Model hyper-parameter adjustment using vehicle driving context classification

By using machine learning models in autonomous driving systems to dynamically adjust the hyperparameter set based on driving situations, the problem of poor adaptability of driving strategies in the prior art is solved, and driving behavior optimization and computing resource savings in different situations are achieved.

CN118974746APending Publication Date: 2024-11-15QUALCOMM INC
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202380025526.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-22
Filing Date
2023-01-25
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing autonomous driving system is difficult to adapt to and optimize driving strategies when facing different driving situations, resulting in waste of computing resources and suboptimization of behavior.

Method used

By using machine learning models to dynamically adjust the model's hyperparameter set based on vehicle-based driving situation classification, adapting to different driving situations in real time, thereby determining appropriate driving behavior.

Benefits of technology

Scalability and computing resource savings in different driving situations are achieved, driving behavior optimization capabilities of autonomous driving systems are improved, and the need to store and switch multiple models is reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118974746A_ABST
    Figure CN118974746A_ABST
Patent Text Reader

Abstract

In some aspects, a device of a vehicle may obtain information related to an environment in which the vehicle is located. The device may use a machine learning model to determine a driving context of the vehicle based at least in part on the information related to the environment, and to determine a set of hyper-parameters of a model for determining driving behavior of the vehicle based at least in part on the driving context. The device may determine the driving behavior of the vehicle using the model configured with the set of hyper-parameters. The device may cause autonomous operation of the vehicle according to the driving behavior. Numerous other aspects are described.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This patent application claims priority to U.S. non-provisional patent application No. 17 / 655,837, filed on March 22, 2022, entitled “MODEL HYPERPARAMETER ADJUSTMENT USING VEHICLE DRIVING CONTEXT CLASSIFICATION,” which is hereby expressly incorporated herein by reference. Technical Field

[0003] Aspects of the present disclosure relate generally to wireless communications, and to techniques and apparatus for model hyperparameter tuning using vehicle driving context classification. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies that can support communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, time division synchronous code division multiple access (TD-SCDMA) systems, and long term evolution (LTE). LTE / LTE-Advanced is a set of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard promulgated by the Third Generation Partnership Project (3GPP).

[0005] A wireless network may include one or more base stations that support communications for a user equipment (UE) or multiple UEs. A UE may communicate with a base station via downlink communications and uplink communications. A "downlink" (or "DL") refers to the communication link from a base station to a UE, and an "uplink" (or "UL") refers to the communication link from a UE to a base station.

[0006] The above-mentioned multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different UEs to communicate at a city, country, region and / or global level. New Radio (NR), which may be referred to as 5G, is a set of enhancements to the LTE mobile standard promulgated by 3GPP. NR is designed to better integrate with other open standards by improving spectrum efficiency, reducing costs, improving services, utilizing new spectrum, and using orthogonal frequency division multiplexing (OFDM) (CP-OFDM) with cyclic prefix (CP) on the downlink, using CP-OFDM and / or single carrier frequency division multiplexing (SC-FDM) (also known as discrete Fourier transform spread OFDM (DFT-s-OFDM)) on the uplink, as well as supporting beamforming, multiple input multiple output (MIMO) antenna technology and carrier aggregation, so as to better support mobile broadband Internet access. As the demand for mobile broadband access continues to increase, further improvements in LTE, NR and other radio access technologies remain useful. Summary of the invention

[0007] Some aspects described herein relate to a method. The method may include: obtaining, by a device of a vehicle, information related to an environment in which the vehicle is located. The method may include: using a machine learning model by the device: determining a driving context of the vehicle based at least in part on the information related to the environment, and determining a set of hyperparameters of a model for determining a driving behavior of the vehicle based at least in part on the driving context. The method may include: determining, by the device, the driving behavior of the vehicle using the model configured using the set of hyperparameters. The method may include: causing, by the device, autonomous operation of the vehicle according to the driving behavior.

[0008] Some aspects of this document relate to a system for autonomous driving of a vehicle. The system may include a memory and one or more processors coupled to the memory. The one or more processors may be configured to obtain information related to the environment in which the vehicle is located. The one or more processors may be configured to use a machine learning model to determine a driving situation of the vehicle based at least in part on the information related to the environment, and to determine a set of hyperparameters of a model for determining a driving behavior of the vehicle based at least in part on the driving situation. The one or more processors may be configured to determine the driving behavior of the vehicle using the model configured using the hyperparameter set. The one or more processors may be configured to cause the vehicle to operate autonomously according to the driving behavior.

[0009] Some aspects described herein relate to a non-transitory computer-readable medium storing an instruction set by a device. The instruction set, when executed by one or more processors of the device, may cause the device to obtain information related to an environment in which a vehicle is located. The instruction set, when executed by one or more processors of the device, may cause the device to use a machine learning model: determine a driving context of the vehicle based at least in part on the information related to the environment, and determine a set of hyperparameters of a model for determining driving behavior of the vehicle based at least in part on the driving context. The instruction set, when executed by one or more processors of the device, may cause the device to configure the model using the hyperparameter set based at least in part on determining the hyperparameter set.

[0010] Some aspects described herein are directed to an apparatus. The apparatus may include components for obtaining information related to an environment in which a vehicle is located. The apparatus may include components for determining, using a machine learning model, a set of hyperparameters for a model for determining driving behavior of the vehicle based at least in part on the information related to the environment. The apparatus may include components for configuring the model using the set of hyperparameters based at least in part on determining the set of hyperparameters.

[0011] Aspects generally include methods, apparatus, systems, computer program products, non-transitory computer readable media, user equipment, base stations, wireless communication devices and / or processing systems as fully described herein with reference to and as illustrated by the accompanying drawings and description.

[0012] The features and technical advantages of examples according to the present disclosure have been outlined quite extensively above so that the following specific embodiments may be better understood. Additional technical features and advantages will be described below. The disclosed concepts and specific examples may be easily used as a basis for modifying or designing other structures for achieving the same purpose of the present disclosure. Such equivalent constructions do not depart from the scope of protection of the appended claims. The characteristics of the concepts disclosed herein, both in terms of their organization and method of operation, and the associated advantages will be better understood by considering the following description in conjunction with the accompanying drawings. Each of the accompanying drawings is provided for the purpose of illustration and description, and not as a definition of limitations of the claims.

[0013] Although various aspects are described in the present disclosure by the description of some examples, it will be understood by those skilled in the art that such aspects can be implemented in many different arrangements and scenarios. The technology described herein can be implemented using different platform types, devices, systems, shapes, sizes and / or packaging arrangements. For example, some aspects can be implemented via integrated chip implementations or other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchasing equipment, medical equipment, and / or artificial intelligence devices). Various aspects can be implemented in chip-level components, modular components, non-modular components, non-chip-level components, device-level components and / or system-level components. The equipment combined with the various aspects and features described may include additional components and features for implementing and practicing the various aspects claimed and described. For example, the transmission and reception of wireless signals may include one or more components for analog and digital purposes (e.g., hardware components, including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders and / or summers). The various aspects described herein are intended to be practiced in a wide variety of devices, components, systems, distributed arrangements, and / or end-user devices of different sizes, shapes, and configurations. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to be able to understand the above-mentioned features of the present disclosure in detail, a more specific description briefly summarized above may be obtained by reference to various aspects (some of which are illustrated in the accompanying drawings). However, it should be noted that the accompanying drawings illustrate only certain typical aspects of the present disclosure and are therefore not to be considered as limiting the scope thereof, as the specification may admit of other equally effective aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0015] Figure 1 is a diagram illustrating an example of a wireless network according to the present disclosure.

