Distributed processing of vehicle sensor data

Abstract

In some examples, a first electronic control unit (ECU) receives zone sensor data for a plurality of zones associated with the vehicle. For example, a respective second ECU and a respective set of zone sensors are associated with each respective zone of the plurality of zones. Based on a commanded driving mode of the vehicle, the first ECU can perform recognition on the zone sensor data from a first zone of the plurality of zones to determine first recognition information. The first ECU receives second recognition information from each second ECU of the respective zone. For example, each second ECU is configured to perform recognition processing on the respective zone sensor data from the set of zone sensors of the respective zone. Based on the first recognition information and the second recognition information, the first ECU transmits at least one control signal to at least one vehicle actuator.

Description

[Technical field]

[0001] Certain implementations herein relate to techniques and configurations for employing multiple distributed processors and intelligent processing distribution schemes to reduce the processing requirements imposed on a primary processor for processing sensor data from multiple vehicle sensors to perform perception and other tasks to enable ADAS and / or AD system operation in a vehicle. [Background technology]

[0002] Advanced driver assistance systems (ADAS), as well as semi-autonomous, fully autonomous, or other autonomous driving (AD) systems, are systems that automate or otherwise enhance vehicle control for improved safety, automated navigation, and the like. These systems generally use multiple types of sensors to recognize the road and to recognize and avoid other vehicles, obstacles, pedestrians, and the like. However, the sensors, processors, and other computing components used to process the sensor data can substantially increase the cost of the vehicle. Furthermore, if the vehicle is an electric vehicle, the power required by the sensors and computing components can significantly drain the vehicle's battery. Furthermore, if a central processor is relied upon for most or all of the sensor data processing, this can leave the vehicle vulnerable to a single point of failure if the central processor fails or is attacked by a virus, malware, or the like. Summary of the Invention

[0003] In some implementations, a first electronic control unit (ECU) receives zone sensor data for a plurality of zones associated with the vehicle. For example, a respective second ECU and a respective set of zone sensors are associated with each respective zone of the plurality of zones. Based on a commanded driving mode of the vehicle, the first ECU can perform recognition on the zone sensor data from a first zone of the plurality of zones to determine first recognition information. The first ECU receives second recognition information from each second ECU of the respective zones. For example, each second ECU is configured to perform recognition processing on the respective zone sensor data from the set of zone sensors of their respective zones. Based on the first recognition information and the second recognition information, the first ECU transmits at least one control signal to at least one vehicle actuator. [Brief description of the drawings]

[0004] The detailed description is set forth in conjunction with the accompanying drawings, in which the leftmost digit(s) of a reference number identifies the figure in which the reference number first appears. Use of the same reference number in different figures indicates similar or identical items or features. [Figure 1] 1 illustrates an example of a system for distributed processing of vehicle sensor data according to some implementations. [Diagram 2] 2 illustrates an example of a physical and logical architecture of the system of FIG. 1 according to some implementations. [Diagram 3] 1 illustrates an example of a process performed by a high performance electronic control unit (HPECU) and a zone electronic control unit (Zone ECU) according to some implementations. [Figure 4] 1 illustrates an example process performed by one or more zone ECUs in the event of an HPECU failure, according to some implementations. [Diagram 5] FIG. 2 is a flow diagram illustrating an example of a process for determining a vehicle operating mode according to some implementations. [Figure 6]1 illustrates a data structure showing a comparison of features and capabilities of an HPECU and a zone ECU according to some implementations. [Figure 7] 1 illustrates an example of sensor coverage area in forward driving mode according to some implementations. [Figure 8] 1 illustrates an example of sensor coverage area in reverse driving mode according to some implementations. [Figure 9] 1 illustrates an example of sensor coverage area in a left turn driving mode according to some implementations. [Figure 10] 1 illustrates an example of a sensor coverage area in a right turn driving mode according to some implementations. [Figure 11] 1 illustrates an example of data processing in a low power mode of operation according to some implementations. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0005] Some implementations herein relate to techniques and configurations for employing multiple distributed processors and intelligent processing distribution schemes to reduce the processing requirements imposed on a primary processor for processing sensor data from multiple vehicle sensors to perform perception and other tasks to enable ADAS and / or AD system operation in a vehicle. Examples herein can provide comparable performance to support vehicle operation while improving resistance to component failures, malware, viruses, hacking, and the like.

[0006] In some examples, the system may include multiple separate on-board processors, referred to herein as respective electronic control units (ECUs), that may receive sensor data from multiple respective sensors that perform sensing functions that enable the vehicle to operate as a partially or fully automated vehicle. As an example, the system includes at least one high performance ECU (HPECU) and multiple zone ECUs. The HPECU may be a first type ECU that may function as a primary ECU and may include a relatively high performance processor capable of larger data processing capacity than the respective zone ECUs. The system may further include multiple zone ECUs, which may be second type ECUs, each zone ECU having a relatively low power processor compared to the HPECU and therefore a lower capacity for data processing compared to the HPECU.

[0007] The zone ECUs can be placed in strategic locations within the vehicle such that they are in close proximity to the respective sensors from which they receive data. For example, each zone can correspond to a set of one or more sensors, and each zone ECU can be assigned to a respective zone to process the sensor data of the sensors corresponding to that respective zone. As an example, there may be four zones, e.g., front, rear, left, and right, each zone having a respective zone ECU and corresponding set of sensors, although other implementations herein may include more or fewer zones.

[0008] The zone ECUs are connected to the HPECU via a wired or wireless network and may transmit at least one of processed data or raw data to the HPECU. The zone ECUs are configured to receive raw data from their respective sensors, aggregate or otherwise reduce the raw sensor data, and then process the reduced data to perform recognition processing, such as object detection, to determine a position of a detected object relative to the vehicle. For a selected vehicle operating mode, the HPECU may receive raw sensor data from one or more selected zones determined to be of interest for the selected vehicle operating mode, and may process the raw data to perform recognition processing for the selected one or more zones. Because the HPECU has higher computational processing power, the HPECU may be configured to process the raw data and provide higher performance recognition results (e.g., more accurate, more detailed, etc.) for a particular area of ​​interest corresponding to the selected vehicle operating mode than is possible for a corresponding zone ECU. The zone sensor data selected for processing by the HPECU is selected based at least in part on the indicated operating mode of the vehicle, such as based on the direction of travel, the speed of the vehicle, weather conditions, whether the vehicle is attempting to turn right or left, etc. In addition to processing raw sensor data from one or more selected zones itself, the HPECU may also receive recognition results from each zone ECU, such that all of the recognition results, regardless of which ECU processed what sensor data, may be used as inputs by the HPECU to determine one or more signals to send to one or more actuators or other devices in the vehicle.

