Detection of road elements

Abstract

A method for detecting road elements that may include (a) detecting predefined identifiers of road elements, in road related information sensed by vehicles; (b) detecting potential identifiers of road elements that differ from the predefined identifiers of road elements, by processing road related information that was acquired by the vehicles during relevant time windows that are related to the detecting of the predefined identifiers; (c) finding actual identifiers of road elements out of the potential identifiers; wherein the findings is based, at least in part, on road related information that was acquired by the vehicles outside the relevant time windows; and (d) updating a database with the actual identifiers.

Description

CROSS REFERENCE

This application claims priority from US provisional patent serial number 62/771,323, filing date Nov. 26, 2018.

BACKGROUND

Autonomous vehicle are required to detect road elements such as junctions, crossing and roundabouts.

Road elements may be detected based on a set of predefined characters such as the existence of traffic lights, specific road signs, zebra crossings.

It has been found that detection that is based on predefined characters may only detect some of the road elements—as these predefined characters do not appear in each road element. For example—only some roundabouts are preceded by appropriate road signs.

There is a goring need to detect road elements in an efficient manner.

SUMMARY

There are provided systems, method and computer readable mediums for detecting road elements.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to understand the invention and to see how it may be carried out in practice, a preferred embodiment will now be described, by way of non-limiting example only, with reference to the accompanying drawings.

FIG. 1 illustrates an example of a vehicle and a remote computerized system;

FIG. 2 illustrates an example of a method;

FIG. 3 illustrates an example of a roundabout and its environment;

FIG. 4 illustrates an example of a roundabout and its environment;

FIG. 5 illustrates an example of a roundabout and its environment;

FIG. 6 illustrates an example of a roundabout and its environment;

FIG. 7 illustrates an example of an image of a roundabout and its environment;

FIG. 8 illustrates an example of a junction and its environment; and

FIG. 9 illustrates an example of timing diagrams.

DETAILED DESCRIPTION OF THE DRAWINGS

Any reference to a system should be applied, mutatis mutandis to a method that is executed by a system and/or to a non-transitory computer readable medium that stores instructions that once executed by the system will cause the system to execute the method.

Any reference to method should be applied, mutatis mutandis to a system that is configured to execute the method and/or to a non-transitory computer readable medium that stores instructions that once executed by the system will cause the system to execute the method.

Any reference to a non-transitory computer readable medium should be applied, mutatis mutandis to a method that is executed by a system and/or a system that is configured to execute the instructions stored in the non-transitory computer readable medium.

The term “and/or” is additionally or alternatively.

The following systems, method and computer readable mediums may use predefined identifiers as road element during an unsupervised process of learning actual identifiers of road elements. The unsupervised learning does not suffer from the limitations of the supervised learning (limited set of predefined identifier, dependency on predefined identifiers that may not exists in each instance of a road element), enhances the detection capabilities of road elements as it is not limited by the set of predefined identifiers, enables a reliable detection of road elements even when the predefined identifiers are not present (or not detected on the fly), may be based on a compact set of predefined identifiers, may be executed by remote computerized system and/or on vehicle mounted processors, may dynamically track changed in the road elements, may use a vast amount of road related information acquired from vehicle (that use relatively cheap sensors, may require a transmission of limited amount of road related information (for example—only acquired during relevant time windows), may be adjustable (selection of actual identifiers out of potential identifiers may be done using adjustable parameters).

Reference is now made to FIG. 1 which is a block diagram of a vehicle 100 that drives a long a road 20 and communicates with a remote computerized system 400.

Vehicle 100 includes an advanced driver-assistance system (ADAS) or autonomous driving system 200, constructed and implemented in accordance with embodiments described herein. For simplicity of explanation the following text will refer to system 200 or to autonomous driving system. Any reference to an autonomous driving system may be applied mutatis mutandis to a Advanced driver-assistance system.

Autonomous driving system 200 may include processing circuitry 210, input/output (I/O) module 220, camera 230, telemetry ECU 240, shock sensor 250, autonomous driving manager 260, and database 270.

Autonomous driving manager 260 may be instantiated in a suitable memory for storing software such as, for example, an optical storage medium, a magnetic storage medium, an electronic storage medium, and/or a combination thereof. It will be appreciated that autonomous driving system 200 may be implemented as an integrated component of an onboard computer system in a vehicle, such as, for example, vehicle 100 from FIG. 1.

Alternatively, system 200 may be implemented and a separate component in communication with the onboard computer system. It will also be appreciated that in the interests of clarity, while autonomous driving system 200 may comprise additional components and/or functionality e.g., for autonomous driving of vehicle 100, such additional components and/or functionality are not depicted in FIG. 1 and/or described herein.

Processing circuitry 210 may be operative to execute instructions stored in memory (not shown). For example, processing circuitry 210 may be operative to execute autonomous driving manager 260.

