium (e.g., a non-transitory computer readable medium) is defined herein as a non-transitory memory device. A non-transitory memory device includes memory space located inside a single physical storage device or memory space spread across multiple physical storage devices.Attorney Docket No. MOTN.155WO / I2024026

[0057] In some embodiments, software instructions are read into memory 306 and / or storage component 308 from another computer-readable medium or from another device via communication interface 314. When executed, software instructions stored in memory 306 and / or storage component 308 cause processor 304 to perform one or more processes described herein. Additionally or alternatively, hardwired circuitry is used in place of or in combination with software instructions to perform one or more processes described herein. Thus, embodiments described herein are not limited to any specific combination of hardware circuitry and software unless explicitly stated otherwise.

[0058] Memory 306 and / or storage component 308 includes data storage or at least one data structure (e.g., a database and / or the like). Device 300 is capable of receiving information from, storing information in, communicating information to, or searching information stored in the data storage or the at least one data structure in memory 306 or storage component 308. In some examples, the information includes network data, input data, output data, or any combination thereof.

[0059] In some embodiments, device 300 is configured to execute software instructions that are either stored in memory 306 and / or in 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 in the memory of another device that, when executed by processor 304 and / or by a processor of another device (e.g., another device that is the same as or similar to device 300) cause device 300 (e.g., at least one component of device 300) to perform one or more processes described herein. In some embodiments, a module is implemented in software, firmware, hardware, and / or the like.

[0060] The number and arrangement of components illustrated in FIG.3 are provided as an example. In some embodiments, device 300 can include additional components, fewer components, different components, or differently arranged components than those illustrated in FIG.3. Additionally or alternatively, a set of components (e.g., one or more components) of device 300 can perform one or more functions described as being performed by another component or another set of components of device 300.

[0061] Referring now to FIG. 4, illustrated is an example block diagram of an autonomous vehicle compute 400 (sometimes referred to as an “AV stack”). As illustrated,Attorney Docket No. MOTN.155WO / I2024026 autonomous vehicle compute 400 includes perception system 402 (sometimes referred to as a perception module), planning system 404 (sometimes referred to as a planning module), localization system 406 (sometimes referred to as a localization module), control system 408 (sometimes referred to as a control module), and database 410. In some embodiments, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included and / or implemented in an autonomous navigation system of a vehicle (e.g., autonomous vehicle compute 202f of vehicle 200). Additionally, or alternatively, in some embodiments perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included in one or more standalone systems (e.g., one or more systems that are the same as or similar to autonomous vehicle compute 400 and / or the like). In some examples, perception system 402, planning system 404, localization system 406, control system 408, and database 410 are included in one or more standalone systems that are located in a vehicle and / or at least one remote system as described herein. In some embodiments, any and / or all of the systems included in autonomous vehicle compute 400 are implemented in software (e.g., in software instructions stored in memory), computer hardware (e.g., by microprocessors, microcontrollers, application-specific integrated circuits (ASICs), Field Programmable Gate Arrays (FPGAs), and / or the like), or combinations of computer software and computer hardware. It will also be understood that, in some embodiments, autonomous vehicle compute 400 is configured to be in communication with a remote system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114, a fleet management system 116 that is the same as or similar to fleet management system 116, a V2I system that is the same as or similar to V2I system 118, and / or the like).

[0062] In some embodiments, perception system 402 receives data associated with at least one physical object (e.g., data that is used by perception system 402 to detect the at least one physical object) in an environment and classifies the at least one physical object. In some examples, perception system 402 receives image data captured by at least one camera (e.g., cameras 202a), the image associated with (e.g., representing) one or more physical objects within a field of view of the at least one camera. In such an example, perception system 402 classifies at least one physical object based on one orAttorney Docket No. MOTN.155WO / I2024026 more groupings of physical objects (e.g., bicycles, vehicles, traffic signs, pedestrians, and / or the like). In some embodiments, perception system 402 transmits data associated with the classification of the physical objects to planning system 404 based on perception system 402 classifying the physical objects.

[0063] In some embodiments, planning system 404 receives data associated with a destination and generates data associated with at least one route (e.g., routes 106) along which a vehicle (e.g., vehicles 102) can travel along toward a destination. In some embodiments, planning system 404 periodically or continuously receives data from perception system 402 (e.g., data associated with the classification of physical objects, described above) and planning system 404 updates the at least one trajectory or generates at least one different trajectory based on the data generated by perception system 402. In other words, planning system 404 may perform tactical function-related tasks that are required to operate vehicle 102 in on-road traffic. Tactical efforts involve maneuvering the vehicle in traffic during a trip, including but not limited to deciding whether and when to overtake another vehicle, change lanes, or selecting an appropriate speed, acceleration, deacceleration, etc. In some embodiments, planning system 404 receives data associated with an updated position of a vehicle (e.g., vehicles 102) from localization system 406 and planning system 404 updates the at least one trajectory or generates at least one different trajectory based on the data generated by localization system 406.

[0064] In some embodiments, localization system 406 receives data associated with (e.g., representing) a location of a vehicle (e.g., vehicles 102) in an area. In some examples, localization system 406 receives LiDAR data associated with at least one point cloud generated by at least one LiDAR sensor (e.g., LiDAR sensors 202b). In certain examples, localization system 406 receives data associated with at least one point cloud from multiple LiDAR sensors and localization system 406 generates a combined point cloud based on each of the point clouds. In these examples, localization system 406 compares the at least one point cloud or the combined point cloud to two-dimensional (2D) and / or a three-dimensional (3D) map of the area stored in database 410. Localization system 406 then determines the position of the vehicle in the area based on localization system 406 comparing the at least one point cloud or the combined pointAttorney Docket No. MOTN.155WO / I2024026 cloud to the map. In some embodiments, the map includes a combined point cloud of the area generated prior to navigation of the vehicle. In some embodiments, maps include, without limitation, high-precision maps of the roadway geometric properties, maps describing road network connectivity properties, maps describing roadway physical properties (such as traffic speed, traffic volume, the number of vehicular and cyclist traffic lanes, lane width, lane traffic directions, or lane marker types and locations, or combinations thereof), and maps describing the spatial locations of road features such as crosswalks, traffic signs or other travel signals of various types. In some embodiments, the map is generated in real-time based on the data received by the perception system.