[0016] Figure 2 is a diagram illustrating an example of communication between a base station and a user equipment (UE) in a wireless network according to the present disclosure.

[0017] FIG. 3A to FIG. 3B is a diagram illustrating an example of model hyperparameter adjustment using vehicle driving scenario classification according to the present disclosure.

[0018] Figure 4 is a diagram illustrating an example process associated with model hyperparameter adjustment using vehicle driving context classification according to the present disclosure.

[0019] Figure 5 is a diagram of an example apparatus according to the present disclosure. DETAILED DESCRIPTION

[0020] The various aspects of the present disclosure are described more fully below with reference to the accompanying drawings. However, the present disclosure can be embodied in many different forms, and should not be construed as being limited to any specific structure or function presented throughout the present disclosure. Instead, these aspects are provided so that the present disclosure will be thorough and complete, and the protection scope of the present disclosure will be fully conveyed to those skilled in the art. It should be appreciated by those skilled in the art that the scope of the present disclosure is intended to cover any aspect of the present disclosure disclosed herein, whether it is implemented independently or in combination with any other aspect of the present disclosure. For example, any number of aspects set forth herein may be used to implement a device or practice method. In addition, the scope of the present disclosure is intended to cover such a device or method that is practiced using other structures, functionality, or structure and functionality in addition to or different from the various aspects of the present disclosure set forth herein. It should be understood that any aspect of the present disclosure disclosed herein may be embodied by one or more elements of the claims.

[0021] Several aspects of telecommunication systems will now be presented with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using hardware, software, or a combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0022] Although aspects may be described herein using terminology generally associated with 5G or new radio (NR) radio access technology (RAT), aspects of the present disclosure may be applied to other RATs, such as 3G RAT, 4G RAT, and / or post-5G RATs (e.g., 6G).

[0023] Figure 11 is a diagram illustrating an example of a wireless network 100 according to the present disclosure. The wireless network 100 may be a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network, or may include elements of a 5G (e.g., NR) network and / or elements of a 4G (e.g., Long Term Evolution (LTE)) network, etc. The wireless network 100 may include one or more base stations 110 (shown as BS110a, BS110b, BS110c, and BS110d), a user equipment (UE) 120 or multiple UEs 120 (shown as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other network entities. The base station 110 is an entity that communicates with the UE 120. Base station 110 (sometimes referred to as BS) may include, for example, an NR base station, an LTE base station, a Node B, an eNB (e.g., in 4G), a gNB (e.g., in 5G), an access point, and / or a transmit receive point (TRP). Each base station 110 may provide communication coverage for a particular geographic area. In the Third Generation Partnership Project (3GPP), the term "cell" may refer to a coverage area of ​​a base station 110 and / or a base station subsystem serving the coverage area, depending on the context in which the term is used.

[0024] The base station 110 may provide communication coverage for a macro cell, a pico cell, a femto cell, and / or another type of cell. A macro cell may cover a relatively large geographic area (e.g., a radius of several kilometers) and may allow unrestricted access by a UE 120 with a service subscription. A pico cell may cover a relatively small geographic area and may allow unrestricted access by a UE 120 with a service subscription. A femto cell may cover a relatively small geographic area (e.g., a home) and may allow restricted access by a UE 120 that has an association with the femto cell (e.g., a UE 120 in a closed subscriber group (CSG)). A base station 110 for a macro cell may be referred to as a macro base station. A base station 110 for a pico cell may be referred to as a pico base station. A base station 110 for a femto cell may be referred to as a femto base station or a home base station. In Figure 1 In the example shown in , BS 110a may be a macro base station for macro cell 102a, BS 110b may be a pico base station for pico cell 102b, and BS 110c may be a femto base station for femto cell 102c. A base station may support one or more (eg, three) cells.

[0025] In some examples, the cell may not necessarily be stationary, and the geographic area of ​​the cell may move according to the location of the mobile base station 110 (e.g., a mobile base station). In some examples, the base stations 110 may be interconnected with each other and / or with one or more other base stations 110 or network nodes (not shown) in the wireless network 100 through various types of backhaul interfaces (such as direct physical connections or virtual networks) using any suitable transport network.

[0026] The wireless network 100 may include one or more relay stations. A relay station is an entity that can receive transmissions of data from an upstream station (e.g., a base station 110 or a UE 120) and transmit transmissions of data to a downstream station (e.g., a UE 120 or a base station 110). A relay station may be a UE 120 that is capable of relaying transmissions for other UEs 120. Figure 1 In the example shown in , BS 110d (eg, a relay base station) can communicate with BS 110a (eg, a macro base station) and UE 120d to facilitate communication between BS 110a and UE 120d. Base station 110 that relays communication may be referred to as a relay station, relay base station, relay, or the like.

[0027] The wireless network 100 may be a heterogeneous network that includes different types of base stations 110, such as macro base stations, pico base stations, femto base stations, relay base stations, etc. These different types of base stations 110 may have different transmit power levels, different coverage areas, and / or different impacts on interference in the wireless network 100. For example, a macro base station may have a high transmit power level (e.g., 5 watts to 40 watts), while a pico base station, a femto base station, and a relay base station may have a lower transmit power level (e.g., 0.1 watt to 2 watts).

[0028] A network controller 130 may be coupled to or in communication with a set of base stations 110 and may provide coordination and control for the base stations 110. The network controller 130 may communicate with the base stations 110 via backhaul communication links. The base stations 110 may also communicate directly with each other or indirectly via wireless or wired backhaul communication links.

[0029] UE 120 can be dispersed throughout the wireless network 100, and each UE 120 can be stationary or mobile. UE 120 can include, for example, access terminals, terminals, mobile stations, and / or subscriber units. UE 120 can be a cellular phone (e.g., a smart phone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet computer, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device, a biometric device, a wearable device (e.g., a smart watch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring or a smart bracelet)), an entertainment device (e.g., a music device, a video device, and / or a satellite radio), a vehicle component or sensor, a smart meter / sensor, an industrial manufacturing equipment, a global positioning system device, and / or any other suitable device configured to communicate via a wireless medium.

[0030] Some UEs 120 may be considered as machine type communication (MTC) or evolved or enhanced machine type communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags that may communicate with a base station, another device (e.g., a remote device), or some other entity. Some UEs 120 may be considered as Internet of Things (IoT) devices and / or may be implemented as NB-IoT (narrowband IoT) devices. Some UEs 120 may be considered as customer premises equipment. UE 120 may be included inside a housing that houses components of UE 120, such as a processor component and / or a memory component. In some examples, the processor component and the memory component may be coupled together. For example, a processor component (e.g., one or more processors) and a memory component (e.g., a memory) are operationally coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0031] In general, any number of wireless networks 100 may be deployed in a given geographic area. Each wireless network 100 may support a specific RAT and may operate on one or more frequencies. RAT may be referred to as a radio technology, air interface, etc. Frequency may be referred to as a carrier, frequency channel, etc. Each frequency may support a single RAT in a given geographic area to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks may be deployed.