It will be appreciated that processing circuitry 210 may be implemented as a central processing unit (CPU), and/or one or more other integrated circuits such as application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), full-custom integrated circuits, etc., or a combination of such integrated circuits. It will similarly be appreciated that autonomous driving system 200 may include more than one instance of processing circuitry 210. For example, one such instance of processing circuitry 210 may be a special purpose processor operative to execute autonomous driving manager 260 to perform some, or all, of the functionality of autonomous driving system 200 as described herein.

I/O module 220 may be any suitable communications component such as a network interface card, universal serial bus (USB) port, disk reader, modem or transceiver that may be operative to use protocols such as are known in the art to communicate either directly, or indirectly, with other elements such as, for example, remote computerized system 400, camera 230, telemetry ECU 240, and/or shock sensor 250.

As such, I/O module 220 may be operative to use a wired or wireless connection to connect to remote computerized system 400 via a communications network such as a local area network, a backbone network and/or the Internet, etc. I/O module 220 may also be operative to use a wired or wireless connection to connect to other components of system 200, e.g., camera 230, telemetry ECU 240, and/or shock sensor 250. It will be appreciated that in operation I/O module 220 may be implemented as a multiplicity of modules, where different modules may be operative to use different communication technologies. For example, a module providing mobile network connectivity may be used to connect to remote computerized system 400, whereas a local area wired connection may be used to connect to camera 230, telemetry ECU 240, and/or shock sensor 250.

In accordance with embodiments described herein, camera 230, telemetry ECU 240, and shock sensor 250 represent implementations of sensors. It will be appreciated that camera 230, telemetry ECU 240, and/or shock sensor 250 may be implemented as integrated components of vehicle 100 and may provide other functionality that is the interests of clarity is not explicitly described herein. As described hereinbelow, system 200 may use information about a current driving environment as received from camera 230, telemetry ECU 240, and/or shock sensor 250 to determine to detect road elements such as but not limited to roundabouts, junctions and/or crossings.

Autonomous driving manager 260 may be an application implemented in hardware, firmware, or software that may be executed by processing circuitry 210 to provide driving instructions to vehicle 100.

For example, autonomous driving manager 260 may use images received from camera 230 and/or telemetry data received from telemetry ECU 240 to determine an appropriate driving policy for arriving at a given destination and provide driving instructions to vehicle 100 accordingly. It will be appreciated that autonomous driving manager 260 may also be operative to use other data sources when determining a driving policy, e.g., maps of potential routes, traffic congestion reports, etc.

FIG. 2 illustrates an example of a method 600 for detecting road elements.

Method 600 may start by step 610 of receiving or detecting predefined identifiers of road elements.

Step 610 may include applying a supervised learning process (for example by a neural network or any other machine learning process applied by a machine learning device) on road related information.

For example—images of predefined identifiers of road elements (such as junction traffic signs, roundabout traffic signs, crossing traffic signs, traffic lights, and the like) as well as indications of the content of these images (at least identifying the predefined identifiers) are fed to a neural network/machine learning device thereby training the neural network/machine learning device to identify the predefined identifiers.

Step 610 may include receiving the outcome of supervised learning process.

Step 610 may be followed by step 620 of receiving road related information sensed by vehicles. The road related information may include visual information (for example images acquired by one or more visual sensors of a vehicle), and/or audio information and/or non-visual and non-audio information sensed by the vehicle for example any telemetry information, force, speed, acceleration sensed by the vehicle, and the like.

Additionally or alternatively, at least some of the road related information may be detected by sensors located outside the vehicles—for example traffic monitoring cameras or other sensors.

Step 620 may be followed by step 630 of detecting predefined identifiers of road elements, in road related information sensed by vehicles.

Step 430 may be followed by step 640 of detecting potential identifiers of road elements that differ from the predefined identifiers of road elements.

Step 640 may include processing road related information that was acquired by the vehicles during relevant time windows related to timings of detection of the predefined identifiers by the multiple vehicles. For example assuming that a vehicle sensed a predefined identifier at point of time T1 then the vehicle may transmit and/or process road related information within a relevant time window that is related to T1 in the sense that there is a known timing relationship between T1 and the relevant time window. The relevant time window may or may not include T1. The term “sensed” may refer to any one of the acquisition of the predefined identifier by a sensor, to the determination (detection) that the predefined identifier was sensed, and the like. For example—an image sensor may acquire an image of a predefined identifier and the system may identify the predefined identifier in the image at another point of time.

It should be noted that different vehicle may define the same relevant time window in relation to the sensing of the same predefined identifier—but at least two vehicles may define different relevant time windows in relation to the sensing of the same predefined identifier. Differences may stem from differences in the sensing process, from different processing and/or transmission and/or memory resources, and the like.

The relevant time window may start before T1, may start at T1, may start after T1, may end at T1, may end after T1, and the like.