[0065] In another example, localization system 406 receives Global Navigation Satellite System (GNSS) data generated by a global positioning system (GPS) receiver. In some examples, localization system 406 receives GNSS data associated with the location of the vehicle in the area and localization system 406 determines a latitude and longitude of the vehicle in the area. In such an example, localization system 406 determines the position of the vehicle in the area based on the latitude and longitude of the vehicle. In some embodiments, localization system 406 generates data associated with the position of the vehicle. In some examples, localization system 406 generates data associated with the position of the vehicle based on localization system 406 determining the position of the vehicle. In such an example, 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.

[0066] In some embodiments, control system 408 receives data associated with at least one trajectory from planning system 404 and control system 408 controls operation of the vehicle. In some examples, control system 408 receives data associated with at least one trajectory from planning system 404 and control system 408 controls operation of the vehicle by generating and transmitting control signals to cause a powertrain control system (e.g., DBW system 202h, powertrain control system 204, and / or the like), a steering control system (e.g., steering control system 206), and / or a brake system (e.g., brake system 208) to operate. For example, control system 408 is configured to perform operational functions such as a lateral vehicle motion control or a longitudinal vehicle motion control. The lateral vehicle motion control causes activities necessary for theAttorney Docket No. MOTN.155WO / I2024026 regulation of the y-axis component of vehicle motion. The longitudinal vehicle motion control causes activities necessary for the regulation of the x-axis component of vehicle motion. In an example, where a trajectory includes a left turn, control system 408 transmits a control signal to cause steering control system 206 to adjust a steering angle of vehicle 200, thereby causing vehicle 200 to turn left. Additionally, or alternatively, control system 408 generates and transmits control signals to cause other devices (e.g., headlights, turn signal, door locks, windshield wipers, and / or the like) of vehicle 200 to change states.

[0067] In some embodiments, perception system 402, planning system 404, localization system 406, and / or control system 408 implement at least one machine learning model (e.g., at least one multilayer perceptron (MLP), at least one convolutional neural network (CNN), at least one recurrent neural network (RNN), at least one autoencoder, at least one transformer, and / or the like). In some examples, perception system 402, planning system 404, localization system 406, and / or control system 408 implement at least one machine learning model alone or in combination with one or more of the above-noted systems. In some examples, perception system 402, planning system 404, localization system 406, and / or 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 an environment and / or the like). An example of an implementation of a machine learning model is included below with respect to FIGS.4B–4D.

[0068] Database 410 stores data that is transmitted to, received from, and / or updated by perception system 402, planning system 404, localization system 406 and / or control system 408. In some examples, database 410 includes a storage component (e.g., a storage component that is the same as or similar to storage component 308 of FIG.3) that stores data and / or software related to the operation and uses at least one system of autonomous vehicle compute 400. In some embodiments, database 410 stores data associated with 2D and / or 3D maps of at least one area. In some examples, database 410 stores data associated with 2D and / or 3D maps of a portion of a city, multiple portions of multiple cities, multiple cities, a county, a state, a State (e.g., a country), and / or the like). In such an example, a vehicle (e.g., a vehicle that is the same as or similar to vehicles 102 and / or vehicle 200) can drive along one or more drivable regions (e.g.,Attorney Docket No. MOTN.155WO / I2024026 single-lane roads, multi-lane roads, highways, back roads, off road trails, and / or the like) and cause at least one LiDAR sensor (e.g., a LiDAR sensor that is the same as or similar to LiDAR sensors 202b) to generate data associated with an image representing the objects included in a field of view of the at least one LiDAR sensor.

[0069] In some embodiments, database 410 can be implemented across a plurality of devices. In some examples, database 410 is included in a vehicle (e.g., a vehicle that is the same as or similar to vehicles 102 and / or vehicle 200), an autonomous vehicle system (e.g., an autonomous vehicle system that is the same as or similar to remote AV system 114, a fleet management system (e.g., a fleet management system that is the same as or similar to fleet management system 116 of FIG.1, a V2I system (e.g., a V2I system that is the same as or similar to V2I system 118 of FIG.1) and / or the like.

[0070] Referring now to FIG. 4B, illustrated is a diagram of an implementation of a machine learning model. More specifically, illustrated is a diagram of an implementation of a convolutional neural network (CNN) 420. For purposes of illustration, the following description of CNN 420 will be with respect to an implementation of CNN 420 by perception system 402. However, it will be understood that in some examples CNN 420 (e.g., one or more components of CNN 420) is implemented by other systems different from, or in addition to, perception system 402 such as planning system 404, localization system 406, and / or control system 408. While CNN 420 includes certain features as described herein, these features are provided for the purpose of illustration and are not intended to limit the present disclosure.

[0071] CNN 420 includes a plurality of convolution layers including first convolution layer 422, second convolution layer 424, and convolution layer 426. In some embodiments, CNN 420 includes sub-sampling layer 428 (sometimes referred to as a pooling layer). In some embodiments, sub-sampling layer 428 and / or other subsampling layers have a dimension (i.e., an amount of nodes) that is less than a dimension of an upstream system. By virtue of sub-sampling layer 428 having a dimension that is less than a dimension of an upstream layer, CNN 420 consolidates the amount of data associated with the initial input and / or the output of an upstream layer to thereby decrease the amount of computations necessary for CNN 420 to perform downstream convolution operations. Additionally, or alternatively, by virtue of sub-sampling layer 428 beingAttorney Docket No. MOTN.155WO / I2024026 associated with (e.g., configured to perform) at least one subsampling function (as described below with respect to FIGS.4C and 4D), CNN 420 consolidates the amount of data associated with the initial input.

[0072] Perception system 402 performs convolution operations based on perception system 402 providing respective inputs and / or outputs associated with each of first convolution layer 422, second convolution layer 424, and convolution layer 426 to generate respective outputs. In some examples, perception system 402 implements CNN 420 based on perception system 402 providing data as input to first convolution layer 422, second convolution layer 424, and convolution layer 426. In such an example, perception system 402 provides the data as input to first convolution layer 422, second convolution layer 424, and convolution layer 426 based on perception system 402 receiving data from one or more different systems (e.g., one or more systems of a vehicle that is the same as or similar to vehicle 102), a remote AV system that is the same as or similar to remote AV system 114, a fleet management system that is the same as or similar to fleet management system 116, a V2I system that is the same as or similar to V2I system 118, and / or the like). A detailed description of convolution operations is included below with respect to FIG.4C.