[0009] For purposes of illustration, some exemplary implementations are described in the context of selecting an ECU of multiple ECUs to process sensor data based on a commanded driving mode of the vehicle. However, implementations herein are not limited to the specific examples provided and may be extended to other types of processors, other techniques for distributing processing tasks, other types of data processing, other types of vehicles, other types of sensors, etc., as would be apparent to one of ordinary skill in the art in light of the disclosure herein. For example, implementations herein may be used in personal vehicles, fleet vehicles and other commercially owned vehicles, trucks, cargo aircraft, or any other vehicle with some degree of autonomy. Furthermore, in the case of battery-powered vehicles, the reduction in power consumption provided by the embodiments herein may increase the range of the battery-powered vehicle. Furthermore, in the case of internal combustion vehicles, implementations herein may reduce the fuel consumption of the vehicle.

[0010] 1 illustrates an example of a system 100 for distributed processing of vehicle sensor data according to some implementations. In this example, a vehicle 102 includes a high performance ECU (HPECU) 104 that can communicate over one or more networks with multiple zones 108, which in the illustrated example include a first zone 108(1) corresponding to the front of the vehicle 102, a second zone 108(2) corresponding to the rear of the vehicle 102, a third zone 108(3) corresponding to the right side of the vehicle 102, and a fourth zone 108(4) corresponding to the left side of the vehicle 102.

[0011] Each zone 108 includes a respective zone ECU 110 and a set of zone sensors 112. In this example, a first zone 108(1) includes a first zone ECU 110(1) and one or more first zone sensors 112(1), a second zone 108(2) includes a second zone ECU 110(2) and one or more second zone sensors 112(2), a third zone 108(3) includes a third zone ECU 110(3) and one or more third zone sensors 112(3), and a fourth zone 108(4) includes a fourth zone ECU 110(4) and one or more fourth zone sensors 112(4). As described further below, the respective zone ECU 110 of each respective zone 108 can receive raw sensor data from the respective sensors 112 included in its respective zone 108.

[0012] Additionally, the HPECU 104 may communicate with one or more actuators 114 over one or more networks, such as to send one or more control signals to one or more of the actuators 114 based on results of sensor data processing performed by the HPECU 104 and the zone ECUs 110. For example, the system 100 may be included in a vehicle 102 having actuators that may control some or all aspects of vehicle operation, such as steering, braking, acceleration, signals, lighting, etc.

[0013] The zone sensors 112 may generally include one or more of cameras (mono and / or stereo, visible light and / or near infrared), lidar sensors, radar sensors, ultrasonic sensors, thermal imaging sensors, and the like. Additionally, other sensors 116 may be included in the system 100, and in some examples, the other sensors 116 may provide their sensor data directly to the HPECU 104. Examples of the other sensors 116 may include Global Navigation Satellite System (GNSS) sensors or other position sensors, steering wheel position sensors (or front wheel position sensors if the vehicle does not have a steering wheel), vehicle speed sensors, and various other vehicle condition sensors as known in the art. Additionally, while FIG. 1 illustrates the other sensors 116 as providing sensor information directly to the HPECU 104, in other examples, the other sensors 116 may provide their sensor information to one or more zone ECUs 110.

[0014] The zone ECUs 110 can communicate with each other and with the HPECU 104 via one or more networks 106. For example, the vehicle ECUs can generally communicate with each other via a vehicle bus according to a vehicle bus protocol. As an example, the one or more networks can include a Controller Area Network bus (CAN bus) that enables communication according to a CAN bus protocol. The CAN bus protocol is a vehicle bus protocol that allows ECUs and other vehicle devices and systems to communicate with each other without involving a host computer. CAN buses can include at least two different types. For example, high-speed CAN may be used in applications where a bus runs from one end of an environment to the other, and fault-tolerant CAN may be used where a group of nodes are connected to each other. Furthermore, the one or more networks 106 are not limited to the CAN bus protocol, but can include other types of wired and wireless network technologies, such as Ethernet, fiber optics, Wi-Fi, or other short-range wireless technologies. Thus, implementations herein are not limited to any particular networking technology or protocol.

[0015] As defined by the Society of Automotive Engineers (SAE), there are six levels of driving automation, from level 0 to level 5. Notably, at "Level 0" (no driving automation), the driver performs all operational tasks such as steering, braking, and acceleration. At "Level 1" (driver assistance), the vehicle can assist with some functions (e.g., cruise control), but the driver still handles all acceleration, braking, and monitoring of the surrounding environment. At "Level 2" (partial driving automation), the vehicle can assist with steering or acceleration functions, allowing the driver to step away from some of their tasks. Adaptive cruise control is an example of level 2 autonomy.

[0016] The concept of autonomous driving mainly starts with "Level 3" (conditional driving automation), where the vehicle itself monitors its surroundings and can exert some control over the vehicle (e.g., automatic emergency braking). At "Level 4" (high driving automation), the vehicle can drive independently in most cases, but will not act unless all conditions are met and an operator is still able to take over. At "Level 5" (full driving automation), the vehicle can drive anywhere in any condition without an operator. Therefore, some examples in this specification may be useful for driving automation systems at levels 3 to 5.

[0017] As previously discussed, Zone ECU 110 may generally process sensor data received from each sensor in each zone to which Zone ECU 110 is assigned. Depending on the current and future operating modes of the vehicle, HPECU 104 may additionally or alternatively process sensor data from one or more of zones 108(1)-108(4). By way of example, HPECU 104 may receive raw sensor data directly from each sensor in each zone, or HPECU 104 may receive raw sensor data via each Zone ECU 110 in each zone. Further details are described below with respect to Figures 2-11.

[0018] FIG. 2 illustrates an example of a physical and logical architecture 200 of the system 100 of FIG. 1 according to some implementations. In this example, the HPECU 104 includes one or more processors 202, one or more computer-readable media 204, and one or more communication interfaces 206. The one or more processors 202 may include one or more of a central processing unit (CPU), a graphic processing unit (GPU), a microprocessor, a microcomputer, a microcontroller, a digital signal processor, a state machine, a logic circuit, and / or other device that manipulates signals based on operational instructions. By way of example, the processor 202 may include one or more hardware processors and / or logic circuits of any suitable type that are specifically programmed or configured to execute the algorithms and other processes described herein. The processor 202 may be configured to fetch and execute computer-readable instructions stored on the computer-readable medium 204, which may program the processor 202 to perform the functions described herein.