The length and/or any timing parameter of any relevant time window may fulfill at least one of the following

• • be fixed (for example 0.5, 1, 2, 10, 20, 30, 40, 60, 90, 120, 180 seconds or more).
  • change over time.
  • depend on the potential identifier.
  • depend on whether the predefined identifier is expected to preceded the road element.
  • depend on whether the predefined identifier is expected to follow the road element.
  • depend on resources (at least one communication, storage, processing) of the vehicle.
  • depend on resources (at least one communication, storage, processing) of the remote computerized system.
  • depend on the uniqueness and/or confidence level associated with the predefined identifier, and the like. For example a longer time window may be allocated to a predefined identifier that is unique to roundabouts and is detected by a highly reliable sensor. Shorter time window may be allocated to predefined identifiers that are detected by less reliable sensors and/or are detected at bad conditions (for example low visibility) and/or are less unique to the road element.

Step 640 may include searching for potentially relevant objects and/or potentially relevant events that appear in the relevant road related information. A relevant road related information was acquired during at least one relevant time windows.

A potentially relevant event may be a behavior of at least one object. For example—a behavior of the vehicle that senses the road related information, the behavior of one or more other vehicles, the behavior or one or more pedestrians, or a combination of at least two of said behaviors.

A potentially relevant object may be an object that appears in the relevant road related information.

Step 640 may be followed by step 650 of finding actual identifiers of road elements out of the potential identifiers. The findings is based, at least in part, on road related information that was acquired by the vehicles outside the relevant time windows.

The finding may include searching for actual identifiers that will identify (with a first certain probability) road elements of interest (such as roundabouts, crossings and junctions) but not identify (at a second certain probability) road segments that are not interesting.

The finding of the actual identifiers may aim to achieve a desired tradeoff between detection parameters such as false detection rate, positive detection rate, and the like.

Step 650 may include at least one out of:

• • Calculating one or more attributes related to the potentially relevant objects.
  • Calculating one or more attributes related to the potentially relevant events.
  • Calculating one or more attributes related to a group of at least one potentially relevant object and at least one potentially relevant event.
  • Determining whether a potential relevant object is an actual identifier based on the value of one or more attributes associated with the potential relevant object.
  • Determining whether a potential relevant event is an actual identifier based on the value of one or more attributes associated with the potential relevant event.
  • Determining whether a combination of potential relevant objects is an actual identifier based on the value of one or more attributes associated with the combination of potential relevant objects.
  • Determining whether a combination of potential relevant events is an actual identifier based on the value of one or more attributes associated with the combination of potential relevant events.
  • Determining whether a group of at least one potential relevant event and at least one potential relevant object is an actual identifier based on the value of one or more attributes associated with the group.
  • Determining whether a potential relevant object is an actual identifier based on the value of one or more attributes associated with the potential relevant object and one or more attributes related to one or more other potential relevant events and/or one or more attributes related to one or more other potential relevant objects.
  • Determining whether a potential relevant event is an actual identifier based on the value of one or more attributes associated with the potential relevant event and one or more attributes related to one or more other potential relevant events and/or one or more attributes related to one or more other potential relevant objects.
  • Determining whether a combination of potential relevant objects is an actual identifier based on the value of one or more attributes associated with the combination of potential relevant objects and one or more attributes related to one or more other potential relevant events and/or one or more attributes related to one or more other potential relevant objects.
  • Determining whether a combination of potential relevant events is an actual identifier based on the value of one or more attributes associated with the combination of potential relevant events and one or more attributes related to one or more other potential relevant events and/or one or more attributes related to one or more other potential relevant objects.
  • Determining whether a group of at least one potential relevant event and at least one potential relevant object is an actual identifier based on the value of one or more attributes associated with the group and one or more attributes related to one or more other potential relevant events and/or one or more attributes related to one or more other potential relevant objects.

An attribute may include, for example, at least one out of:

• • A number of appearances of at least one potentially relevant object within one or more relevant time windows.
  • A number of appearances of at least one potentially relevant object within one or more sub-sets of one or more relevant time windows.
  • A pattern of appearances of at least one potentially relevant object (for example a number of sequences of continuous appearances of at least one potentially relevant object) within one or more relevant time windows.
  • A pattern of appearances of at least one potentially relevant object within one or more sub-sets of one or more relevant time windows.
  • A number of concurrent appearances of multiple potentially relevant objects within one or more relevant time windows.
  • A number of concurrent appearances of multiple potentially relevant objects within one or more sub-sets of one or more relevant time windows.
  • A number non-concurrent appearances of multiple potentially relevant objects within one or more relevant time windows.
  • A number of non-concurrent appearances of multiple potentially relevant objects within one or more sub-sets of one or more relevant time windows.
  • A number of partially concurrent appearances of multiple potentially relevant objects within one or more relevant time windows. Partially concurrent means concurrent appearances (for example at a certain point in time Tx) of two of more potentially relevant objects and an appearance of yet other one or more potentially relevant objects at one or other points in time (that differs from Tx).
  • A number of partially concurrent appearances of multiple potentially relevant objects within one or more sub-sets of one or more relevant time windows.
  • A number of appearances of at least one potentially relevant event within one or more relevant time windows.
  • A number of appearances of at least one potentially relevant event within one or more sub-sets of one or more relevant time windows.
  • A pattern of appearances of at least one potentially relevant event (for example a number of sequences of continuous appearances of at least one potentially relevant event) within one or more relevant time windows.
  • A pattern of appearances of at least one potentially relevant event within one or more sub-sets of one or more relevant time windows.
  • A number of concurrent appearances of multiple potentially relevant events within one or more relevant time windows.
  • A number of concurrent appearances of multiple potentially relevant events within one or more sub-sets of one or more relevant time windows.
  • A number non-concurrent appearances of multiple potentially relevant events within one or more relevant time windows.
  • A number of non-concurrent appearances of multiple potentially relevant events within one or more sub-sets of one or more relevant time windows.
  • A number of partially concurrent appearances of multiple potentially relevant events within one or more relevant time windows.
  • A number of partially concurrent appearances of multiple potentially relevant event within one or more sub-sets of one or more relevant time windows.
  • A number of concurrent appearances of at least one potentially relevant object and at least one potentially relevant event within one or more relevant time windows.
  • A number of concurrent appearances of at least one potentially relevant object and at least one potentially relevant event within one or more sub-sets of one or more relevant time windows.
  • A number non-concurrent appearances of at least one potentially relevant object and at least one potentially relevant event within one or more relevant time windows.
  • A number of non-concurrent appearances of at least one potentially relevant object and at least one potentially relevant event within one or more sub-sets of one or more relevant time windows.
  • A number of partially concurrent appearances of at least one potentially relevant object and at least one potentially relevant event within one or more relevant time windows.
  • A number of partially concurrent appearances at least one potentially relevant object and at least one potentially relevant event within one or more sub-sets of one or more relevant time windows.

It should be noted that the attribute is not limited to numbers or patterns and other attributes may be calculated for example the attribute may be related to location, and/or popularity, and/or frequency, and/or correlation, and/or timing, and the like.

When there are multiple potentially relevant objects then the attribute may be calculated on all possible combinations of any two or more potentially relevant objects of the multiple potentially relevant objects, or on a part of all of the possible combinations.

When there are multiple potentially relevant events then the attribute may be calculated on all possible combinations of any two or more potentially relevant events of the multiple potentially relevant events, or on a part of all of the possible combinations.

When there is a group of at least one potentially relevant object and at least one potentially relevant event then the attribute may be calculated on all possible combinations of any two or more members of the group, or on a part of all of the possible combinations.

Additionally or alternatively, step 650 may include at least one out of

• • Calculating popularities of the potential identifiers within the relevant time windows.
  • Calculating popularities of the potential identifiers outside the relevant time windows.
  • Determining a uniqueness of the different combinations of potential identifiers based on the popularities of the different combinations of potential identifiers within and outside the relevant time windows.
  • Defining at least one combination of potential identifiers as an actual identifier based on a uniqueness of the at least one combination of potential identifiers.
  • Performing an unsupervised learning process.
  • Classifying the actual identifiers to (i) preceding actual identifiers that are detected before reaching the road elements, and (ii) following actual identifiers that are detected after reaching the road elements.

Step 650 may be followed by step 660 of responding to the finding. The responding may include at least one out of (a) transmitting to one or more vehicle the actual identifiers, (b) updating a database of road element identifiers, (c) validating at least one road element identifier, (d) controlling a driving operation of the vehicle based on the finding, and the like.

Step 660 may include updating a data structure of road element identifiers that initially stored the predefined identifiers of road elements, with the actual identifiers of road elements.

Method 600 may be executed by the remote computerized system. Alternatively, method 600 may be executed by system 200. Alternatively, method 200 may be executed in part by a vehicle and in part by the remote computerized system.

FIG. 3 illustrates a roundabout 520 that has three arms 511, 512 and 513, and a vehicle VH1501 that approaches the roundabout (from arm 511), drives within the roundabout and finally exits the roundabout and drives in arm 513. The driving pattern is denoted 501′.

The roundabout is preceded by a roundabout related traffic sign 571 that may be regarded as a predefined identifier of the roundabout.

The vehicle VH1 may acquire road related information while driving. The acquisition may occur regardless of the sensing of the predetermined identifier (the acquisition may be performed in a continuous or non-continuous manner).

The vehicle may first sense the predetermined identifier at an initial point of time—before reaching the roundabout.