[0073] In some embodiments, perception system 402 provides data associated with an input (referred to as an initial input) to first convolution layer 422 and perception system 402 generates data associated with an output using first convolution layer 422. In some embodiments, perception system 402 provides an output generated by a convolution layer as input to a different convolution layer. For example, perception system 402 provides the output of first convolution layer 422 as input to sub-sampling layer 428, second convolution layer 424, and / or convolution layer 426. In such an example, first convolution layer 422 is referred to as an upstream layer and sub-sampling layer 428, second convolution layer 424, and / or convolution layer 426 are referred to as downstream layers. Similarly, in some embodiments perception system 402 provides the output of sub-sampling layer 428 to second convolution layer 424 and / or convolution layer 426 and, in this example, sub-sampling layer 428 would be referred to as an upstream layer and second convolution layer 424 and / or convolution layer 426 would be referred to as downstream layers.Attorney Docket No. MOTN.155WO / I2024026

[0074] In some embodiments, perception system 402 processes the data associated with the input provided to CNN 420 before perception system 402 provides the input to CNN 420. For example, perception system 402 processes the data associated with the input provided to CNN 420 based on perception system 402 normalizing sensor data (e.g., image data, LiDAR data, radar data, and / or the like).

[0075] In some embodiments, CNN 420 generates an output based on perception system 402 performing convolution operations associated with each convolution layer. In some examples, CNN 420 generates an output based on perception system 402 performing convolution operations associated with each convolution layer and an initial input. In some embodiments, perception system 402 generates the output and provides the output as fully connected layer 430. In some examples, perception system 402 provides the output of convolution layer 426 as fully connected layer 430, where fully connected layer 430 includes data associated with a plurality of feature values referred to as F1, F2... FN. In this example, the output of convolution layer 426 includes data associated with a plurality of output feature values that represent a prediction.

[0076] In some embodiments, perception system 402 identifies a prediction from among a plurality of predictions based on perception system 402 identifying a feature value that is associated with the highest likelihood of being the correct prediction from among the plurality of predictions. For example, where fully connected layer 430 includes feature values F1, F2, ... FN, and F1 is the greatest feature value, perception system 402 identifies the prediction associated with F1 as being the correct prediction from among the plurality of predictions. In some embodiments, perception system 402 trains CNN 420 to generate the prediction. In some examples, perception system 402 trains CNN 420 to generate the prediction based on perception system 402 providing training data associated with the prediction to CNN 420.

[0077] Referring now to FIGS. 4C and 4D, illustrated is a diagram of example operation of CNN 440 by perception system 402. In some embodiments, CNN 440 (e.g., one or more components of CNN 440) is the same as, or similar to, CNN 420 (e.g., one or more components of CNN 420) (see FIG.4B).

[0078] At step 450, perception system 402 provides data associated with an image as input to CNN 440 (step 450). For example, as illustrated, perception system 402 providesAttorney Docket No. MOTN.155WO / I2024026 the data associated with the image to CNN 440, where the image is a greyscale image represented as values stored in a two-dimensional (2D) array. In some embodiments, the data associated with the image may include data associated with a color image, the color image represented as values stored in a three-dimensional (3D) array. Additionally, or alternatively, the data associated with the image may include data associated with an infrared image, a radar image, and / or the like.

[0079] At step 455, CNN 440 performs a first convolution function. For example, CNN 440 performs the first convolution function based on CNN 440 providing the values representing the image as input to one or more neurons (not explicitly illustrated) included in first convolution layer 442. In this example, the values representing the image can correspond to values representing a region of the image (sometimes referred to as a receptive field). In some embodiments, each neuron is associated with a filter (not explicitly illustrated). A filter (sometimes referred to as a kernel) is representable as an array of values that corresponds in size to the values provided as input to the neuron. In one example, a filter may be configured to identify edges (e.g., horizontal lines, vertical lines, straight lines, and / or the like). In successive convolution layers, the filters associated with neurons may be configured to identify successively more complex patterns (e.g., arcs, objects, and / or the like).

[0080] In some embodiments, CNN 440 performs the first convolution function based on CNN 440 multiplying the values provided as input to each of the one or more neurons included in first convolution layer 442 with the values of the filter that corresponds to each of the one or more neurons. For example, CNN 440 can multiply the values provided as input to each of the one or more neurons included in first convolution layer 442 with the values of the filter that corresponds to each of the one or more neurons to generate a single value or an array of values as an output. In some embodiments, the collective output of the neurons of first convolution layer 442 is referred to as a convolved output. In some embodiments, where each neuron has the same filter, the convolved output is referred to as a feature map.

[0081] In some embodiments, CNN 440 provides the outputs of each neuron of first convolutional layer 442 to neurons of a downstream layer. For purposes of clarity, an upstream layer can be a layer that transmits data to a different layer (referred to as aAttorney Docket No. MOTN.155WO / I2024026 downstream layer). For example, CNN 440 can provide the outputs of each neuron of first convolutional layer 442 to corresponding neurons of a subsampling layer. In an example, CNN 440 provides the outputs of each neuron of first convolutional layer 442 to corresponding neurons of first subsampling layer 444. In some embodiments, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of the downstream layer. For example, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of first subsampling layer 444. In such an example, CNN 440 determines a final value to provide to each neuron of first subsampling layer 444 based on the aggregates of all the values provided to each neuron and an activation function associated with each neuron of first subsampling layer 444.

[0082] At step 460, CNN 440 performs a first subsampling function. For example, CNN 440 can perform a first subsampling function based on CNN 440 providing the values output by first convolution layer 442 to corresponding neurons of first subsampling layer 444. In some embodiments, CNN 440 performs the first subsampling function based on an aggregation function. In an example, CNN 440 performs the first subsampling function based on CNN 440 determining the maximum input among the values provided to a given neuron (referred to as a max pooling function). In another example, CNN 440 performs the first subsampling function based on CNN 440 determining the average input among the values provided to a given neuron (referred to as an average pooling function). In some embodiments, CNN 440 generates an output based on CNN 440 providing the values to each neuron of first subsampling layer 444, the output sometimes referred to as a subsampled convolved output.

[0083] At step 465, CNN 440 performs a second convolution function. In some embodiments, CNN 440 performs the second convolution function in a manner similar to how CNN 440 performed the first convolution function, described above. In some embodiments, CNN 440 performs the second convolution function based on CNN 440 providing the values output by first subsampling layer 444 as input to one or more neurons (not explicitly illustrated) included in second convolution layer 446. In some embodiments, each neuron of second convolution layer 446 is associated with a filter, as described above. The filter(s) associated with second convolution layer 446 may be configured toAttorney Docket No. MOTN.155WO / I2024026 identify more complex patterns than the filter associated with first convolution layer 442, as described above.