[0032] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly (e.g., without using base station 110 as an intermediary to communicate with each other) using one or more side link channels. For example, UE 120 may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, or vehicle-to-pedestrian (V2P) protocols), and / or mesh networks. In such examples, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by base station 110.

[0033] The devices of the wireless network 100 may communicate using an electromagnetic spectrum, which may be subdivided into various categories, bands, channels, etc., based on frequency or wavelength. For example, the devices of the wireless network 100 may communicate using one or more operating bands. In 5G NR, two initial operating bands have been identified as frequency ranges designated FR1 (410 MHz–7.125 GHz) and FR2 (24.25 GHz–52.6 GHz). It should be understood that, although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the “below 6 GHz” band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the “millimeter wave” band in documents and articles, although different from the extremely high frequency (EHF) band (30 GHz–300 GHz) identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0034] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125GHz–24.25GHz). The bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, so the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range designations FR4a or FR4-1 (52.6GHz–71GHz), FR4 (52.6GHz–114.25GHz), and FR5 (114.25GHz–300GHz). Each of these higher frequency bands falls within the EHF band.

[0035] Considering the above examples, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used herein, the term may broadly refer to frequencies that may be lower than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" or the like is used herein, the term may broadly refer to frequencies that may include mid-band frequencies, may be within FR2, FR4, FR4-a or FR4-1, and / or FR5, or may be within the EHF band. It is contemplated that the frequencies included in these operating bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1, and / or FR5) may be modified, and the techniques described herein are applicable to those modified frequency ranges.

[0036] In some aspects, UE 120 may include a communication manager 140. As described in more detail elsewhere herein, the communication manager 140 may obtain information related to the environment in which the vehicle is located; use a machine learning model to: determine a driving context of the vehicle based at least in part on the information related to the environment, and determine a set of hyperparameters for a model for determining a driving behavior of the vehicle based at least in part on the driving context; use the model configured with the set of hyperparameters to determine the driving behavior of the vehicle; and cause autonomous operation of the vehicle according to the driving behavior. Additionally or alternatively, the communication manager 140 may perform one or more other operations described herein.

[0037] As indicated above, Figure 1 are provided as examples. Other examples can be found in the Figure 1 Different from what is described.

[0038] Figure 2 2 is a diagram illustrating an example 200 of base station 110 communicating with UE 120 in wireless network 100 according to the present disclosure. Base station 110 may be equipped with a set of antennas 234a to 234t, such as T antennas (T≥1). UE 120 may be equipped with a set of antennas 252a to 252r, such as R antennas (R≥1).

[0039] At the base station 110, the transmit processor 220 may receive data intended for the UE 120 (or a set of UEs 120) from the data source 212. The transmit processor 220 may select one or more modulation and coding schemes (MCS) for the UE 120 based at least in part on one or more channel quality indicators (CQI) received from the UE 120. The base station 110 may process (e.g., encode and modulate) the data for the UE 120 based at least in part on the MCS selected for the UE 120, and provide data symbols for the UE 120. The transmit processor 220 may process system information (e.g., for semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling), and provide overhead symbols and control symbols. The transmit processor 220 may generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS) or demodulation reference signals (DMRS)) and synchronization signals (e.g., primary synchronization signals (PSS) or secondary synchronization signals (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., pre-coding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols, where applicable, and may provide a set of output symbol streams (e.g., T output symbol streams) to a corresponding set of modems 232 (e.g., T modems) (shown as modems 232a to 232t). For example, each output symbol stream may be provided to a modulator component (shown as MOD) of the modem 232. Each modem 232 may process a corresponding output symbol stream (e.g., for OFDM) using a corresponding modulator component to obtain an output sample stream. Each modem 232 may further process (e.g., convert to analog, amplify, filter, and / or up-convert) the output sample stream using a corresponding modulator component to obtain a downlink signal. The modems 232a to 232t may transmit a set of downlink signals (e.g., T downlink signals) via a corresponding set of antennas 234 (e.g., T antennas) (shown as antennas 234a to 234t).

[0040] At the UE 120, a set of antennas 252 (shown as antennas 252a to 252r) may receive downlink signals from the base station 110 and / or other base stations 110 and may provide a set of received signals (e.g., R received signals) to a set of modems 254 (e.g., R modems) (shown as modems 254a to 254r). For example, each received signal may be provided to a demodulator component (shown as DEMOD) of the modem 254. Each modem 254 may use a corresponding demodulator component to condition (e.g., filter, amplify, downconvert, and / or digitize) the received signal to obtain input samples. Each modem 254 may use a demodulator component to further process the input samples (e.g., for OFDM) to obtain received symbols. A MIMO detector 256 may obtain received symbols from the modem 254, may perform MIMO detection on the received symbols where applicable, and may provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, may provide decoded data for the UE 120 to the data sink 260, and may provide decoded control information and system information to the controller / processor 280. The term "controller / processor" may refer to one or more controllers, one or more processors, or a combination thereof. The channel processor may determine a reference signal received power (RSRP) parameter, a received signal strength indicator (RSSI) parameter, a reference signal received quality (RSRQ) parameter, and / or a CQI parameter, among other things. In some examples, one or more components of the UE 120 may be included in the housing 284.

[0041] The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 may include, for example, one or more devices in a core network. The network controller 130 may communicate with the base station 110 via the communication unit 294.

[0042] One or more antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include or be included within one or more antenna panels, one or more antenna groups, one or more sets of antenna elements, and / or one or more antenna arrays, etc. Antenna panels, antenna groups, sets of antenna elements, and / or antenna arrays may include one or more antenna elements (in a single housing or multiple housings), sets of coplanar antenna elements, sets of non-coplanar antenna elements, and / or may be coupled to one or more transmit and / or receive components (such as, Figure 2 One or more antenna elements of one or more components in.

[0043] On the uplink, at the UE 120, the transmit processor 264 may receive and process data from the data source 262 and control information from the controller / processor 280 (e.g., for reports including RSRP, RSSI, RSRQ, and / or CQI). The transmit processor 264 may generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be pre-decoded by the TX MIMO processor 266, where applicable, further processed by the modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to the base station 110. In some examples, the modem 254 of the UE 120 may include a modulator and a demodulator. In some examples, the UE 120 includes a transceiver. The transceiver may include any combination of an antenna 252, a modem 254, a MIMO detector 256, a receive processor 258, a transmit processor 264, and / or a TX MIMO processor 266. The transceiver may be used by a processor (eg, controller / processor 280) and memory 282 to perform aspects of any of the methods described herein (eg, with reference to FIG. 3A to FIG. 3B , Figure 4 and Figure 5 ).