[0019] Computer readable medium 204 may include volatile and non-volatile memory and / or removable and non-removable media implemented in any type of technology for storing information such as computer readable instructions, data structures, programs, program modules, and other code or data. For example, computer readable medium 204 may include, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, optical storage, solid state storage, magnetic disks, cloud storage, or any other medium that can be used to store desired information and that can be accessed by a computing device. Depending on the configuration of HPECU 104, computer readable medium 204 may be tangible non-transitory media, insofar as non-transitory computer readable media, when referred to, excludes media such as energy, carrier signals, electromagnetic waves, and / or signals themselves. In some cases, computer readable medium 204 may be co-located with HPECU 104, while in other examples, computer readable medium 204 may be partially remote from HPECU 104, such as accessible via a wireless network, etc.

[0020] The computer readable medium 204 may be used to store any number of functional components executable by the processor 202. In many embodiments, these functional components include instructions or programs executable by the processor 202 that, when executed, specifically program the processor 202 to perform operations attributed to the HPECU 104. The functional components stored on the computer readable medium 204 may include a process manager 208, a recognition program 210, a vehicle control program 212, and a path planning program 214, each of which may include one or more computer programs, applications, executable code, or portions thereof. It is noted that, although in this example, the programs 208-214 are shown as separate programs, some or all of these programs may be combined into one or more programs or may be divided into a larger number of programs.

[0021] Additionally, computer-readable medium 204 may store data, data structures, and other information used to perform the functions and services described herein. For example, computer-readable medium 204 may store perception information 216, vehicle data 218, sensor data 220, and in some examples, one or more machine learning models (MLM(s)) 222 that may be used, for example, by perception program 210 and / or vehicle control program 212. HPECU 104 may also include or maintain other functional components and data that may include programs, drivers, etc., as well as data used or generated by the functional components. Additionally, HPECU 104 may include many other logical, programmatic, and physical components, the aforementioned components of which are merely examples relevant to the description herein.

[0022] The one or more communications interfaces 206 may include one or more software and hardware components for enabling communication with various other devices, such as via one or more networks 106 and / or via a cellular or other wireless communications network for communicating with external computing devices (not shown in FIG. 2 ) outside the vehicle 102. For example, the communications interface 206 may enable communication via one or more of a LAN, the Internet, a cable network, a cellular network, a wireless network (e.g., Wi-Fi) and a wired network (e.g., CAN, fiber optic, Ethernet), a direct connection, and a short-range communication such as BLUETOOTH®.

[0023] The zone ECUs 110 may each have a similar hardware configuration as the HPECU 104, including one or more processors 202, one or more computer readable media 204, and one or more communication interfaces 206. However, the zone ECUs 110 may have substantially lower overall performance compared to the HPECU 104, including lower performance components such as lower performance processors 202 having lower clock speeds, lower performance memory, and a smaller amount of memory and other computer readable media. Thus, the data processing capabilities of each zone ECU may be substantially lower than the data processing capabilities of the HPECU 104, as measured in millions of operations per second (MOPS), millions of instructions per second (MIPS), data processing benchmarks, or the time required to process the same amount of sensor data using a recognition program 210. As an example, the measured performance of the HPECU 104 may be, for example, ten times greater than the performance of each zone ECU 110, although embodiments herein are not limited to any particular difference in the advantage of the measured performance of the HPECU 104 over the performance of the zone ECU 110.

[0024] Additionally, the zone ECU 110 may also include or have access to some or all of the aforementioned programs 208, 210, 212, 214, data 216, 218, 220, and MLM 222 contained in or accessed by the HPECU 104. For example, if the HPECU 104 fails, the zone ECU 110 may execute the object recognition and vehicle control programs necessary to enable the vehicle 102 to continue to operate safely. Further details of this mode of operation are described below, for example, with respect to FIG. 4.

[0025] As previously discussed, each sensor 112 in each zone 108 may provide sensor data 220 to a respective zone ECU 110 in that zone 108. Additionally, the sensor data 220 from each set of zone sensors 112 may also be received by the HPECU 104 and may be at least temporarily stored as sensor data 220, such as in a buffer provided by the computer-readable medium 204. In some cases, the sensor data 220 received directly from the sensors 112 may be referred to as raw sensor data, as the data has not yet undergone data processing, filtering, normalization, etc. Thus, as shown in the example of FIG. 2, the HPECU 104 may receive first sensor data 220(1) from a first zone sensor 112(1), may receive second sensor data 220(2) from a second zone sensor 112(2), may receive third sensor data 220(3) from a third zone sensor 112(3), and may receive fourth sensor data 220(4) from a fourth zone sensor 112(4). However, while the HPECU 104 may receive sensor data 220 from all zones 108, the HPECU 104 may ignore most of this sensor data and may generally perform recognition processing on only a subset of the received sensor data 220, such as based on a commanded operating mode of the vehicle 102.

[0026] Zone ECUs 110 may also perform recognition processing on received sensor data 220 for each zone 108. For example, first zone ECU 110(1) may receive raw sensor data 220(1) from first zone sensor 112(1), may perform a data reduction process on the received sensor data 220(1), and may execute an instance of recognition program 210 to perform recognition processing on the reduced sensor data 220(1). First zone ECU 110(1) may send results of the recognition processing to HPECU 104 as first recognition information 216(1). Similarly, second zone ECU 110(2) may send second recognition information 216(2) to HPECU 104 based on results of the recognition processing of second sensor data 220(2) received from second zone sensor 112(2). Similarly, third zone ECU 110(3) may send third recognition information 216(3) to HPECU 104, and fourth zone ECU 110(4) may send fourth recognition information 216(4) to HPECU 104. HPECU 104 may use received recognition information 216(1), 216(2), 216(3) and / or 216(4), as well as recognition information determined by its own execution of recognition program 210, as inputs to vehicle control program 212 for determining one or more control signals 223 to send to actuators 114. In the example of FIG. 2, actuators 114 include suspension controller 224, steering controller 226, vehicle speed controller 228, braking controller 230, and one or more warning devices 232. Numerous other devices, systems, or other actuators within a vehicle that may receive control signals 123 will be apparent to one of ordinary skill in the art having the benefit of the disclosure herein.