[0084] In some embodiments, CNN 440 performs the second convolution function based on CNN 440 multiplying the values provided as input to each of the one or more neurons included in second convolution layer 446 with the values of the filter that corresponds to each of the one or more neurons. For example, CNN 440 can multiply the values provided as input to each of the one or more neurons included in second convolution layer 446 with the values of the filter that corresponds to each of the one or more neurons to generate a single value or an array of values as an output.

[0085] In some embodiments, CNN 440 provides the outputs of each neuron of second convolutional layer 446 to neurons of a downstream layer. For example, CNN 440 can provide the outputs of each neuron of first convolutional layer 442 to corresponding neurons of a subsampling layer. In an example, CNN 440 provides the outputs of each neuron of first convolutional layer 442 to corresponding neurons of second subsampling layer 448. In some embodiments, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of the downstream layer. For example, CNN 440 adds a bias value to the aggregates of all the values provided to each neuron of second subsampling layer 448. In such an example, CNN 440 determines a final value to provide to each neuron of second subsampling layer 448 based on the aggregates of all the values provided to each neuron and an activation function associated with each neuron of second subsampling layer 448.

[0086] At step 470, CNN 440 performs a second subsampling function. For example, CNN 440 can perform a second subsampling function based on CNN 440 providing the values output by second convolution layer 446 to corresponding neurons of second subsampling layer 448. In some embodiments, CNN 440 performs the second subsampling function based on CNN 440 using an aggregation function. In an example, CNN 440 performs the first subsampling function based on CNN 440 determining the maximum input or an average input among the values provided to a given neuron, as described above. In some embodiments, CNN 440 generates an output based on CNN 440 providing the values to each neuron of second subsampling layer 448.Attorney Docket No. MOTN.155WO / I2024026

[0087] At step 475, CNN 440 provides the output of each neuron of second subsampling layer 448 to fully connected layers 449. For example, CNN 440 provides the output of each neuron of second subsampling layer 448 to fully connected layers 449 to cause fully connected layers 449 to generate an output. In some embodiments, fully connected layers 449 are configured to generate an output associated with a prediction (sometimes referred to as a classification). The prediction may include an indication that an object included in the image provided as input to CNN 440 includes an object, a set of objects, and / or the like. In some embodiments, perception system 402 performs one or more operations and / or provides the data associated with the prediction to a different system, described herein. Angle of Arrival Estimator

[0088] FIG. 5 is a block diagram illustrating an example embodiment of the autonomous system 202. In the illustrated embodiment, the autonomous system 202 includes radar sensors 202c and the perception system 402. The radar sensors 202c may include one or more multiple-input-multiple-output (MIMO) radar arrays 540 (collectively referred to as “MIMO radar array 540). For example, the radar sensors 202c may be part of a radar system, such as that described in International Patent Application No. PCT / US2025 / 031940, filed on June 2, 2025, entitled “SIDELOBE REMOVAL AND CLUTTER RETENTION IN A RADAR IMAGING PIPELINE,” the entirety of which is incorporated by reference herein. The MIMO radar array 540 may include multiple antennas, including multiple receiving and multiple transmitting antennas. For example, the MIMO radar array may include 6 (or more or less) transmitting antennas and 8 (or more or less) receiving antennas, which may work in parallel. In some cases, the radar sensors 202c may include one or more radio transceivers configured to provide outgoing radar signals to transmit antennas and receive reflected radio signals from the receiving antennas. The reflected radio signals may be reflections of outgoing radio signals radiated by any one of the one or more transmitting antennas generated by objects and surfaces in an environment around the autonomous system 202. The reflected radio signals may be received from any of the one or more receiving antennas.Attorney Docket No. MOTN.155WO / I2024026

[0089] The perception system 402 includes a radar data processing module 530, which may be part of a radar data processing pipeline, such as the radar imaging pipeline 606 described in International Patent Application No. PCT / US2025 / 031940, to generate a radar image 532. The radar image 532 may comprise a range-Doppler map visually representing detected objects in an environment based on their distance and velocity and a least a potion of the background and clutter in the environment. the perception system 402 can also include an object detector 534 which may be used to detect and tag objects in the radar image 532 to generate a tagged radar map 536. The tagged radar map 536 may include the radar image 532 as well as additional markers and identifiers indicative of different objects in the image. In some cases, the tagged radar map 536 may also include the spatial coordinate, range, and velocity for individual objects in the radar image 532.

[0090] The radar data processing module 530 can include an Angle of Arrival (AOA) estimator 502, which can determine the angular location of points and objects in an environment with respect to the radar sensors 202c based on data from the radar sensors 202c. In some cases, the data from the radar sensors 202c may include digitized radar signals generated by a transceiver of a radar sensor 202c in response to receiving radio waves, or signals, reflected by an environment around the radar sensor 202c. The AOA estimator 502 may implement an AOA estimation algorithm to determine the direction from which a reflected radio wave of a plurality of reflected radio waves, propagating along closely spaced directions, has arrived at an antenna. In some cases, the AOA estimation algorithm may be learned using the estimation model 520.

[0091] In some embodiments, the estimation model 520 may include a machine learning model comprising a transformer-based neural network architecture. In the illustrated example, the estimation model 520 includes an encoder 506, a decoder 508, and prediction heads 510, however, it will be understood that the estimation model 520 may include fewer or more components. The estimation model 520 may receive inputs from the embedding stage 504 and output data to the AOA predictor 512. As described herein, the estimation model 520 may be trained on synthetic radar array data to estimate AOA from incoming radar signals.Attorney Docket No. MOTN.155WO / I2024026

[0092] During the embedding stage 504, the AOA estimator 502 may process data obtained from the MIMO radar array 540 to demultiplex processed radar data corresponding to various antennas of the MIMO radar array 540 and isolate channels between specific transmitters (e.g., transmitting antennas) and receivers (e.g., receiving antennas). For example, during the embedding stage 504, the AOA estimator 502 may identify virtual array signals based on a virtual array corresponding to the MIMO radar array 540. The virtual array may include virtual array elements corresponding to each transceiver-receiver channel. Each transceiver may have a channel between the transceiver and each receiver. For example, given a MIMO radar array with 6 transmitting antennas and 8 receiving antennas, the MIMO radar array itself may have only 14 array elements (6 transmitters + 8 receivers), but the corresponding virtual array may have 48 virtual array elements (6 transmitters * 8 receivers). The AOA estimator 502 may identify virtual array signals corresponding to some or all of the virtual array elements. For example the AOA estimator 502 may identify a first virtual signal corresponding to virtual array element A, where virtual array element A is associated with the transceiver-receiver pair T1-R1, and a second virtual signal corresponding to virtual array element B, where virtual array element B is associated with the transceiver-receiver pair T1-R2.