[0044] At the base station 110, uplink signals from the UE 120 and / or other UEs may be received by the antenna 234, processed by the modem 232 (e.g., a demodulator component of the modem 232 shown as DEMOD), detected by the MIMO detector 236 (if applicable), and further processed by the receive processor 238 to obtain decoded data and control information transmitted by the UE 120. The receive processor 238 may provide the decoded data to the data sink 239 and the decoded control information to the controller / processor 240. The base station 110 may include a communication unit 244 and may communicate with the network controller 130 via the communication unit 244. The base station 110 may include a scheduler 246 to schedule one or more UEs 120 for downlink and / or uplink communications. In some examples, the modem 232 of the base station 110 may include a modulator and a demodulator. In some examples, the base station 110 includes a transceiver. The transceiver may include any combination of an antenna 234, a modem 232, a MIMO detector 236, a receive processor 238, a transmit processor 220, and / or a TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein (e.g., reference 200 to FIG. 1 ). FIG. 3A to FIG. 3B , Figure 4 and Figure 5 ).

[0045] The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other components of may perform one or more techniques associated with model hyperparameter adjustment using vehicle driving scenario classification, as described in more detail elsewhere herein. In some aspects, the system for autonomous driving is UE 120, is included in UE 120, or includes Figure 2 One or more components of the UE 120 are shown. The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other component of the Figure 4 400 and / or operations of other processes as described herein. Memory 242 and memory 282 may store data and program codes for base station 110 and UE 120, respectively. In some examples, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, one or more instructions, when executed by one or more processors of base station 110 and / or UE 120 (e.g., directly executed, or executed after compilation, conversion, and / or interpretation), may cause one or more processors, UE 120, and / or base station 110 to perform or direct, for example, Figure 4 The process 400 and / or operations of other processes as described herein. In some examples, executing instructions may include running instructions, converting instructions, compiling instructions, and / or interpreting instructions, etc.

[0046] In some aspects, a system for autonomous driving includes: a component for obtaining, by a device of a vehicle, information related to an environment in which the vehicle is located; a component for using a machine learning model by the device to perform the following operations: determining a driving context of the vehicle based at least in part on the information related to the environment, and determining a set of hyperparameters for a model for determining a driving behavior of the vehicle based at least in part on the driving context; a component for determining the driving behavior of the vehicle by the device using a model configured with a set of hyperparameters; and / or a component for causing the vehicle to autonomously operate according to the driving behavior by the device. In some aspects, the components for the device to perform the operations described herein may include, for example, one or more of the communication manager 140, the antenna 252, the modem 254, the MIMO detector 256, the receive processor 258, the transmit processor 264, the TX MIMO processor 266, the controller / processor 280, or the memory 282.

[0047] Although Figure 2The blocks in the 200 and 210 are illustrated as distinct components, but the functionality described above for these blocks may be implemented in a single hardware, software, or combined component or in various combinations of components. For example, the functionality described with respect to the transmit processor 264, the receive processor 258, and / or the TX MIMO processor 266 may be performed by or under the control of the controller / processor 280.

[0048] As indicated above, Figure 2 are provided as examples. Other examples can be found in the Figure 2 Different from what is described.

[0049] An autonomous driving system for a vehicle (e.g., an advanced driver assistance system (ADAS)) may perform three main operations: sensing, planning (e.g., what the vehicle is to do), and action. Planning operations (e.g., behavior planning) may include a driving strategy for the vehicle. One challenge of an autonomous driving system is generalizing behavior for different scenarios. For example, the parameters of a driving strategy in a free-flowing highway scenario may be different from the parameters of a driving strategy at an intersection in a dense urban scenario. Using independent driving strategies for different driving scenarios (e.g., highways, parking lots, or intersections) lacks scalability and consumes excessive computing resources.

[0050] An autonomous driving system for a vehicle may use a model based on a scalable global planner algorithm (such as a Monte Carlo Tree Search (MCTS) algorithm or another search algorithm) to determine a driving policy for the vehicle that maximizes a reward function. The model may be initialized with a set of hyperparameters (e.g., in the case of MCTS, tree width, tree depth, time step resolution, etc.) that are static across the use of the model in various driving scenarios. Therefore, the model may not be able to adapt to different driving scenarios and may result in sub-optimal autonomous operation of the vehicle. In addition, as described above, using multiple models with different sets of hyperparameters for each driving scenario lacks scalability to new driving scenarios and consumes excessive computing resources in conjunction with storing multiple models, switching between multiple models, and updating multiple models.

[0051] Some techniques and devices described herein provide an autonomous driving system in which the hyperparameters of a model (e.g., an MCTS model) that determines the driving behavior of a vehicle can be adjusted based on the driving scenario classification of the vehicle (e.g., highway classification, parking lot classification, intersection classification, etc.). In some aspects, the autonomous driving system can use a machine learning model such as a neural network to determine a set of hyperparameters for the model based on the driving scenario classification of the vehicle. For example, if the vehicle is in a parking lot, the hyperparameters determined by the machine learning model for the model can affect the model to quickly determine the driving behavior. For another example, if the vehicle is on a free-flowing highway, the hyperparameters determined by the machine learning model for the model can affect the model to determine the driving behavior further into the future.

[0052] Inputs to the machine learning model may include information related to an environmental model for the vehicle (e.g., a model of objects around the vehicle based on sensor data of the vehicle) and / or predictions of the vehicle's intent (e.g., predictions related to the next movement of objects in the vehicle's environment). In some aspects, the machine learning model may be trained to identify various driving scenarios (e.g., highways, parking lots, intersections, etc.), and determine a set of hyperparameters for the model (e.g., tree width, tree depth, etc.) based on the driving scenarios. In some other aspects, the machine learning model may receive information indicating the driving scenario of the vehicle as input (e.g., from another machine learning model), and the machine learning model may be trained to determine a set of hyperparameters for the model based on the driving scenarios. In some aspects, the machine learning model may be trained end-to-end with a model in a training loop (e.g., an MCTS model).

[0053] In this way, the autonomous driving system can adjust the hyperparameters used by the model based at least in part on the driving context of the vehicle. Therefore, the hyperparameters can be adjusted in real time or near real time to adapt to the current driving context of the vehicle. Therefore, the model used to determine the driving behavior can be scaled across various driving contexts that the vehicle may encounter, and can be extended to new driving contexts. Therefore, the autonomous driving system can use a single model to determine the appropriate driving behavior of the vehicle across various driving contexts, thereby saving computing resources that might otherwise be spent on storing multiple models, switching between multiple models, and updating multiple models.

[0054] FIG. 3A to FIG. 3B300 is a diagram illustrating an example of model hyperparameter adjustment using vehicle driving context classification according to the present disclosure. As shown, example 300 may include a vehicle 305 that includes a system 310 for autonomous driving. Vehicle 305 may be a car, a bus, a truck, a work machine (e.g., a tractor, a bulldozer, etc.), etc. System 310 may include one or more computing devices. In some aspects, system 310 may be or may include UE 120.

[0055] The system 310 may implement a machine learning model 312 that is trained to determine a set of hyperparameters for a model 314 for determining driving behavior of the vehicle 305. For example, the machine learning model 312 may be trained to determine the set of hyperparameters based at least in part on a driving context of the vehicle 305, as described herein. In particular, the machine learning model 312 may be trained to determine the set of hyperparameters based at least in part on input of environmental information associated with the vehicle 305 (e.g., camera data, light detection and ranging (LIDAR) data, etc.). In some aspects, the machine learning model 312 may be a neural network (e.g., a feed-forward neural network, a convolutional neural network, etc.).