The initial point in time may start a relevant time window—or may trigger (after a certain delay) the beginning of the relevant time window. It should be noted that once the predefined identifier is detected the time window may be defined to include points of time that precede the initial point of time.

During the relevant time window the vehicle may acquire road related information while the vehicle approaches the roundabout and/or while driving in the roundabout and/or exiting the roundabout and even at least a predefined period after exiting the roundabout.

The road related information may be processed to detect potential identifiers of the roundabout.

These potential identifiers may include at least out of first tree 531, first cross road 551, second cross road 552, third cross road 553, second tree 532, outer periphery 522 of the roundabout, any feature related to the inner circle of the roundabout such as inner circle border 521, a fountain 523 located at the center of the roundabout, at least a part of the driving pattern 501′ (stopping before reaching the roundabout, turning within the roundabout, exiting from the roundabout), or any combinations of said objects and/or behaviors (for example other cars turning, other cars slowing down, pedestrians wait and then cross). The relationships (spatial and/or timing relationships) between objects and/or events may also be taken into account-such as the distances between the cross roads and their relative orientations). Yet another example of a potential identifier may include tire skid marks at the roundabout—for example on the periphery of the inner circle of the roundabout.

Some of these potential identifiers (such as outer periphery 522 of the roundabout) may be deemed as actual identifiers while others (such as first tree 531 and second tree 532, asphalt sections that may appear in each image) may be rejected. The trees are not unique to roundabouts and may be found in road related information obtained outside the relevant time window.

FIG. 4 illustrates a roundabout 520 that has three arms 511, 512 and 512 and a vehicle VH1501 that approaches the roundabout (from arm 511), drives within the roundabout and finally exits the roundabout and drives in arm 513. The driving pattern is denoted 501′.

The roundabout is preceded by a roundabout related traffic sign 571 that may be regarded as a predefined identifier of the roundabout.

The potential identifiers may include at least out of first tree 531, second tree 532, forth tree 534, building 561, first pedestrian 541, second pedestrians 542, first cross road 551, second cross road 552, third cross road 553, outer periphery 522 of the roundabout, any feature related to the inner circle of the roundabout such as inner circle border 521, a third tree 533 (located at the center of the roundabout), at least a part of the driving pattern 501′ (stopping before reaching the roundabout, turning within the roundabout, exiting from the roundabout), or any combinations of said objects and/or behaviors. For example an potential identifier may be related to a behavior of one or more pedestrians out of first pedestrian 541 and second pedestrians 542.

The relationships (spatial and/or timing relationships) between objects and/or events may also be taken into account—such as the distances between the cross roads and their relative orientations).

Some of these potential identifiers (such as outer periphery 522 of the roundabout) may be deemed as actual identifiers while others (such as first tree 531 and second tree 532, forth tree 532, building 561, pedestrians, asphalt sections that may appear in each image) may be rejected. The trees are not unique to roundabouts and may be found in road related information obtained outside the relevant time window.

FIG. 4 illustrates that the vehicle acquires images—(a) N1 images I1(1)-I1(N1) 580(1)-580(N1) before reaching the roundabout, (b) (N2−N1) images I1(N1+1)-I1(N2) 580(N1+1)-580(N2) while driving in the roundabout, and (c) (N3−N2) images I1(N2+1)-I1(N3) 580(N2+1)-580(N3) after exiting the roundabout.

Images I1(1)-I1(N2) may be acquired during a relevant time window.

Images I1(1)-I1(N1) are acquired before entering the roundabout and may be used for predicting an arrival of the vehicle to the roundabout.

Images I1(1)-I1(N1) are acquired when driving in the roundabout and can be used to verify the prediction.

FIG. 5 illustrates a roundabout 520 that has three arms 511, 512 and 512 and a vehicle VH1501 that approaches the roundabout (from arm 511), drives within the roundabout and finally exits the roundabout and drives in arm 513. The driving pattern is denoted 501′.

FIG. 5 illustrates that the vehicle acquires sensed information—(a) N1 sensed information S1(1)-S1(N1) 581(1)-581(N1) before reaching the roundabout, (b) (N2−N1) sensed information S1(N1+1)-S1(N2) 581(N1+1)-581(N2) while driving in the roundabout, and (c) (N3−N2) sensed information S1(N2+1)-S1(N3) 581(N2+1)-581(N3) after exiting the roundabout.

Sensed information S1(1)-S1(N2) may be acquired during a relevant time window.

Sensed information S1(1)-S1(N1) are acquired before entering the roundabout and may be used for predicting an arrival of the vehicle to the roundabout.

Sensed information S1(1)-1(N1) are acquired when driving in the roundabout and can be used to verify the prediction.

The sensed information may be visual information, may be audio information, may be non-visual and non-audio information, or be combination of information of various types—for example a combination of audio and video, a combination of acceleration and/or speed and/or telemetry readings, and the like.