[0093] Additionally, the AOA estimator 502 may identify positions of the virtual array elements based on the convolution of the set of transmitter positions and the set of receiver positions on the MIMO radar array 540. For example, if the transmitters are positioned along a first axis, and the receivers are positioned along a second axis parallel to the first axis, the virtual array element positions may reduce to a set of intersections between the cartesian coordinates for each of the transmitters and receivers in the MIMO radar array 540. In some embodiments, the virtual array signals may be represented bya measured data vector ^^ ∈ ℂ^ൈ^, and the virtual array element positions may berepresented by the vector ^^ ∈ ℝ^ൈଷ, where ^^ is the number of virtual array elements. Insome embodiments, the virtual array signals and virtual array element positions may be fed in as inputs to the estimation model 520.

[0094] The estimation model 520 may process the virtual array signal and virtual arrayelement position vectors (^^ ∈ ℂ^ൈ^ and ^^ ∈ ℝ^ൈଷ) to project the virtual array signals andvirtual array element positions to high dimensional embedding vectors ^ത^ ∈ ℝ^ൈ^ andAttorney Docket No. MOTN.155WO / I2024026^ത^ ∈ ℝ^ൈ^ respectively, which may be fed into the encoder 506. In some embodiments,the estimation model 520 may use basis expansion techniques, such as implementation of radial basis function (RBF) kernels to transform the virtual array signal and virtual array element position vectors into a higher dimensional embedding space. In some embodiments, the encoder 506 may be a transformer encoder. For example, the encoder 506 may be a transformer encoder such as that described in “End-to-end object detection with transformers” by N. Carion et al., in European Conference on Computer Vision, 213- 229, Springer, the entirety of which is incorporated by reference herein. The encoder 506 can include multiple encoder blocks, or layers. The sum of the projected virtual array signal vector and the projected virtual array element position vector (representing positional encodings of the virtual array signals) may be fed into a first encoder block of the encoder 506. Additional encoder blocks may take as input, the output of a previous encoder block. In some embodiments, one or more of the encoder blocks may include a layer normalization (LN) module, a multi-head self-attention module, and one or more feed-forward networks (FFNs). The resulting output of the encoder 506 may includeencoded messages ^ത^ ∈ ℝ^ൈ^ representing processed virtual array signals. The encodedmessages (^ത^^ and the positional encodings (^ത^) may be fed into the decoder 508.

[0095] In some embodiments, the decoder 508 may be a transformer decoder. The decoder 508 may include one or more decoder blocks. In some cases, one or more of the decoder blocks may include an LN module, a multi-head self-attention module, a multi- head cross-attention module, and one or more FFNs. For example, the decoder 508 may be a transformer decoder such as that described in Carion et. al. In some embodiments, the decoder 508 may take as input a set of angle queries 516, represented by the setഥ ^^ ∈ ℝெൈ^. The angle queries 516 may correspond to a set of angle proposals associatedwith a plurality of angles corresponding to signals transmitted by the MIMO radar array 540. In some embodiments, the multi-head self-attention module of the decoder 508 may take as input query, key, and value vectors. The query, key, and value vectors may be based on the angle queries 516. In some cases, the number of angle queries may correspond to a plurality of angles corresponding to signals transmitted by the MIMO radar array 540 (also referred to herein as the “radar detection space”). For example, if the MIMO radar array 540 transmits signals at 80 different angles, 80 angle queries 516Attorney Docket No. MOTN.155WO / I2024026 may be initialized (e.g., one per angle, one per degree, etc.). In some cases, more or less angle queries 516 may be initialized with random values. The set of angle queries 516 may be initialized with learned parameters, such as parameters learned during model training. In some cases, embedding values representing the set of angle queries 516 may be added to the query and key vectors prior to input into the multi-head self-attention module.

[0096] Additionally, in some embodiments, the embedding values representing the set of angle queries 516 may be added to the output vector from the multi-head self-attention module and input to as the query vector to the multi-head cross-attention module. Further, the decoder 508 may use the encoded messages (^ത^^ as the keys, and the positional encodings (^ത^) as the values, for the multi-head cross-attention module in the decoder blocks. This can enable enrichment of the set of angle queries 516 using cross-attention with the virtual array signal features output by the encoder 506.

[0097] The decoder 508 can output angle query output vectors 518 from the last decoder block, with each angle query output vector 518 corresponding to one of the angle queries 516. The angle query output vectors 518 may then be fed to the prediction heads 510 for mapping to an output space.

[0098] Thus, unlike traditional grid-based AOA estimation approaches, the AOA estimator 502 can globally reason about the angles in the detection space together in one-shot rather than having to split the radar detection space into a grid and analyze each grid element individually. Accordingly, the AOA estimator 502 enables more efficient and computationally less expensive AOA estimation than traditional grid-based approaches.

[0099] The prediction heads 510 may process the queries to map some or all of the queries to an output space. In some embodiments, the prediction heads 510 include the FFNs of the decoder blocks. The output space may include an estimated angle (^^), an estimated magnitude (^^), and a confidence level (^^) for a detection target. The estimated angle may correspond to an estimated azimuth of a radar detection. The estimated magnitude may correspond to an estimated reflectivity of a target or signal strength associated with a radar detection. The confidence level may correspond to a confidence level that a radar detection is a true positive detection of a target. Accordingly, for each of the angle query output vectors 518, the prediction heads 510 can predict an angle,Attorney Docket No. MOTN.155WO / I2024026 magnitude, and confidence level. In some embodiments, the outputs of the prediction heads 510 may be further processed by the AOA estimator 502. The AOA estimator 502 may analyze the predictions output by the prediction heads 510 and discard any predictions that fail to satisfy a confidence threshold to generate a final set of angle predictions 514.