[0056] In some aspects, the system 310 may train a machine learning model 312. The system 310 may train the machine learning model 312 alone or in collaboration with similar systems of one or more other vehicles (e.g., using distributed learning, federated learning, etc.). In some other aspects, the system 310 may receive a trained machine learning model 312 from another device or may be otherwise provided with a trained machine learning model 312. In some aspects, the machine learning model 312 may be trained using reinforcement learning techniques. The training data for the machine learning model 312 may include environmental information of the vehicle, such as camera data, lidar data, etc. In addition, the machine learning model 312 may be trained based at least in part on the output of the model 314 (e.g., the loss function used to train the machine learning model 312 may be based at least in part on the output of the model 314).

[0057] In practice, the vehicle 305 may be located in an environment that includes one or more objects. For example, the objects may include one or more other vehicles and / or one or more pedestrians, etc. Figure 3AAs shown, and by reference numeral 315, system 310 may obtain information related to the environment in which vehicle 305 is located (e.g., obtain an environment model) (referred to herein as "environmental information"). For example, system 310 may obtain environmental information from one or more sensors of vehicle 305. The one or more sensors may include one or more LIDAR systems of vehicle 305, one or more cameras of vehicle 305, and / or one or more radio detection and ranging (RADAR) systems of vehicle 305, etc. In some aspects, environmental information may include location data associated with vehicle 305, map data associated with the location of vehicle 305, traffic data associated with vehicle 305, condition data associated with the location of vehicle 305 (e.g., weather data, crash data, lane closure data, etc.), etc. System 310 may obtain location data from sensors of vehicle 305 (e.g., a global navigation satellite system (GNSS) of vehicle 305, such as a global positioning system (GPS) of vehicle 305). System 310 may obtain map data, traffic data, and / or condition data from a storage system of vehicle 305, from another vehicle (e.g., using V2X communication on a sidelink), from a server device (e.g., via communication using wireless network 100), and the like.

[0058] As shown by reference numeral 320, system 310 may determine one or more intent predictions. One or more intent predictions may be associated with one or more objects in the environment of vehicle 305 (e.g., other vehicles, pedestrians, animals, etc.). System 310 may identify one or more objects from environmental information (e.g., using computer vision techniques, object detection techniques, etc.). System 310 may use different machine learning models to determine one or more intent predictions. The intent prediction for an object may be a prediction of the future movement of the object (e.g., direction of movement, speed of movement, etc.).

[0059] As shown by reference numeral 325, the system 310 can provide context information and / or one or more intent predictions (e.g., as input) to the machine learning model 312. As shown, the system 310 can implement the machine learning model 312. However, in some aspects, the machine learning model 312 can be implemented by a remote device from the system 310 (e.g., by a remote server device, by a cloud computing environment, by a roadside unit, etc.). Here, in order to provide the context information and / or intent predictions to the machine learning model 312, the system 310 can send the context information and / or intent predictions to the remote device (e.g., via the wireless network 100).

[0060] like Figure 3BAnd as indicated by reference numeral 330, system 310 may determine a set of hyperparameters for model 314. System 310 may determine a set of hyperparameters for model 314 based at least in part on environmental information and / or intent prediction. In particular, system 310 may determine a set of hyperparameters for model 314 based at least in part on a driving context of the vehicle indicated by environmental information and / or intent prediction. Thus, system 310 may determine a first set of hyperparameters for model 314 in response to a first driving context, system 310 may determine a second set of hyperparameters for model 314 in response to a second driving context, and so on. For example, for a highway driving context, system 310 may determine a relatively large tree depth for model 314, and for a parking lot context, system 310 may determine a relatively small tree depth for model 314.

[0061] In some aspects, the system 310 may continuously (e.g., at the same frequency as the model 314 determines the driving behavior) determine the set of hyperparameters for the model 314. In some aspects, the system 310 may periodically (e.g., at a frequency slower than the model 314 determines the driving behavior) determine the set of hyperparameters for the model 314. In some aspects, the system 310 may determine the set of hyperparameters for the model 314 based at least in part on detecting the occurrence of an event. For example, the system 310 may determine the set of hyperparameters for the model 314 based at least in part on detecting (e.g., using a machine learning model trained to perform driving context classification, as described herein) that the driving context of the vehicle 305 has changed. In some aspects, the system 310 may store information indicating the route that the vehicle 305 will take. Here, the system 310 may determine the location where the driving context of the vehicle 305 will change based at least in part on the route, and the system 310 may determine the set of hyperparameters when the vehicle 305 is at or approaching the location where the driving context of the vehicle will change.

[0062] The system 310 may use the machine learning model 312 to determine a set of hyperparameters for the model 314. For example, the system 310 using the machine learning model 312 may determine a driving context (e.g., a driving context classification) of the vehicle 305 based at least in part on the environmental information and / or the intent prediction, and determine a set of hyperparameters for the model 314 based at least in part on the driving context. In other words, the machine learning model 312 may output a set of hyperparameters for the model 312 in response to the input of the machine learning model 314 by the environmental information and / or the intent prediction.

[0063] In some aspects, the machine learning model 312 may be trained to determine a set of hyperparameters based at least in part on a set of features related to the characteristics of the environmental information and / or the intent prediction (e.g., the set of features may include the number of objects in the environment, the distance of the objects in the environment from the vehicle 305, the speed of the objects in the environment, the orientation of the objects in the environment relative to the vehicle 305, the movement of the objects in the environment relative to the vehicle 305, the configuration of one or more roads in the environment, the traffic signals in the environment, and / or the traffic signs in the environment, etc.). In some aspects, the machine learning model 312 is trained to determine the driving situation classification based at least in part on a set of features related to the characteristics of the environmental information and / or the intent prediction, and the machine learning model 312 may be trained to determine the set of hyperparameters based at least in part on the driving situation classification and / or the intent prediction. In some aspects, the system 310 using different machine learning models may determine the driving situation classification based at least in part on the environmental information and / or the intent prediction, and the machine learning model 312 may be trained to determine the set of hyperparameters based at least in part on the driving situation classification and / or the intent prediction. In some aspects, system 310 can determine a driving situation classification, as described herein, and system 310 can use a mapping of driving situation classification to a set of hyperparameters (e.g., stored by system 310) in order to determine the set of hyperparameters. In some aspects, system 310 can determine a driving situation classification based at least in part on information indicating a route to be taken by vehicle 305, as described herein.

[0064] The driving context may be related to a current driving scenario in which the vehicle 305 is involved. For example, the driving context may be related to the type of road on which the vehicle 305 is traveling, the type of intersection that the vehicle 305 is approaching, the driving maneuver that the vehicle 305 is performing, etc. For example, the driving context may be an intersection context, a traffic signal context, a highway context, a local road context, a one-way road context, a parking lot context, a parking context, a parallel parking context, or a merging context, etc. In some aspects, the set of hyperparameters determined by the system 310 based at least in part on the driving context may include (e.g., for a heuristic search algorithm) a tree width, a tree depth, a time length of a step in the tree, a reward function and / or a range of an action space, etc.