[0027] As an example, the vehicle control program 212 may use rule-based and / or machine learning based control algorithms to determine parameters for controlling the vehicle 102. For example, the vehicle control program 212 may apply one or more of the machine learning models 222 to determine an appropriate action, such as braking, steering, decelerating, accelerating, etc., based on the perception information 216 determined by the HPECU 104 and the perception information 216 received from the zone ECU 110. Additionally, the vehicle control program 212 may send one or more control signals 223 to one or more vehicle systems in response to the perception information 212. For example, the vehicle control program 212 may send the control signals 223 to a suspension controller 224, a steering controller 226, a vehicle speed controller 228, and / or a braking controller 230. For example, the control signals 223 may include specific spring rate and / or damping control information sent to a suspension controller 224, a specific steering angle sent to a steering controller 226 to steer one or more wheels, specific acceleration / deceleration control information sent to a vehicle speed controller 228, and / or specified brake control information to control the vehicle brakes. Additionally, in some examples, the control signals 223 may also be sent to one or more warning devices 232, such as to sound or display a warning to a vehicle occupant.

[0028] Additionally, as previously discussed, the HPECU 104 may receive other sensor data 234 from other sensors 102 within the vehicle 102. For example, the vehicle may include a number of other sensors 116 in addition to the zone sensors 112 that may provide sensor information used by the vehicle control program 212. The other sensor data 234 may also include information received from or associated with various vehicle systems, such as position information received from the suspension controller 224, the steering controller 226, the vehicle speed controller 228, etc.

[0029] As an example, such as for levels 3-5 autonomy, the HPECU 104 and each zone ECU 110 may continuously receive raw sensor data 220 while the vehicle is moving. Additionally, the perception program 210 executed by the HPECU 104 and each zone ECU 110 may process the received sensor data 220 to recognize road features, obstacles, and the like. The HPECU 104 may provide perception information 216 regarding detected obstacles, road features, and the like to the vehicle control program 212, which may take one or more actions in response to the perception information in the case of levels 3-5 autonomy. In some examples, the vehicle control program 212 and / or the perception program 210 may fuse or combine and integrate the perception information determined from the image data with other types of sensor data (e.g., radar, lidar, ultrasonic, etc.) to provide additional available information to the vehicle control program 212 for controlling the vehicle. Sensor fusion can take into account all sensor detection results (e.g., lidar, radar, other cameras), can compare the results of various sensors with those of other sensors, and can use the combined results to perform vehicle control. If the sensors do not agree on the presence or location of one or more potential obstacles, the sensor fusion function can determine a confidence value for each sensor, can determine how many sensors agree, can determine whether current environmental conditions may be adversely affecting sensor performance, etc., and can determine a conclusion regarding the likelihood that a particular object is actually present.

[0030] Additionally or alternatively, such as when the vehicle is under the control of a human driver, the vehicle control program 212 may send control signals 223 to one or more warning devices 232, such as an audible or visual warning device. Examples of warning devices 232 include speakers capable of generating an audible warning, haptic devices capable of generating vibrations or other types of tactile warnings (e.g., in the seat or steering wheel), and / or visual signal devices capable of generating visual warnings.

[0031] 3-5 include flow diagrams illustrating examples of algorithms or other processes according to some implementations. The processes are illustrated as a collection of logical flow diagram blocks representing a sequence of operations, some or all of which may be implemented in hardware, software, or a combination thereof. In the context of software, the blocks may correspond to computer-executable instructions stored on one or more computer-readable media that, when executed by one or more processors, programs the processors to perform the recited operations. In general, computer-executable instructions include routines, programs, objects, components, data structures, etc. that perform a particular function or implement a particular data type. The order in which the blocks are described should not be construed as limiting. Any number of the described blocks may be combined in any order and / or in parallel to perform a process or alternative processes, and not all blocks need to be performed. For illustrative purposes, the processes are described with reference to the environments, frameworks, and systems described in the examples herein, although the processes may be implemented in a wide variety of other environments, frameworks, and systems.

[0032] FIG. 3 illustrates an example process 300 performed by the HPECU and the zone ECU, according to some embodiments. As previously described, the zone ECU 110 can be configured to perform recognition processing, such as object detection and basic sensor fusion, on the sensor data 220 received from each zone sensor 112. The zone ECU performs deep machine learning using one or more of the machine learning models 222 described above to detect the position, relative speed, and identity of each recognized object visible or otherwise detectable to the side of the vehicle to which the zone corresponds. Each zone ECU 110 can include a relatively low to mid-range processor, as previously described. Because the zone ECU 110 includes a low-performance processor, the zone ECU 110 may not be able to process the raw data from its respective sensor in the time required to ensure vehicle safety. Thus, the zone ECU 110 can crop the received raw images and reduce the resolution of the raw images, as well as reduce the size of other sensor data, such as by reducing the sampling frequency of all data from the respective sensors 112. The zone ECUs can then process the reduced data to generate perception information 216, which may include generating a map of the vehicle's surroundings (e.g., a disparity map) corresponding to the respective zone. Each zone ECU 110 can send the perception information to the HPECU 104 for further analysis and as an input to the vehicle control program 212.

[0033] Additionally, the HPECU 104 may also perform recognition processing on sensor data 220 selected from one or more of the zones depending on the indicated vehicle operating mode. For example, if the vehicle is traveling in a forward direction above a threshold speed, the vehicle is operating in a forward driving mode, and the HPECU 104 may perform recognition processing on sensor data 220(1) collected by a first zone sensor 112(1) corresponding to the front of the vehicle. An example process 302 that may be performed by the HPECU 104 is shown in FIG.

[0034] At 304, HPECU 104 receives sensor data from the zone sensors and determines one or more zones of interest based on a commanded operating mode of the vehicle. In the illustrated example, the commanded operating mode is a forward driving mode. Thus, HPECU 104 may perform processing on sensor data 220(1) received from first zone sensor 112(1) and may ignore or otherwise not process sensor data received from second, third, and fourth zone sensors 112(2)-112(4).

[0035] At 306, the HPECU 104 may perform recognition on the sensor data from the region of interest. In this example, the HPECU 104 may perform high-resolution recognition on the raw sensor data 220-1 received from the first zone sensor 112-1. As previously described, the HPECU 104 may execute the recognition program 210, which may also employ one or more machine learning models 222 when performing recognition. For example, the output of the recognition program 210 may be a disparity map or other recognition information 216.

[0036] At 308, HPECU 104 may receive recognition information 216(1)-216(4) from each zone ECU 110(1)-110(4). In this example, first zone ECU 110(1) may perform recognition processing on first zone sensor information 220(1). For example, HPECU 104 may compare output recognition information 216(1) to its own recognition information determined from processing first zone sensor data 220(1), such as to detect any inconsistencies between the two recognition results. In another example, to provide further reduction in power consumption, first zone ECU 110(1) may be configured to not perform recognition processing when recognition processing is being performed by HPIECU 104 on sensor data 220(1).