[0100] In some embodiments, the AOA estimator 502 may train the estimation model 520 using a modified set prediction loss, such as that discussed in “End-to-end object detection with transformers” by N. Carion et al., in European Conference on Computer Vision, 213-229, Springer, the entirety of which is incorporated by reference herein. Forexample, given ^^ ground truth targets, ground truth angles ^^ ∈ ℝெൈ^ and magnitudes^^ ∈ ℝெൈ^ are padded with ^^ െ ^^s of no detection. For example, ^^^ ൌ⊘ may be used toindicate the ith ground truth is a padded detection. Additionally, bipartite matching between ground truth and prediction sets can be performed to find a permutation of ^^elements ^^ ∈ ^^ as follows^^∗ ൌ argmin^^ ∈ ^^ ∑ெ ^ℒ୫ୟ^ୡ୦൫ఏ,ఈ,^^,ఏ^^^^^,ఈ^^^^^,^^^^^^,൯, (1) whereℒ୫ୟ^ୡ୦൫ఏ,ఈ,^^,ఏ^^^^^,ఈ^^^^^,^^^^^^,൯, ൌെ ^^^ఙ^^^ฮ^^^^ఈ ∙ ^^^^^ஷ⊘^ฮ^^ െ ^^^ఙ^^^ฮ^ (2)and ^^ఈand ^^ఏare the weights to the regression loss terms associated with magnitude and angle, respectively. With the bipartite matching results, the training objective is as follows, ℒ^୰ୟ୧୬^ఏ,ఈ,^^,ఏ^^∗^^^,ఈ^^∗^^^,^^^∗^^^,^, (3)

[0101] In somesuch that given ^^ predicted targets ൫^^^^ , ^^^^ ,^^^^൯ for ^^ ൌ 1, 2, …^^, the predictions with lowAttorney Docket No. MOTN.155WO / I2024026 probability, or confidence level, are first filtered out by confidence thresholds. Then the predictions that are within ±0.5 deg error with any of the N ground truth targets^^^^,^^^^for ^^ ൌ 1, 2, …^^ are considered as True Positive (TP). The predictions with no matchingground truth are considered as False Positive (FP), and the ground truth targets with no matching predictions are considered as False Negative (FN).

[0102] In some cases, training data may be generated synthetically. Generation of synthetic data can enable an unlimited supply of training data. This can reduce a performance gap between training and validation sets, and can lead to improved generalization performance on data from real radar sensors. For example, for a training sample, a number of targets may first be sampled uniformly as ^^~^^^0,^^୫ୟ^^, where ^^୫ୟ^is the maximum number of targets. In some cases, the maximum number of targets in the generation that balance the design of the array and the complexity of the real-world driving scenario may be chosen. In some cases, for generalization purposes, the angle ^^ and magnitude ^^ of each target may be uniformly sampled as ^^~^^^^^୫୧୬,^^୫ୟ^^and ^^~^^^^^୫୧୬,^^୫ୟ^^.

[0103] As a further example of a radar array with ^^ sensors, when multiple targets are present, the signal received by the ^^-th sensor at time ^^ can be modeled as the sum of the contributions from each target, represented by K targets, as follows: ^^^^^^^ ൌ∑^ ^ୀ^ ^^^^^^ ^^^ െ ^^^,^^^^^^^ ^ ^^^^^^^ where, ^^^^^^^ represents the signal received at the ^^-thof the ^^-th target, ^^^,^^^^^^the delay of the signal from the ^^-th target at the ^^-th sensor, ^^^^^^^represents the noise and interference at the ^^-th sensor, and ^^^^^^ represents the transmitted signal. Additionally, a time delay at each element may be represented as a steering vector for the ^^-th target, ^^^^^^^^, incorporating the angle of arrival ^^^. The steering vector may be determined as follows: ^^^^^^^^ ൌ^ఏ ^ ି^ఠఛ ^ ^ ^ ^் ^^^^^^ି^ఠఛభ,ೖೖ , ^^ మ,ೖ ఏೖ , … , ^^ି^ఠఛಾ,ೖ ఏೖ ൧, where ^^ represents the angular frequency ofarray can be modeled as: ^ ^^^^^^ ^ ^^^^^^ (4)Attorney Docket No. MOTN.155WO / I2024026where: ^^^^^^ ൌ ^^^^^^^^, ^^ଶ^^^^, … , ^^^^^^^^், ^^^^^^ represents a matrix with columns as steeringvectors for different angles, ^^^^^^ represents the source signals at time ^^, and ^^^^^^ represents the noise and interference vector on the sensors. Example Object Detection

[0104] FIGS.6A and 6B illustrate an example scene observed by a vehicle equipped with a MIMO radar array, such as the MIMO radar array 540, and a corresponding tagged radar map of the scene generated based on detections from the MIMO radar array 540 as processed by the radar data processing module 530. In the illustrated example, the environment scanned by the MIMO radar array includes multiple targets, including vehicle 602, vehicle 604, and lamp post 606.

[0105] As part of the radar data processing pipeline, the radar data processing module 530 may generate a range doppler cube (RDC), which may be implemented as a three- dimensional array representing a space-time processing of radar data. In some cases, the radar data processing module 530 may generate an RDC for some or all antennas of the MIMO radar array.

[0106] In the illustrated example, the estimation model 520 can be used to estimate AOA for objects in the environment, including the vehicle 602, the vehicle 604, and the lamp post 606, with respect to the MIMO radar array. In some cases, the perception system 402 can use summation splatting such as that discussed in “Softmax splatting for video frame interpolation” by S. Niklaus and F. Liu. in Proceedings of the IEEE / CVF Conference on Computer Vision And Pattern Recognition, 5437-5446, the entirety of which is incorporated by reference herein, to convert the final set of angle predictions 514 to a range angle doppler cube (RAD) cube. In some cases, an RAD cube may be generated for some all antennas of the MIMO radar array. An RAD cube may be a three- dimensional array representing a radar signal based on range, angle (which may include azimuth and / or elevation), and doppler data of the signal.