[0065] In some aspects, the system 310 may use the collaboration between the vehicle 305 and one or more different vehicles to determine the set of hyperparameters. In particular, a vehicle that arrives at a location or area associated with a particular driving scenario may determine the hyperparameters based at least in part on the driving scenario, as described herein, and the vehicle may send information indicating the determined hyperparameters to one or more neighboring vehicles (e.g., in particular, neighboring vehicles that will arrive at the location or area). The information may also indicate a feedback value (e.g., a loss function value, a reward function value, etc.) that quantifies the accuracy and / or optimality associated with the driving behavior determined at least in part by the vehicle based on the hyperparameters, as described herein. For example, the system 310 may (e.g., using V2X communication on a side link) receive information and / or feedback values ​​indicating the hyperparameters determined at different vehicles for a particular location or area. Continuing with this example, the system 310 may use the hyperparameters determined at different vehicles, or the system 310 may determine the set of hyperparameters based at least in part on the hyperparameters and / or feedback values ​​determined at different vehicles (e.g., using a machine learning model 312). For example, hyperparameters and / or feedback values ​​determined at different vehicles can be additional inputs to the machine learning model 312. In this way, the vehicles can collaborate to facilitate improved hyperparameter determination over time.

[0066] As shown by reference numeral 335, the system 310 may configure the model 314 with a set of hyperparameters. That is, the system 310 may initialize the model 314 with the set of hyperparameters. In some aspects, the model 314 may be based at least in part on a heuristic search algorithm (e.g., a scalable global planner algorithm). For example, the model 314 may be based at least in part on MCTS. That is, the model 314 may employ the MCTS algorithm.

[0067] As shown by reference numeral 340, the system 310 may determine the driving behavior (e.g., driving strategy) of the vehicle 305. For example, the system 310 may determine the driving behavior of the vehicle 305 using a model 314 configured using a set of hyperparameters. As an example, the system 310 may determine the driving behavior by executing an MCTS algorithm with respect to a set of hyperparameters (e.g., by executing an MCTS algorithm using a specific tree width indicated by a set of hyperparameters, using a specific tree depth indicated by a set of hyperparameters, etc.). The model 314 may be configured to output the driving behavior in response to input information such as environmental information (e.g., an environmental model), an intention prediction, etc. In addition, the system 310 may determine the driving behavior using the model 314 so as to maximize the reward function of the model 314. The driving behavior may be related to the action of the vehicle 305 (e.g., braking, acceleration, steering, etc.), the speed of the vehicle 305, and / or the path of the vehicle 305.

[0068] As shown at reference numeral 345, system 310 may cause autonomous operation (e.g., operation without human input) of vehicle 305 in accordance with the driving behavior. For example, system 310 may cause one or more systems (e.g., steering system, propulsion system, braking system, etc.) of vehicle 305 to perform one or more operations in accordance with the driving behavior.

[0069] In this way, model 314 can determine appropriate driving behavior for different driving scenarios. In particular, model 314 can be adapted to different driving scenarios by adjusting a set of hyperparameters used by model 314 using machine learning model 312, as described herein. Therefore, model 314 can provide the same functionality as multiple different models that are separately configured to handle different driving scenarios. Therefore, system 310 promotes the scalability of model 114 to different driving scenarios and saves computing resources that might otherwise be spent on storing multiple different models, switching between multiple different models, and updating multiple different models.

[0070] As indicated above, FIG. 3A to FIG. 3B are provided as examples. Other examples can be found in relation to FIG. 3A to FIG. 3B Different from what is described.

[0071] Figure 4 4 is a diagram illustrating an example process 400, for example, performed by a device according to the present disclosure. The example process 400 is an example in which a device (eg, system 310, UE 120, etc.) uses vehicle driving context classification to perform operations associated with model hyperparameter adjustment.

[0072] like Figure 4 As shown, in some aspects, process 400 may include obtaining information related to the environment in which the vehicle is located (block 410). For example, a device (e.g., using Figure 5 The depicted communications manager 508 and / or sensing component 510) may obtain information related to the environment in which the vehicle is located, as described above.

[0073] like Figure 4 As further shown, in some aspects, process 400 may include: using a machine learning model: determining a driving context of a vehicle based at least in part on information related to the environment, and determining a set of hyperparameters of a model for determining a driving behavior of the vehicle based at least in part on the driving context (block 420). For example, a device (e.g., using Figure 5 The depicted communication manager 508 and / or determination component 512) may use a machine learning model to: determine a driving context of a vehicle based at least in part on information related to the environment, and determine a set of hyperparameters for a model for determining the driving behavior of the vehicle based at least in part on the driving context, as described above.

[0074] like Figure 4 As further shown, in some aspects, process 400 may include: using a model configured using a set of hyperparameters to determine a driving behavior of a vehicle (block 430). Figure 5 The depicted communication manager 508 and / or determination component 512) can determine the driving behavior of the vehicle using a model configured using a set of hyperparameters, as described above.

[0075] like Figure 4 As further shown, in some aspects, process 400 may include causing the vehicle to operate autonomously based on the driving behavior (block 440). Figure 5 The depicted communication manager 508 and / or action component 514) may cause autonomous operation of the vehicle based on driving behavior, as described above.

[0076] Process 400 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other processes described elsewhere herein.

[0077] In a first aspect, the model is based at least in part on a heuristic search algorithm.

[0078] In a second aspect, either alone or in combination with the first aspect, the model is based at least in part on a Monte Carlo tree search.

[0079] In a third aspect, alone or in combination with one or more of the first and second aspects, the set of hyperparameters includes at least one of a tree width, a tree depth, a time length of a step in the tree, or a reward function.

[0080] In a fourth aspect, either alone or in combination with one or more of the first to third aspects, the machine learning model is a neural network trained to determine hyperparameters of the model based at least in part on the driving context.

[0081] In a fifth aspect, alone or in combination with one or more of the first to fourth aspects, the driving context of the vehicle is an intersection context, a highway context, a local road context, or a parking lot context.

[0082] In a sixth aspect, alone or in combination with one or more of the first to fifth aspects, the information related to the environment is obtained from one or more sensors of the vehicle.

[0083] In a seventh aspect, either alone or in combination with one or more of the first to sixth aspects, the one or more sensors include one or more of a light detection and ranging system or a camera.

[0084] In an eighth aspect, alone or in combination with one or more of the first to seventh aspects, the driving behavior is determined to maximize a reward function of the model.

[0085] In a ninth aspect, either alone or in combination with one or more of aspects one to eight, process 400 includes determining one or more intention predictions associated with one or more objects in an environment, wherein at least one of the driving scenarios or hyperparameter sets is further determined at least in part based on the one or more intention predictions.

[0086] In a tenth aspect, alone or in combination with one or more of the first to ninth aspects, process 400 includes: configuring a model using a set of hyperparameters based at least in part on determining the set of hyperparameters.