[0037] At 310, the HPECU 104 may perform path planning, risk map generation, and / or vehicle control processing based on the perception information determined by the HPECU 104 and also based on the perception information received from the zone ECU 110.

[0038] At 312, the HPECU 104 may send one or more control signals to one or more of the actuators 114 based on the results of the path planning, risk map generation, and / or vehicle control processing.

[0039] Additionally, each zone ECU 110 may execute a process 320 as described below.

[0040] At 322, the zone ECU 110 may receive sensor data 220 from each zone sensor for that zone.

[0041] At 324, the zone ECU 110 may reduce the size of the sensor data received from each zone sensor. As previously described, the zone ECU 110 may reduce the sampling rate of the sensor data, may reduce the resolution of the received images, may crop the received images, or may take other actions to reduce the size of the received data before performing recognition processing on the received data.

[0042] At 326, the zone ECU 110 may perform recognition processing on the reduced sensor data for each zone.

[0043] At 328 , the zone ECU 110 may transmit the identification information 216 to the HPECU 104 .

[0044] FIG. 4 illustrates an example of a process 400 performed by one or more of the zone ECUs in the event of a failure of the HPECU, according to some embodiments. For example, if the HPECU 104 fails, the zone ECUs 110(1)-110(4) can operate the vehicle without the HPECU 104, as shown at 402, but with less accuracy than when the HPECU is operating. For example, in some examples, the zone ECU 110 can perform typical ADAS functions such as lane keeping, adaptive cruise control, automatic emergency braking, etc. Furthermore, depending on the specifications of the zone ECU, in some cases, the zone ECU 110 can also perform fully autonomous driving, at least in some driving conditions, or at lower speeds, etc. Thus, the system herein can operate the vehicle even if any one component fails.

[0045] At 404 , the zone ECUs 110 receive sensor data from their respective zone sensors 112 .

[0046] At 406, the zone ECU 110 reduces the size of the sensor data received from each zone sensor. As previously discussed, size reduction may include reducing the sampling frequency of the received sensor data, reducing the resolution of the received sensor data, cropping images of the received sensor data, etc.

[0047] At 408, the zone ECU 110 performs recognition on the reduced sensor data to determine recognition information. By way of example, the recognition information may include one or more disparity maps or any of a variety of other types of information related to objects detected within range of each sensor.

[0048] At 410, the zone ECUs may perform route planning and / or vehicle control processing. For example, one or more of the zone ECUs may execute an instance of the route planning program 214 and / or an instance of the vehicle control program 212. In some cases, these programs 214 and 212 may be optimized to run on a lower power processor than the HPECU 104. In some cases, the zone ECU 110 may select one of the zone ECUs using any of a variety of selection techniques to perform route planning and / or vehicle control processing. As an example, if the vehicle is currently operating in a forward driving mode, the zone ECU 110(2) associated with the second zone sensor 112(2) (i.e., the rear zone) may be selected to perform route planning and / or vehicle control processing while receiving more reduced sensor data from the second zone sensor. As another example, one zone ECU 110 may be selected to perform route planning processing and the other zone ECU 110 may be selected to perform vehicle control processing. Numerous other variations may be apparent to one of ordinary skill in the art having the benefit of the disclosure herein.

[0049] At 412, the zone ECU 110, which performs the path planning and / or vehicle control processing, may send one or more control signals 414 to one or more of the actuators 114 based on the results.

[0050] 5 is a flow diagram illustrating an example of a process 500 for determining a vehicle operating mode according to some implementations. In some examples, the process 500 may be performed by the aforementioned systems, such as by executing the process manager 208 on at least one of the HPECUs 104 and / or one or more of the zone ECUs 110.

[0051] At 502, the system can receive information regarding vehicle operation. For example, the system can receive satellite positioning information, information regarding a planned route the vehicle is traversing, current speed information of the vehicle, current weather condition information, current day and time information, etc.

[0052] At 504, the system may determine whether the vehicle is reversing. If so, the process proceeds to 506. If not, the process proceeds to 508.

[0053] At 506, if the indicated vehicle operating mode is that the vehicle is traveling in reverse, the system may operate in a reverse driving mode in which the HPECU 104 processes sensor information received from the sensor 112 corresponding to the rear zone of the vehicle, i.e., the second zone sensor 112(2) in the exemplary zone configuration described above with respect to Figures 1-4.

[0054] At 508, the system may determine whether a turn is approaching. If so, the process proceeds to 510. If not, the process proceeds to 516.

[0055] Once the system determines that the vehicle is approaching a turn at 510, the system may determine whether the vehicle is turning right or left. If the vehicle is turning right, the process proceeds to 512. If the vehicle is turning left, the process proceeds to 514.

[0056] At 512, the system operates in a right-turn driving mode. For example, during a right-turn driving mode of vehicle operation, HPECU 104 may process sensor data 112 received from sensors for the front and left zones of the vehicle, which correspond, for example, to first zone sensor 112(1) and fourth zone sensor 112(4) in the example zone configuration described above with respect to FIGS. 1-4.

[0057] At 514, the system operates in a left turn driving mode. For example, during a left turn driving mode of vehicle operation, HPECU 104 may process sensor data 112 received from sensors for a forward zone and a right zone of the vehicle, which correspond, for example, to first zone sensor 112(1) and third zone sensor 112(3) in the example zone configuration described above with respect to FIGS. 1-4.

[0058] At 516, when the vehicle is not reversing and not approaching a turn, the system may determine whether the current speed of the vehicle exceeds a threshold speed. For example, as the vehicle speed exceeds a threshold speed, such as 10 mph, 20 mph, 30 mph, etc., it becomes more important for the forward sensor to perform higher resolution sensing of the field of view ahead of the vehicle to ensure safety. Thus, if the vehicle speed exceeds the threshold, the process proceeds to 518. If not, the process proceeds to 520.

[0059] At 518, based on the vehicle speed exceeding the threshold, the system may operate in a forward driving mode in which the HPECU 104 processes sensor information received from a sensor 112 corresponding to a forward zone of the vehicle, i.e., the first zone sensor 112(1) in the example zone configuration described above with respect to Figures 1-4.

[0060] At 520, the system may determine whether the vehicle is operating at night. If so, the process proceeds to 522. If not, the process proceeds to 524.

[0061] At 522, based on the vehicle being operated at night in a forward direction, the system may operate in a forward driving mode in which the HPECU 104 processes sensor information received from a sensor 112 corresponding to a front zone of the vehicle, i.e., the first zone sensor 112(1) in the example zone configuration described above with respect to Figures 1-4.