[0107] In some embodiments, the radar data processing module 530 may resample the features of the processed RAD cube(s) into BEV space using bi-linear interpolation. For example, the radar data processing module 530 may project one or more features of the RAD cube(s) onto a two-dimensional plane. In some cases, the radar data processingAttorney Docket No. MOTN.155WO / I2024026 module 530 may sum or average values over the doppler dimension of the RAD cube(s), or the other dimensions of the RAD cube(s). In some cases, the radar data processing module 530 may use bi-linear interpolation to obtain a smoother radar image representation. In some cases, maximal magnitude values may be used to obtain BEV features of the environment. Accordingly, the radar data processing module 530 may generate a radar image of the scene illustrated by FIG.6A. The object detector 534 may process the radar image to detect objects in the scene. In some embodiments, the object detector 534 may employ a machine learning model to detect objects in the radar image. For example, the object detector 534 may employ an R-CNN architecture, or may employ a transformer architecture, such as that described in Carion, et. al. In some cases, the object detector 534 may employ other various object detection mechanisms to identify and / or annotate objects in the radar image. In some embodiments, the object detector 534 may annotate the radar image to generate a tagged radar map as illustrated by FIG. 6B. FIG.6B illustrates a tagged radar map generated by the perception system 402 of the scene illustrated in FIG.6A along with ground-truth bounding boxes for the vehicle 602 and the vehicle 604. Example AOA Estimation Process

[0108] FIG. 7 is a flowchart of a process 700 for AOA estimation. In some embodiments, one or more of the steps described with respect to process 700 are performed (e.g., completely, partially, and / or the like) by perception system 402. Although illustrated with specific components, components may be combined, or different components may be used to perform the steps.

[0109] At block 702, perception system 402 can receive a plurality of radar signals from a MIMO radar array, such as the MIMO radar array 540. For example, the perception system 402 may perform operations as described herein with reference to FIG.5. In some embodiments, the MIMO radar array 540 may include multiple receiving and transmitting antennas. The MIMO radar array 540 may be attached to or located on a vehicle, such as the vehicle 200. In some cases, the radar signals may be reflections of outgoing radio signals radiated by any one of the one or more transmitting antennas generated by objects and surfaces in an environment around the vehicle 200.. In some embodiments,Attorney Docket No. MOTN.155WO / I2024026 the vehicle 200 may be configured with multiple MIMO radar arrays 540 positioned at various locations around the vehicle 200, that when combined give the vehicle 200 a 360- degree view of the environment, and enabling detection of objects near (e.g., next to the vehicle) and far away (e.g., 50 meters, 100 meters, 250 meters, etc.).

[0110] At block 704 the perception system 402 may process the plurality of radar signals to generate multiple virtual array signals and virtual array element positions. For example, the perception system 402 may perform operations as described herein with respect to the embedding stage 504 of FIG.5. The perception system 402 may isolate channels between specific transmitting antennas and receiving antennas of the MIMO radar array 540. A virtual array corresponding to the MIMO radar array 540 may have a virtual array element for each transmitter-receiver channel of the MIMO radar array 540. A virtual array signal may correspond to a signal received by a particular virtual array element. Virtual array element positions may correspond to the positions of virtual array elements in the virtual array. The virtual array element positions may be based on the convolution of the positions of the transmitters and receivers of the MIMO radar array 540..

[0111] At block 706, the perception system 402 may generate one or more encoded messages based on the virtual array signals and virtual array element positions using one or more trained transformer encoder blocks. For example, as described herein with respect to FIG.5, during the embedding stage 504, the AOA estimator 502 may project the vectors representing the virtual array signals and virtual array element positions to higher dimensional embedding spaces to generate embedding vectors corresponding to the virtual array signals and virtual array element positions. The perception system 402 may implement various basis expansion techniques, including radial basis function kernels. The embedding vectors may be fed into one or more encoder blocks of the encoder 506. In some cases, one or more of the encoder blocks may comprise an LN module, a multi-head self-attention module, and one or more FFNs. The encoder 506 may implement self-attention mechanisms using the multi-head attention module to generate encoded messages comprising enriched data regarding the virtual array signals, such that data associated with each virtual array signal is enriched with data regarding some or all of the other virtual array signals. The encoder 506 may output encodedAttorney Docket No. MOTN.155WO / I2024026 messages corresponding to output vectors representing the context-enriched input embedding virtual signal array vectors.

[0112] At block 708, the perception system 402 may generate one or more decoded messages based on the one or more encoded messages using one or more trained decoder blocks and a plurality of angle queries 516. In some cases, one or more of the decoder blocks may comprise an LN module, a multi-head self-attention module, a multi- head cross-attention module, and one or more FFNs. For example, as described herein with respect to FIG.5, the angle queries 516 may be used as inputs for the multi-head self-attention module. The multi-head self-attention module may implement self-attention mechanisms to enrich the inputs and generate an output vector corresponding to a set of context enriched angle queries. The multi-head cross attention module, may take as input, the output vector from the multi-head self-attention module, the encoded messages output by the encoder 506, and the positional encodings associated with the virtual array element positions. the decoder 508 may then further enrich the set of angle queries 516 using the enriched virtual signal data corresponding to the encoded messages generated by the encoder 506. The decoder 508 may output decoded messages corresponding to angle query output vectors 518.

[0113] At block 710, the perception system 402 may map the one or more decoded messages to one or more estimation outputs. For example, as described herein with respect to FIG.5, the prediction heads 510 may process the decoded messages, such as by using a FFN, to associate an estimated angle, magnitude, and confidence level with each decoded message. The estimated angle may correspond to an estimated azimuth of a radar detection. The estimated magnitude may correspond to an estimated reflectivity of a target or signal strength associated with a radar detection. The confidence level may correspond to a confidence level that a radar detection is a true positive detection of a target. In some embodiments, the AOA may further process the outputs of the prediction heads 510 generate a final set of angle predictions 514 which satisfy a confidence threshold.

[0114] At block 712, the perception system 402 may generate a set of object detections based on the one or more estimation outputs. For example, as described herein with respect to FIGS.5 and 6, the AOA estimator 502 may be part of a radar dataAttorney Docket No. MOTN.155WO / I2024026 processing module 530, which may implement a radar data processing pipeline to generate a radar image of the environment around the vehicle 200. For example, the radar data processing module 530 may generate a range-doppler cube based on radar data of a scene. The radar data processing module 530 may use the estimation outputs to generate a range angle doppler cube. The radar data processing module 530 may then resample the features of the processed RAD cube(s) into BEV space using bi-linear interpretation. In some cases, maximal magnitude values may be used to obtain BEV features of the environment. The object detector 534 may process the radar image generated by the radar data processing module 530 and to identify objects in the environment. In some cases, the object detector 534 may employ a machine-learning model or other methods to detect objects in the radar image. At block 714, the autonomous system 202 may navigate a vehicle based on the set of object detections. For example, the planning system 404 may use the set of object detections during route planning to determine a route for a vehicle to a destination. The autonomous system 202 may cause the vehicle to navigate the route to the destination based on operations performed by the control system 408.