FIG. 6 illustrates a roundabout 520 that has three arms 511, 512 and 512 and a vehicle VH1501 that approaches the roundabout (from arm 511), drives within the roundabout and finally exits the roundabout and drives in arm 513. The driving pattern is denoted 501′.

The roundabout is not preceded by a roundabout related traffic sign 571 that may be regarded as a predefined identifier of the roundabout.

Despite the absence of the predefined identifier—the roundabout may be detected based on actual identifiers such as (a) outer periphery 522 of the roundabout, (b) any feature related to the inner circle of the roundabout such as inner circle border 521, (c) at least a part of the driving pattern 501′ (stopping before reaching the roundabout, turning within the roundabout, exiting from the roundabout), or any combinations of said objects and/or behaviors.

FIG. 7 illustrates an image acquired by a vehicle that entered a roundabout.

The image include a curved road 502 within the roundabout, an ring shaped zone 603 that surrounds the inner circle 604 of the roundabout, sand 608 and few bushes or plants 605 located in the inner circle 604, various trees 606 that surround the roundabout, a pavement 605 that surrounds the roundabout, and a vehicle 601 that is about to enter the roundabout.

Even at the absence of a roundabout related traffic sign the vehicle may detect the roundabout based on actual identifier such as the curved road 502 within the roundabout, the ring shaped zone 603 that surrounds the inner circle 604 of the roundabout, a driving pattern of the vehicle that acquired the image when entering the roundabout and/when turning in the roundabout, and the like.

FIG. 8 illustrates a T-junction 590 that has three arms 511, 512 and 512 and a vehicle VH1501 that approaches the junction (from arm 512), enters the junction and turns to the right- to arm 512, and drives in arm 513. The driving pattern is denoted 501′.

The junction is preceded by a junction related traffic sign 572 that may be regarded as a predefined identifier of the junction.

The vehicle VH1 may acquire road related information while driving.

The vehicle may first sense the predetermined identifier at an initial point of time—before reaching the j unction. The initial point in time may start a relevant time window—or may trigger (after a certain delay) the beginning of the relevant time window.

During the relevant time window the vehicle may acquire road related information while the vehicle approaches the junction and/or while driving in the junction and/or exiting the junction and even at least a predefined period after exiting the junction.

The road related information may be processed to detect potential identifiers of the junction.

These potential identifiers may include at least out of first tree 531, first cross road 551, second cross road 552, third cross road 553, third tree 533, edge 591 of the junction that faces arm 512, at least a part of the driving pattern 501′ (stopping before reaching the junction, turning within the junction, exiting from the junction), or any combinations of said objects and/or behaviors. The relationships (spatial and/or timing relationships) between objects and/or events may also be taken into account-such as the distances between the cross roads and their relative orientations).

Some of these potential identifiers (such as edge 591) may be deemed as actual identifiers while others (such as first tree 531 and third tree 533, asphalt sections that may appear in each image) may be rejected. The trees are not unique to junctions and may be found in road related information obtained outside the relevant time window.

Various predefined identifiers as well as actual identifiers may be used. Road related information

FIG. 9 illustrates examples of timing diagrams.

Event 661 represents a sensing of a predefined identifier by a vehicle. The sensing occurred at point of time T1. Various relevant time windows 671, 672 and 673 may be defined—all including T1. T2 represents an estimated moment of reaching the road element identified by the predefined identifier.

Event 662 represents a sensing of a predefined identifier by a vehicle. The sensing occurred at point of time T1. Various relevant time windows 674, 675 and 676 may be defined—all including T1. T2 represents an estimated moment of reaching the road element identified by the predefined identifier.

Event 661 is expected to occur before reaching the road element while event 662 is expected to occur after reaching the road element.

Any time window may be of any length, any timing relationships may exist from any time window and the sensing of the predefined event.

There may be provided a method for driving an autonomous vehicle, the method may include:

• • a. Sensing by a vehicle road related information that is indicative of predefined identifiers of road elements.
  • b. Transmitting the road related information to a computerized system such as remote computerized system located outside the vehicle and/or to a computer located in the vehicle.
  • c. Receiving actual identifiers of the road elements.
  • d. Sensing new (new—sensed after step C) road related information by the vehicle.
  • e. Searching in the new road related information for at least one of the actual identifiers.
  • f. Detecting a road element identified by at least one of the actual identifiers.
  • g. Performing a driving related operation based on the detection of the road element.

The terms “including”, “comprising”, “having”, “consisting” and “consisting essentially of” are used in an interchangeable manner. For example—any method may include at least the steps included in the figures and/or in the specification, only the steps included in the figures and/or the specification. The same applies to the system and the mobile computer.

It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Further, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.

In the foregoing specification, the invention has been described with reference to specific examples of embodiments of the invention. It will, however, be evident that various modifications and changes may be made therein without departing from the broader spirit and scope of the invention as set forth in the appended claims.