[0062] At 524, the system may determine whether the vehicle is being driven in inclement weather. If so, the process proceeds to 526. If not, the process proceeds to 528.

[0063] At 526, based on the vehicle being operating in a forward direction, during inclement weather the system may operate in a forward driving mode in which the HPECU 104 processes sensor information received from a sensor 112 corresponding to a forward zone of the vehicle, i.e., the first zone sensor 112(1) in the example zone configuration described above with respect to Figures 1-4.

[0064] At 528, the system may operate in a low power mode in which the HPECU 104 does not perform recognition processing on the sensor data 112 received from any of the zones. For example, based on the vehicle being moving in a forward direction without turning and at a speed below a threshold speed, not at night or in poor weather, there is no need to perform high resolution processing of the sensor data. Thus, recognition may be performed by the zone ECUs to reduce power consumption of the HPECU 104. As an example, the zone ECU 110 may transmit the determined recognition information to the HPECU 104 as an input to a path planning program and / or a vehicle control program. As another example, in the low power mode, one or more of the zone ECUs 110 may execute a path planning program and / or a vehicle control program to further reduce power consumed by the HPECU 104.

[0065] FIG. 6 illustrates an example data structure 600 illustrating a comparison of features and capabilities of HPECU 104 and zone ECU 110 according to some implementations. As previously described, HPECU 104 includes one or more high performance processors, while zone ECU 110 includes a lower performance processor that consumes less power than the HPECU processor. HPECU 104 may receive raw sensor data 120(1)-120(4) directly from zone sensors 112(1)-112(4), respectively. Zone ECUs 110 generally receive sensor data only from their assigned zone sensors 112. HPECU 104 may perform recognition processing on some or any of the received sensor data 120(1)-120(4) depending on a commanded vehicle operating mode of the vehicle, and may receive recognition information determined by zone ECU 110.

[0066] The data structure 600 includes capabilities of the HPECU 104 listed at 602 and capabilities of the zone ECU 110 listed at 604. For example, the HPECU 104 may perform object recognition based on raw sensor data, as shown at 606, and the zone ECU 110 may perform object recognition based on reduced-sized sensor data of the respective zone sensors. Additionally, both the HPECU 104 and the zone ECU 110 may perform object tracking based on object recognition information they determine, as shown at 608. Additionally, the HPECU 104 may perform sensor fusion based on raw sensor data, but the zone ECU 110 may perform sensor fusion only based on reduced-sized sensor data or data recognized as an object, as shown at 610.

[0067] Additionally, as shown at 612, 614 and 616, the HPECU 104 may use the perception information to perform additional processing such as risk map generation, path planning, and vehicle control. For example, the HPECU 104 may generate a risk map, which may include creating a map of the area around the vehicle indicating the level of risk associated with driving at each location. For example, the risk map may be determined based on at least the identities, locations, and relative speeds of the perceived objects, as well as the terrain around the vehicle, and other information such as the vehicle's speed, weather conditions, time of day, etc. The risk map may help ensure that the path selected by the HPECU 104 does not endanger vehicle occupants or the vehicle's surroundings. However, determining a risk map may be computationally expensive, and in some examples herein, the Zone ECU 110 may not be able to perform this operation in parallel with the perception processing and other processing tasks.

[0068] Additionally, as shown at 614, the HPECU 104 may perform route planning based on the awareness information determined by the HPECU 104 and the zone ECU 110. In some examples, the zone ECU 110 may perform route planning as a backup, such as in the event that the HPECU 104 fails. Similarly, the HPECU 104 may perform vehicle control processing based on the awareness information and other vehicle information. The zone ECU 110 may perform vehicle control processing as a backup or reduced capability vehicle control, such as in the event that the HPECU 104 fails, depending on the particular capabilities of the zone ECU processor.

[0069] 7 illustrates an example sensor coverage area 700 in a forward driving mode according to some implementations. For example, when the vehicle is indicated as traveling in a forward direction and the conditions of one of blocks 518, 522, or 526 of FIG. 5 are met, the HPECU 104 may operate in a forward driving mode in which the HPECU 104 processes sensor data received from a forward-facing sensor corresponding to the first zone sensor 112(1).

[0070] As shown at 702, in a forward driving mode, forward facing sensor field of view 704 corresponds to sensor data of interest for processing by HPECU 104. In this example, forward facing sensor field of view 704 corresponds to the aforementioned first zone sensor 112(1), rear facing sensor field of view 706 corresponds to the aforementioned second zone sensor 112(2), right sensor field of view 708 corresponds to the aforementioned third zone sensor 112(3), and left sensor field of view 710 corresponds to the aforementioned fourth zone sensor 112(4).

[0071] As shown at 712, in a forward driving mode, HPECU 104 performs recognition processing on first zone sensor data 220(1) and does not perform recognition processing on sensor data 220(2)-112(4) received from second through fourth zone sensors 112(2)-220(4). For example, HPECU 104 performing recognition processing on sensor data from forward field of view 704 provides more accurate high resolution object detection and therefore safer vehicle operation. In some examples, first zone ECU 110(1) also performs recognition processing on first zone sensor data 220(1). In that situation, first zone ECU 110(1) can provide recognition information 216(1) to HPECU 104 to provide redundancy, increased security, error checking, etc. The other zone ECUs 110(2)-110(4) also provide respective perception data 216(2)-216(4) to the HPECU 104, such as for path planning, risk map generation, and / or vehicle control processing.

[0072] 8 illustrates an example sensor coverage area 800 in a reverse driving mode according to some implementations. For example, as shown at 802, when the vehicle is traveling in reverse, sensor data corresponding to field of view 706 is sensor data of interest for processing by HPECU 104. Thus, when the vehicle is indicated as traveling in a reverse direction and the conditions of block 506 of FIG. 5 are satisfied, HPECU 104 may operate in a reverse driving mode in which HPECU 104 processes sensor data received from a rearward facing sensor corresponding to second zone sensor 112(2).

[0073] As shown at 804, in the reverse driving mode, HPECU 104 performs recognition processing on second zone sensor data 220(2) and does not perform recognition processing on sensor data 220(1), 220(3), 220(4) received from zone sensors 112(1), 112(3), 112(4). Thus, when the reverse driving mode is selected, the system focuses on the rearward facing sensors for processing by HPECU 104 to provide a more accurate recognition of the direction of travel. In some examples, second zone ECU 110(2) also performs recognition processing on second zone sensor data 220(2). In that situation, second zone ECU 110(2) can provide recognition information 216(2) to HPECU 104 to provide redundancy, increased security, error checking, etc. The other zone ECUs 110(1), 110(3), and 110(4) also provide respective perception data 216(1), 216(3), and 216(4) to HPECU 104 for purposes such as path planning, risk map generation, and / or vehicle control processing.