[0115] In some cases, the perception system 402 may be configured to generate a radar image based on the radar signals received at block 702. For example, the 402 may generate an RAD cube for each antenna of the MIMO radar array and may resample features of the RAD cubes into BEV space using bi-linear interpretation.

[0116] In the foregoing description, aspects and embodiments of the present disclosure have been described with reference to numerous specific details that can vary from implementation to implementation. Accordingly, the description and drawings are to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the invention, and what is intended by the applicants to be the scope of the invention, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent correction. Any definitions expressly set forth herein for terms contained in such claims shall govern the meaning of such terms as used in the claims. In addition, when we use the term “further comprising,” in the foregoing description or followingAttorney Docket No. MOTN.155WO / I2024026 claims, what follows this phrase can be an additional step or entity, or a sub-step / sub- entity of a previously-recited step or entity.

Claims

Attorney Docket No. MOTN.155WO / I2024026 WHAT IS CLAIMED IS:

1. A method, comprising: receiving a plurality of radar signal from a multiple-input-multiple-output (MIMO) radar array, the MIMO radar array comprising a plurality of antennas; generating a plurality of virtual array signals and a plurality of virtual array element positions using the plurality of radar signals and a relative position of the plurality of antennas; generating a plurality of encoded messages from the plurality of virtual array signals and the plurality of virtual array positions using a plurality of trained transformer encoder blocks; generating a plurality of decoded messages from the plurality encoded messages using a using at least one trained transformer decoder block and a plurality of angle queries; generating a plurality of estimation outputs based on the decoded messages, wherein a first estimation output of the plurality of estimation outputs comprises an estimated angle of arrival of a target, an estimated amplitude of the target, and a confidence level; and navigating a vehicle based on the estimation outputs.

2. The method of claim 1, wherein a first encoder block of the plurality of trained transformer encoder blocks comprises a layer normalization module, a multi-head self-attention module, and one or more feed-forward networks.

3. The method of claim 1, wherein the at least one trained transformer decoder block comprises a layer normalization module, a multi-head cross-attention module, and one or more feed-forward networks.

4. The method of claim 3, wherein the mapping is performed using the or one or more feed-forward networks.

5. The method of claim 1, wherein the angle queries correspond to a set of angle proposals associated with a plurality of angles corresponding to signals transmitted by the MIMO radar array.Attorney Docket No. MOTN.155WO / I2024026 6. The method of claim 1, wherein generating the plurality of estimation outputs comprises: processing the decoded messages to determine for one or more of the decoded messages an estimated angle of arrival of a target, an estimated amplitude of the target, and a confidence level; and discarding one or more estimation outputs that fail to satisfy a confidence threshold.

7. The method of claim 1, further comprising: generating, based on the plurality of estimation outputs a range angle doppler cube; generating a radar image by projecting one or more features of the range angle doppler cube onto a two-dimensional plane using bi-linear interpolation.

8. The method of claim 7, further comprising generating a tagged radar map based on the radar image, where in the tagged radar map includes identifiers indicative of one or more objects in the radar image.

9. The method of claim 1, wherein the machine learning model is trained using a synthetic training data set.

10. The method of claim 9, wherein the synthetic training data set comprises one or more uniformly sampled targets, wherein each target is associated with an angle and a magnitude.

11. A system, comprising: at least one processor; and at least one non-transitory storage media storing instructions that, when executed by the at least one processor, cause the at least one processor to: receive a plurality of radar signal from a multiple-input-multiple- output (MIMO) radar array, the MIMO radar array comprising a plurality of antennas; generate a plurality of virtual array signals and a plurality of virtual array element positions using the plurality of radar signals and a relative position of the plurality of antennas;Attorney Docket No. MOTN.155WO / I2024026 generate a plurality of encoded messages from the plurality of virtual array signals and the plurality of virtual array positions using a plurality of trained transformer encoder blocks; generate a plurality of decoded messages from the plurality encoded messages using a using at least one trained transformer decoder block and a plurality of angle queries; generate a plurality of estimation outputs based on the decoded messages, wherein a first estimation output of the plurality of estimation outputs comprises an estimated angle of arrival of a target, an estimated amplitude of the target, and a confidence level; and navigate a vehicle based on the estimation outputs.

12. The system of claim 11, wherein a first encoder block of the plurality of trained transformer encoder blocks comprises a layer normalization module, a multi-head self-attention module, and one or more feed-forward networks.

13. The system of claim 11, wherein the at least one trained transformer decoder block comprises a layer normalization module, a multi-head cross-attention module, and one or more feed-forward networks.

14. The system of claim 13, wherein the mapping is performed using the or one or more feed-forward networks.

15. The system of claim 11, wherein the angle queries correspond to a set of angle proposals associated with a plurality of angles corresponding to signals transmitted by the MIMO radar array.

16. The system of claim 11, wherein to generate the plurality of estimation outputs, the instructions, when executed by the at least one processor, cause the at least one processor to: process the decoded messages to determine for one or more of the decoded messages an estimated angle of arrival of a target, an estimated amplitude of the target, and a confidence level; and discard one or more estimation outputs that fail to satisfy a confidence threshold.Attorney Docket No. MOTN.155WO / I2024026 17. The system of claim 11, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to: generate, based on the plurality of estimation outputs a range angle doppler cube; generate a radar image by projecting one or more features of the range angle doppler cube onto a two-dimensional plane using bi-linear interpolation.

18. The system of claim 17, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to generate a tagged radar map based on the radar image, where in the tagged radar map includes identifiers indicative of one or more objects in the radar image.

19. The system of claim 11, wherein the machine learning model is trained using a synthetic training data set.

20. A non-transitory storage media storing instructions that, when executed by at least one processor, cause the at least one processor to: receive a plurality of radar signal from a multiple-input-multiple-output (MIMO) radar array, the MIMO radar array comprising a plurality of antennas; generate a plurality of virtual array signals and a plurality of virtual array element positions using the plurality of radar signals and a relative position of the plurality of antennas; generate a plurality of encoded messages from the plurality of virtual array signals and the plurality of virtual array positions using a plurality of trained transformer encoder blocks; generate a plurality of decoded messages from the plurality encoded messages using a using at least one trained transformer decoder block and a plurality of angle queries; generate a plurality of estimation outputs based on the decoded messages, wherein a first estimation output of the plurality of estimation outputs comprises an estimated angle of arrival of a target, an estimated amplitude of the target, and a confidence level; and navigate a vehicle based on the estimation outputs.

Images