Moreover, the terms “front,” “back,” “top,” “bottom,” “over,” “under” and the like in the description and in the claims, if any, are used for descriptive purposes and not necessarily for describing permanent relative positions. It is understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in other orientations than those illustrated or otherwise described herein.

Those skilled in the art will recognize that the boundaries between logic blocks are merely illustrative and that alternative embodiments may merge logic blocks or circuit elements or impose an alternate decomposition of functionality upon various logic blocks or circuit elements. Thus, it is to be understood that the architectures depicted herein are merely exemplary, and that in fact many other architectures can be implemented which achieve the same functionality.

Any arrangement of components to achieve the same functionality is effectively “associated” such that the desired functionality is achieved. Hence, any two components herein combined to achieve a particular functionality can be seen as “associated with” each other such that the desired functionality is achieved, irrespective of architectures or intermedial components. Likewise, any two components so associated can also be viewed as being “operably connected,” or “operably coupled,” to each other to achieve the desired functionality.

Furthermore, those skilled in the art will recognize that boundaries between the above described operations merely illustrative. The multiple operations may be combined into a single operation, a single operation may be distributed in additional operations and operations may be executed at least partially overlapping in time. Moreover, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be altered in various other embodiments.

Also for example, in one embodiment, the illustrated examples may be implemented as circuitry located on a single integrated circuit or within a same device. Alternatively, the examples may be implemented as any number of separate integrated circuits or separate devices interconnected with each other in a suitable manner.

Also for example, the examples, or portions thereof, may implemented as soft or code representations of physical circuitry or of logical representations convertible into physical circuitry, such as in a hardware description language of any appropriate type.

Also, the invention is not limited to physical devices or units implemented in non-programmable hardware but can also be applied in programmable devices or units able to perform the desired device functions by operating in accordance with suitable program code, such as mainframes, minicomputers, servers, workstations, personal computers, notepads, personal digital assistants, electronic games, automotive and other embedded systems, cell phones and various other wireless devices, commonly denoted in this application as ‘computer systems’.

However, other modifications, variations and alternatives are also possible. The specifications and drawings are, accordingly, to be regarded in an illustrative rather than in a restrictive sense.

In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word ‘comprising’ does not exclude the presence of other elements or steps then those listed in a claim. Furthermore, the terms “a” or “an,” as used herein, are defined as one as or more than one. Also, the use of introductory phrases such as “at least one” and “one or more” in the claims should not be construed to imply that the introduction of another claim element by the indefinite articles “a” or “an” limits any particular claim containing such introduced claim element to inventions containing only one such element, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “an.” The same holds true for the use of definite articles. Unless stated otherwise, terms such as “first” and “second” are used to arbitrarily distinguish between the elements such terms describe. Thus, these terms are not necessarily intended to indicate temporal or other prioritization of such elements the mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage.

Any system, apparatus or device referred to this patent application includes at least one hardware component.

While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.

Any combination of any component of any component and/or unit of system that is illustrated in any of the figures and/or specification and/or the claims may be provided.

Any combination of any system illustrated in any of the figures and/or specification and/or the claims may be provided.

Any combination of any set of pool cleaning robots illustrated in any of the figures and/or specification and/or the claims may be provided.

Any combination of steps, operations and/or methods illustrated in any of the figures and/or specification and/or the claims may be provided.

Any combination of operations illustrated in any of the figures and/or specification and/or the claims may be provided.

Any combination of methods illustrated in any of the figures and/or specification and/or the claims may be provided.

Claims

1. A method for detecting road elements, the method comprises: detecting predefined identifiers of road elements, in road related information sensed by vehicles;detecting potential identifiers of road elements that differ from the predefined identifiers of road elements, by processing road related information that was acquired by the vehicles during relevant time windows that are related to the detecting of the predefined identifiers;finding actual identifiers of road elements out of the potential identifiers; wherein the finding is based, at least in part, on road related information that was acquired by the vehicles outside the relevant time windows; andupdating a database with the actual identifiers.

2. The method according to claim 1 wherein the finding of the actual identifiers is responsive to (a) popularities of the potential identifiers within the relevant time windows and (b) popularities of the potential identifiers outside the relevant time windows.

3. The method according to claim 1 wherein the finding of the actual identifiers comprises (a) calculating popularities of different combinations of potential identifiers within the relevant time windows; (b) calculating popularities of the different combinations of potential identifiers outside the relevant time windows; (c) determining a uniqueness of the different combinations of potential identifiers based on the popularities of the different combinations of potential identifiers within and outside the relevant time windows, (d) and defining at least one combination of potential identifiers as an actual identifier based on a uniqueness of the at least one combination of potential identifiers.

4. The method according to claim 1 comprising generating the predefined identifiers of road elements by performing a supervised learning process.