[0087] although Figure 4 An example block diagram of process 400 is shown, but in some aspects, process 400 may include Figure 4 The depicted blocks may include additional blocks, fewer blocks, different blocks, or blocks arranged in a different manner. Additionally or alternatively, two or more of the blocks of process 400 may be performed in parallel.

[0088] Figure 5 5 is a diagram of an example apparatus 500. Apparatus 500 may be a system for autonomous driving, or a system for autonomous driving may include apparatus 500. In some aspects, apparatus 500 includes a receiving component 502 and a sending component 504 that may communicate with each other (e.g., via one or more buses and / or one or more other components). As shown, apparatus 500 may communicate with another apparatus 506 (such as a UE, a base station, or another wireless communication device) using receiving component 502 and sending component 504. As further shown, apparatus 500 may include a communication manager 508. Communication manager 508 may be, may include, or may be similar to communication manager 140. Communication manager 508 may include one or more of sensing component 510, determining component 512, or action component 514, etc.

[0089] In some aspects, the apparatus 500 may be configured to perform FIG. 3A to FIG. 3B Additionally or alternatively, the apparatus 500 may be configured to perform one or more of the processes described herein (such as Figure 4 In some aspects, the apparatus 500 and / or Figure 5 One or more of the components shown may include a combination of Figure 2 Additionally or alternatively, Figure 5 One or more of the components shown may be combined with Figure 2Additionally or alternatively, one or more of the set of components may be implemented at least in part as software stored in a memory. For example, a component (or a portion of a component) may be implemented as instructions or codes stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0090] The receiving component 502 may receive communications, such as reference signals, control information, data communications, or combinations thereof, from the device 506. The receiving component 502 may provide the received communications to one or more other components of the device 500. In some aspects, the receiving component 502 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications and may provide the processed signals to one or more other components of the device 500. In some aspects, the receiving component 502 may include combining Figure 2 One or more antennas, modems, demodulators, MIMO detectors, receive processors, controllers / processors, memories, or combinations thereof of the system.

[0091] Transmit component 504 may transmit communications, such as reference signals, control information, data communications, or combinations thereof, to device 506. In some aspects, one or more other components of device 500 may generate communications and may provide the generated communications to transmit component 504 for transmission to device 506. In some aspects, transmit component 504 may perform signal processing (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding) on ​​the generated communications and may transmit the processed signals to device 506. In some aspects, transmit component 504 may include combining Figure 2 One or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memories, or combinations thereof of the system. In some aspects, the transmit component 504 can be co-located with the receive component 502 in a transceiver.

[0092] The sensing component 510 may obtain information related to the environment in which the vehicle is located. The determination component 512 may use a machine learning model to determine the driving context of the vehicle based at least in part on the information related to the environment, and to determine a set of hyperparameters of a model for determining the driving behavior of the vehicle based at least in part on the driving context. The determination component 512 may determine the driving behavior of the vehicle using a model configured using the set of hyperparameters. The action component 514 may cause the vehicle to operate autonomously according to the driving behavior.

[0093] The determination component 512 can determine one or more intent predictions associated with one or more objects in the environment. In some aspects, at least one of the driving scenario or the set of hyperparameters is further determined based at least in part on the one or more intent predictions. The determination component 512 can configure the model using the set of hyperparameters based at least in part on determining the set of hyperparameters.

[0094] Figure 5 The number and arrangement of components shown are provided as examples. In practice, there may be Figure 5 Additional components, fewer components, different components, or components arranged in a different manner than those shown. Figure 5 Two or more components shown may be implemented in a single component, or Figure 5 The single component shown may be implemented as multiple distributed components. Additionally or alternatively, Figure 5 The component set (one or more components) shown may be described as being executable by Figure 5 Another set of components shown performs one or more functions.

[0095] The following provides an overview of some aspects of the disclosure:

[0096] Aspect 1: A method, comprising: obtaining, by a device of a vehicle, information related to an environment in which the vehicle is located; using a machine learning model by the device: determining a driving scenario of the vehicle based at least in part on the information related to the environment, and determining a set of hyperparameters of a model for determining a driving behavior of the vehicle based at least in part on the driving scenario; using the model configured using the set of hyperparameters by the device to determine the driving behavior of the vehicle; and causing the vehicle to operate autonomously according to the driving behavior.

[0097] Aspect 2: The method according to aspect 1, wherein the model is based at least in part on a heuristic search algorithm.

[0098] Aspect 3: The method according to any one of aspects 1 to 2, wherein the model is based at least in part on a Monte Carlo tree search.

[0099] Aspect 4: The method according to any one of aspects 1 to 3, wherein the set of hyperparameters comprises at least one of the following: tree width, tree depth, time length of a step in the tree, or a reward function.

[0100] Aspect 5: A method according to any one of aspects 1 to 4, wherein the machine learning model is a neural network trained to determine hyperparameters of the model based at least in part on the driving context.

[0101] Aspect 6: The method according to any one of aspects 1 to 5, wherein the driving situation of the vehicle is an intersection situation, a highway situation, a local road situation or a parking lot situation.

[0102] Aspect 7: The method according to any one of aspects 1 to 6, wherein the information related to the environment is obtained from one or more sensors of the vehicle.

[0103] Aspect 8: The method according to aspect 7, wherein the one or more sensors include one or more of the following: a light detection and ranging system or a camera.

[0104] Aspect 9: The method according to any one of aspects 1 to 8, wherein the driving behavior is determined to maximize a reward function of the model.

[0105] Aspect 10: The method according to any one of Aspects 1 to 9 further includes: determining one or more intention predictions related to one or more objects in the environment, wherein at least one of the driving scenario or the hyperparameter set is further determined at least in part based on the one or more intention predictions.

[0106] Aspect 11: The method according to any one of Aspects 1 to 10 further includes: configuring the model using the hyperparameter set based at least in part on determining the hyperparameter set.

[0107] Aspect 12: An apparatus at a device, comprising: a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform one or more of the methods described in Aspects 1 to 11.

[0108] Aspect 13: A device comprising: a memory; and one or more processors coupled to the memory, the one or more processors configured to execute the method according to one or more of aspects 1 to 11.

[0109] Aspect 14: An apparatus comprising: at least one component for executing the method according to one or more of aspects 1 to 11.

[0110] Aspect 15: A non-transitory computer-readable medium storing code, the code comprising instructions executable by a processor to perform the method according to one or more of aspects 1 to 11.

[0111] Aspect 16: A non-transitory computer-readable medium storing an instruction set, the instruction set comprising one or more instructions, which, when executed by one or more processors of a device, causes the device to perform the method according to one or more of aspects 1 to 11.

[0112] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of these aspects.

[0113] As used herein, the term "component" is intended to be broadly interpreted as a combination of hardware and / or hardware and software. Whether referred to as software, firmware, middleware, microcode, hardware description language or other names, "software" should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes and / or functions, etc. As used herein, a "processor" is implemented in a combination of hardware and / or hardware and software. It will be apparent that the system or method described herein can be implemented by a combination of hardware and / or hardware and software in different forms. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit various aspects. Therefore, there is no reference to a specific software code herein to describe the operation and behavior of the system and / or method, because it will be understood by those skilled in the art that software and hardware can be designed to implement the system and / or method at least in part based on the description herein.