[0074] 9 illustrates an example sensor coverage area 900 in a left turn driving mode according to some implementations. For example, as shown in 902, when a vehicle is turning left, sensor data corresponding to fields of view 704 and 708 (to detect oncoming traffic) may be sensor data of interest for processing by HPECU 104. Thus, when a vehicle is indicated as turning left and the conditions of block 514 of FIG. 5 are met, HPECU 104 may operate in a left turn driving mode in which HPECU 104 processes sensor data received from a forward facing sensor corresponding to first zone sensor 112(1) and a right side sensor corresponding to third zone sensor 112(3).

[0075] As shown at 904, in a left turn driving mode, HPECU 104 performs recognition processing on first zone sensor data 220(1) and third zone sensor data 220(3) and does not perform recognition processing on sensor data 220(2) or 220(4) received from zone sensors 112(2) and 112(4), respectively. Thus, when a left turn driving mode is selected, the system focuses on the forward and right facing sensors for processing by HPECU 104 to provide higher accuracy recognition of these directions. In some examples, first zone ECU 110(1) and third zone ECU 110(3) also perform recognition processing on sensor data 220(1) and 220(3), respectively. In that situation, zone ECUs 110(1) and 110(3) can provide recognition information 216(1) and 216(3), respectively, to HPECU 104 to provide redundancy, increased security, error checking, etc. The other zone ECUs 110(2) and 110(4) also provide respective perception data 216(2) and 216(4) to the HPECU 104, such as for path planning, risk map generation, and / or vehicle control processing.

[0076] 10 illustrates an example sensor coverage area 1000 in a right turn driving mode according to some implementations. For example, as shown in 1002, when a vehicle is turning right, sensor data corresponding to fields of view 704 and 710 (to detect oncoming traffic) may be sensor data of interest for processing by HPECU 104. Thus, when the vehicle is indicated as turning right and the conditions of block 512 of FIG. 5 are met, HPECU 104 may operate in a right turn driving mode in which HPECU 104 processes sensor data received from a forward facing sensor corresponding to first zone sensor 112(1) and a left sensor corresponding to fourth zone sensor 112(4).

[0077] As shown at 1004, in a right turn driving mode, HPECU 104 performs recognition processing on first zone sensor data 220(1) and fourth zone sensor data 220(4) and does not perform recognition processing on sensor data 220(2) or 220(3) received from zone sensors 112(2) and 112(3), respectively. Thus, when a right turn driving mode is selected, the system focuses on the forward and left facing sensors for processing by HPECU 104 to provide higher accuracy recognition of these directions. In some examples, first zone ECU 110(1) and fourth zone ECU 110(4) also perform recognition processing on sensor data 220(1) and 220(4), respectively. In that situation, zone ECUs 110(1) and 110(4) can provide recognition information 216(1) and 216(4), respectively, to HPECU 104 to provide redundancy, increased security, error checking, etc. The other zone ECUs 110(2) and 110(3) also provide respective perception data 216(2) and 216(3) to the HPECU 104, such as for path planning, risk map generation, and / or vehicle control processing.

[0078] FIG. 11 illustrates an example 1100 of data processing for a low power driving mode according to some implementations. For example, when the condition of block 528 of FIG. 5 is satisfied, the system does not need to focus on any of the sensor zones. As shown at 1102, the low power driving mode may be implemented in a situation where the vehicle 102 is moving forward below a threshold speed, during daylight hours, and on a clear day. In such a situation, as shown at 1104, the zone ECUs 110(1)-110(4) can perform all perception processing and provide perception data 216(1)-216(4), respectively, to the HPECU 104, which can still perform risk map generation, path planning, and vehicle control processing. By operating the system in a low power mode, the processing load of the HPECU 104 is reduced, and the power consumption of the HPECU 104 is reduced.

[0079] The exemplary processes described herein are merely examples of processes provided for illustrative purposes. Numerous other variations may become apparent to those skilled in the art in light of the disclosure herein. Furthermore, although the disclosure herein describes some examples of suitable frameworks, architectures, and environments for carrying out the processes, the implementations herein are not limited to the specific examples shown and described. Furthermore, the disclosure provides various exemplary implementations as described and shown in the drawings. However, the disclosure is not limited to the implementations described and illustrated herein, and may extend to other implementations as known or become known to those skilled in the art.

[0080] Various instructions, processes, and techniques described herein may be considered in the general context of computer-executable instructions, such as computer programs and applications, stored on a computer-readable medium and executed by a processor herein. In general, the terms programs and applications may be used interchangeably and may include instructions, routines, modules, objects, components, data structures, executable code, and the like, for performing particular tasks or implementing particular data types. These programs, applications, and the like may be executed as native code, downloaded and executed in a virtual machine or other just-in-time compilation execution environment, and the like. In general, the functionality of the programs and applications may be combined or distributed as desired in various implementations. Implementations of these programs, applications, and techniques may be stored in computer storage media or transmitted over some form of communication medium.

[0081] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as example forms of implementing the claims.

Claims

1. 1. A system for processing sensor data in a vehicle, comprising: a first electronic control unit (ECU) capable of communicating with a plurality of zone ECUs, the first ECU having a higher data processing capability than a respective zone ECU of the plurality of zone ECUs, each respective zone ECU being associated with a respective zone of a plurality of zones associated with the vehicle, a set of zone sensors being associated with each respective zone for providing zone sensor data to the respective zone ECU associated with the respective zone, the first ECU including a processor, the processor configured to execute executable instructions to: receiving, by the processor of the first ECU, zone sensor data from each set of zone sensors for each of the plurality of zones; selecting, by the processor of the first ECU, the zone sensor data for a first zone of the plurality of zones based on a commanded operating mode of the vehicle; performing, by the processor of the first ECU, recognition on the zone sensor data for the first zone to determine first recognition information; receiving, by the processor of the first ECU, second identification information from the respective zone ECU associated with the respective zone of the plurality of zones; transmitting, by the processor of the first ECU, at least one control signal to at least one vehicle actuator based on at least the first identification information and the second identification information; A system configured to perform operations including:

2. The operation includes: determining a designated driving mode from information related to vehicle operation; dynamically selecting, by the processor of the first ECU, the zone sensor data from the first zone for performing the recognition based on determining the indicated driving mode from the information related to the vehicle operation; The system of claim 1 further comprising:

3. The operation includes: selecting, by the processor of the first ECU, zone sensor data from a second zone for performing the recognition based on the indicated driving mode change indication; and ceasing to perform the recognition on the zone sensor data received from the first zone. The system of claim 1 further comprising:

4. Each of the zone ECUs includes: receiving zone sensor data from the set of zone sensors associated with the respective zone associated with the respective zone ECU; reducing, by the respective zone ECU, an amount of the zone sensor data to obtain reduced sensor data; performing recognition on the reduced sensor data to obtain recognition information; transmitting the recognition information to the first ECU as a part of the second recognition information; The system of claim 1 configured to perform operations including:

5. The indicated driving mode of the vehicle is: a forward driving mode in which the vehicle is traveling in a forward direction; or a reverse driving mode in which the vehicle is traveling in a reverse direction; The system of claim 1 , wherein the first and second inputs are one of:

6. The indicated driving mode of the vehicle is: a left turn driving mode in which the vehicle is approaching a left turn; or A right-turn driving mode in which the vehicle is approaching a right turn. One of the The operation includes: selecting, by the processor of the first ECU, the zone sensor data of a second zone of the plurality of zones based on the indicated driving mode being one of the left turn driving mode or the right turn driving mode; performing, by the processor of the first ECU, recognition on the zone sensor data of the second zone in addition to the zone sensor data of the first zone to determine the first recognition information; The system of claim 1 further comprising:

7. The operation includes:

2. The system of claim 1, further comprising: an operation of selecting a low power driving mode based at least on a commanded vehicle speed being below a threshold speed; and an operation of ceasing execution of the recognition by the processor of the first ECU, wherein the zone ECU provides the second recognition information in the respective zone to the first ECU.

8. receiving, by a first electronic control unit (ECU), zone sensor data for a plurality of zones associated with the vehicle, a respective second ECU and a respective set of zone sensors associated with each respective zone of the plurality of zones; performing, by the first ECU, recognition on the zone sensor data from a first zone of the plurality of zones based on an indicated driving mode of the vehicle to determine first recognition information; receiving, by the first ECU, second recognition information from one or more of the respective second ECUs associated with the respective zones, the respective second ECUs being configured to perform recognition processing on respective zone sensor data from the set of zone sensors of the respective zones with which the respective second ECUs are associated; sending, by the first ECU, at least one control signal to at least one vehicle actuator based on at least the first identification information and the second identification information; The method includes:

9. The method of claim 8 , wherein the first ECU has a higher data processing capability than the respective second ECU associated with the respective zone.

10. receiving, by the first ECU, the zone sensor data from each set of zone sensors for each of the plurality of zones; dynamically selecting, by the first ECU, the zone sensor data from the first zone for performing recognition based on determining the indicated driving mode from information related to vehicle operation; The method of claim 8 further comprising:

11. 9. The method of claim 8, further comprising the steps of: selecting, by the first ECU, zone sensor data from a second zone for performing the recognition based on the indicated driving mode change indication; and ceasing performance of the recognition on the zone sensor data received from the first zone.

12. Each of the second ECUs includes: receiving zone sensor data from the set of zone sensors associated with the respective zones associated with the respective second ECUs; reducing an amount of the zone sensor data to obtain reduced sensor data, and performing recognition on the reduced sensor data to obtain recognition information; transmitting the recognition information to the first ECU as a part of the second recognition information; The method of claim 8 , wherein the method is configured to:

13. The indicated driving mode of the vehicle is: a left turn driving mode in which the vehicle is approaching a left turn; or A right-turn driving mode in which the vehicle is approaching a right turn. One of the The method comprises: selecting, by the first ECU, the zone sensor data of a second zone among the plurality of zones based on the instructed driving mode being one of the left turn driving mode or the right turn driving mode; performing, by the first ECU, recognition on the zone sensor data of the first zone as well as the zone sensor data of the second zone to determine the first recognition information; The method of claim 8 further comprising:

14. 9. The method of claim 8, wherein following a failure of the first ECU, one of the second ECUs is configured to transmit at least one subsequent control signal to at least one vehicle actuator based at least on the subsequently determined second recognition information.

15. The vehicle includes a first electronic control unit (ECU) disposed in a vehicle and capable of communicating with a plurality of second ECUs disposed in the vehicle, each respective second ECU associated with a respective zone of a plurality of zones associated with the vehicle, at least one respective sensor associated with each respective zone for providing zone sensor data in the respective zone to the respective second ECU associated with the respective zone, the first ECU configured to execute executable instructions to: receiving, by the first ECU, the zone sensor data for each of the plurality of zones; performing, by the first ECU, recognition on the zone sensor data from a first zone of the plurality of zones based on an indicated operating mode of the vehicle to determine first recognition information; an operation of receiving, by the first ECU, second recognition information from one or more of the respective second ECUs associated with the respective zones, the respective second ECUs being configured to perform recognition processing on respective zone sensor data from the at least one respective sensor associated with the respective zone with which the respective second ECU is associated; transmitting, by the first ECU, at least one control signal to at least one vehicle actuator based on at least the first identification information and the second identification information; A system configured to perform operations including:

16. 16. The system of claim 15, wherein the first ECU has greater data processing capabilities than the respective second ECU associated with the respective zone.

17. The operation includes: selecting, by the first ECU, zone sensor data from a second zone for performing the recognition based on the indicated driving mode change instruction; and ceasing performance of the recognition on the zone sensor data received from the first zone. The system of claim 15 further comprising:

18. Each of the second ECUs includes: receiving zone sensor data from the set of zone sensors associated with the respective zones associated with the respective second ECUs; reducing an amount of the zone sensor data to obtain reduced sensor data, and performing recognition on the reduced sensor data to obtain recognition information; transmitting the recognition information to the first ECU as a part of the second recognition information; The system of claim 15 configured to:

19. The indicated driving mode of the vehicle is: a left turn driving mode in which the vehicle is approaching a left turn; or A right-turn driving mode in which the vehicle is approaching a right turn. One of the The method comprises: selecting, by the first ECU, the zone sensor data of a second zone among the plurality of zones based on the instructed driving mode being one of the left turn driving mode or the right turn driving mode; performing, by the first ECU, recognition on the zone sensor data of the first zone as well as the zone sensor data of the second zone to determine the first recognition information; The system of claim 15 further comprising:

20. 16. The system of claim 15, wherein following a failure of the first ECU, one of the second ECUs is configured to transmit at least one subsequent control signal to at least one vehicle actuator based at least on the subsequently determined second recognition information.

Images