[0114] As used herein, "satisfying a threshold" may refer to a value being greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0115] Although the specific combination of features is set forth in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various aspects. Many of these features can be combined in a manner that is not specifically listed in the claims and / or is not disclosed in the specification. The disclosure of various aspects includes each dependent claim combined with each other claim in the claim set. As used herein, the phrase "at least one of" the list of items refers to any combination of these items (which includes a single member). As an example, "at least one of a, b or c" is intended to cover a, b, c, a+b, a+c, b+c and a+b+c, and any combination with multiple identical elements (e.g., a+a, a+a+a, a+a+b, a+a+c, a+b+b, a+c+c, b+b, b+b+b, b+b+c, c+c and c+c+c, or any other ordering of a, b and c).

[0116] Any element, action or instruction used herein should not be interpreted as key or necessary, unless clearly stated so. In addition, as used herein, the articles "one" and "an" are intended to include one or more items, and can be used interchangeably with "one or more". In addition, as used herein, the article "said (the)" is intended to include one or more items connected to the article "said", and can be used interchangeably with "one or more". In addition, as used herein, the terms "set" and "group" are intended to include one or more items, and can be used interchangeably with "one or more". If only one item is intended to be referred to, the phrase "only one" or similar terms will be used. In addition, as used herein, the terms "have", "have", "have" etc. are intended to be open terms, which do not limit the elements they modify (for example, "an element with" A may also have B). In addition, the phrase "based on" is intended to mean "based at least in part on", unless otherwise clearly stated. Furthermore, as used herein, the term "or" when used in a series is intended to be open-ended and can be used interchangeably with "and / or" unless expressly stated otherwise (eg, if used in conjunction with "either" or "only one of").

Claims

1. A method comprising: obtaining, by a device of a vehicle, information related to an environment in which the vehicle is located; Machine learning models used by the device: determining a driving context of the vehicle based at least in part on the information related to the environment, and determining a set of hyperparameters of a model for determining driving behavior of the vehicle based at least in part on the driving scenario; determining, by the device, the driving behavior of the vehicle using the model configured using the set of hyperparameters; as well as Autonomous operation of the vehicle according to the driving behavior is caused by the device.

2. The method of claim 1, wherein the model is based at least in part on a heuristic search algorithm.

3. The method of claim 1, wherein the model is based at least in part on a Monte Carlo tree search.

4. The method of claim 1, wherein the set of hyperparameters comprises at least one of: tree width, tree depth, time length of a step in the tree, or a reward function.

5. The method of claim 1, wherein the machine learning model is a neural network trained to determine hyperparameters of the model based at least in part on driving context. The method according to claim 1 , wherein the driving situation of the vehicle is an intersection situation, a highway situation, a local road situation or a parking lot situation. The method of claim 1 , wherein the information related to the environment is obtained from one or more sensors of the vehicle.

8. The method of claim 7, wherein the one or more sensors include one or more of: a light detection and ranging system or a camera.

9. The method of claim 1, wherein the driving behavior is determined to maximize a reward function of the model.

10. The method according to claim 1, further comprising: determining one or more intent predictions associated with one or more objects in the environment, Wherein at least one of the driving scenario or the set of hyperparameters is further determined based at least in part on the one or more intention predictions.

11. The method according to claim 1, further comprising: The model is configured using the set of hyperparameters based at least in part on determining the set of hyperparameters.

12. A system for autonomous driving of a vehicle, comprising: Memory; and one or more processors coupled to the memory, the one or more processors configured to: obtaining information related to an environment in which the vehicle is located; Using machine learning models: determining a driving context of the vehicle based at least in part on the information related to the environment, and determining a set of hyperparameters of a model for determining driving behavior of the vehicle based at least in part on the driving scenario; determining the driving behavior of the vehicle using the model configured using the set of hyperparameters; as well as Causing autonomous operation of the vehicle based on the driving behavior.

13. The system of claim 12, wherein the model is based at least in part on a heuristic search algorithm.

14. The system of claim 12, wherein the model is based at least in part on a Monte Carlo tree search.

15. The system of claim 12, wherein the set of hyperparameters comprises at least one of: tree width, tree depth, time length of a step in the tree, or a reward function.

16. The system of claim 12, wherein the machine learning model is a neural network trained to determine hyperparameters of the model based at least in part on driving context. 17 . The system according to claim 12 , wherein the driving context of the vehicle is an intersection context, a highway context, a local road context, or a parking lot context.

18. The system of claim 12, wherein the information related to the environment is obtained from one or more sensors of the vehicle.

19. The system of claim 18, wherein the one or more sensors include one or more of: a light detection and ranging system or a camera.

20. The system of claim 12, wherein the driving behavior is determined to maximize a reward function of the model.

21. The system of claim 12, wherein the one or more processors are further configured to: determining one or more intent predictions associated with one or more objects in the environment, Wherein at least one of the driving scenario or the set of hyperparameters is further determined based at least in part on the one or more intention predictions.

22. The system of claim 12, wherein the one or more processors are further configured to: The model is configured using the set of hyperparameters based at least in part on determining the set of hyperparameters.

23. A non-transitory computer readable medium storing a set of instructions, the set of instructions comprising: One or more instructions that, when executed by one or more processors of a device, cause the device to: obtaining information related to the environment in which the vehicle is located; Using machine learning models: determining a driving context of the vehicle based at least in part on the information related to the environment, and determining a set of hyperparameters of a model for determining driving behavior of the vehicle based at least in part on the driving scenario; as well as The model is configured using the set of hyperparameters based at least in part on determining the set of hyperparameters.

24. The non-transitory computer readable medium of claim 23, wherein the set of hyperparameters comprises at least one of: tree width, tree depth, time length of a step in the tree, or a reward function. 25 . The non-transitory computer-readable medium of claim 23 , wherein the driving context of the vehicle is an intersection context, a highway context, a local road context, or a parking lot context.

26. The non-transitory computer readable medium of claim 23, wherein the one or more instructions further cause the device to: determining one or more intent predictions associated with one or more objects in the environment, Wherein at least one of the driving scenario or the set of hyperparameters is further determined based at least in part on the one or more intention predictions.

27. An apparatus comprising: means for obtaining information related to the environment in which the vehicle is located; means for determining, using a machine learning model, a set of hyperparameters for a model for determining driving behavior of the vehicle based at least in part on the information related to the environment; and Means for configuring the model using the set of hyperparameters based at least in part on determining the set of hyperparameters.

28. The apparatus of claim 27, wherein the set of hyperparameters comprises at least one of: tree width, tree depth, time length of a step in the tree, or a reward function.

29. The apparatus of claim 27, further comprising: means for determining one or more intent predictions associated with one or more objects in the environment, Wherein the set of hyperparameters is further determined based at least in part on the one or more intent predictions.

30. The apparatus of claim 27, further comprising: Means for configuring the model using the set of hyperparameters based at least in part on determining the set of hyperparameters.

Citation Information

Patent Citations

  • Systems, methods, and devices for driving control

    CN113448265A

  • Driving decision-making method and device

    CN113837211A

  • Decision Making Methods and Systems for Automated Vehicle

    US20200363800A1