5. The method according to claim 1 wherein the steps of (a) detecting of the potential identifiers, and (b) finding actual identifiers, are included in a unsupervised learning process.

6. The method according to claim 1 wherein the actual identifiers identify corresponding road elements, wherein the method comprising classifying the actual identifiers to (i) preceding actual identifiers that appear in the road related information before predefined identifiers of their corresponding road elements, and (ii) following actual identifiers that appear in the road related information after the predefined identifiers of their corresponding road elements.

7. The method according to claim 6 comprising predicting an arrival of a vehicle to a road element of a certain type based on at least one preceding actual identifier associated with the certain type of road element.

8. The method according to claim 6 comprising verifying an arrival of a vehicle to a road element of a certain type based on at least one following actual identifier associated with the certain type of road element.

9. The method according to claim 1 comprising updating a data structure of road element identifiers that initially stored the predefined identifiers of road elements, with the actual identifiers of road elements.

10. The method according to claim 1 wherein at least one actual identifier is a visual actual identifier.

11. The method according to claim 1 wherein at least one actual identifier is an audio actual identifier.

12. The method according to claim 1 wherein at least one actual identifier is a non-visual and non-audio actual identifier.

13. The method according to claim 1 wherein at least one actual identifier is an accelerometer.

14. The method according to claim 1 wherein at least one actual identifier represents an object.

15. The method according to claim 1 wherein at least one actual identifier represents a behavior of an object.

16. The method according to claim 1 wherein each potential identifier comprises a label that identifies the potential identifier.

17. The method according to claim 16, wherein the finding of the actual identifiers is responsive to (a) popularity of the label within the relevant time windows and (b) a popularity of the label outside the relevant time windows.

18. The method according to claim 1 comprising transmitting, to one or more vehicles the actual identifiers.

19. A method for detecting road elements, the method comprises: detecting predefined identifiers of road elements, in road related information sensed by at least one vehicle; detecting potential identifiers of road elements that differ from the predefined identifiers of road elements, by processing road related information that was acquired by the at least one vehicle during relevant time windows that are related to the detecting of the predefined identifiers; finding actual identifiers of road elements out of the potential identifiers; wherein the finding is based, at least in part, on road related information that was acquired by the at least one vehicle outside the relevant time windows; and updating a database with the actual identifiers.

20. A non-transitory computer readable medium that stores instructions that once executed by a computerized system causes the computerized system to detect road elements, by: detecting predefined identifiers of road elements, in road related information sensed by vehicles;detecting potential identifiers of road elements that differ from the predefined identifiers of road elements, by processing road related information that was acquired by the vehicles during relevant time windows that are related to the detecting of the predefined identifiers;finding actual identifiers of road elements out of the potential identifiers; wherein the finding is based, at least in part, on road related information that was acquired by the vehicles outside the relevant time windows; andupdating a database with the actual identifiers.

21. The non-transitory computer readable medium according to claim 20 wherein the finding of the actual identifiers is responsive to (a) popularities of the potential identifiers within the relevant time windows and (b) popularities of the potential identifiers outside the relevant time windows.

22. The non-transitory computer readable medium according to claim 20 wherein the finding of the actual identifiers comprises (a) calculating popularities of different combinations of potential identifiers within the relevant time windows; (b) calculating popularities of the different combinations of potential identifiers outside the relevant time windows; (c) determining a uniqueness of the different combinations of potential identifiers based on the popularities of the different combinations of potential identifiers within and outside the relevant time windows, (d) and defining at least one combination of potential identifiers as an actual identifier based on a uniqueness of the at least one combination of potential identifiers.

23. The non-transitory computer readable medium according to claim 20 that stores instructions for generating the predefined identifiers of road elements by performing a supervised learning process.

24. The non-transitory computer readable medium according to claim 20 wherein the steps of (a) detecting of the potential identifiers, and (b) finding actual identifiers, are included in an unsupervised learning process.

25. The non-transitory computer readable medium according to claim 20 wherein the actual identifiers identify corresponding road elements, wherein the non-transitory computer readable medium stores instructions for classifying the actual identifiers to (i) preceding actual identifiers that appear in the road related information before predefined identifiers of their corresponding road elements, and (ii) following actual identifiers that appear in the road related information after the predefined identifiers of their corresponding road elements.

26. The non-transitory computer readable medium according to claim 25 that stores instructions for predicting an arrival of a vehicle to a road element of a certain type based on at least one preceding actual identifier associated with the certain type of road element.

27. The non-transitory computer readable medium according to claim 25 that stores instructions for verifying an arrival of a vehicle to a road element of a certain type based on at least one following actual identifier associated with the certain type of road element.

28. The non-transitory computer readable medium according to claim 20 that stores instructions for updating a data structure of road element identifiers that initially stored the predefined identifiers of road elements, with the actual identifiers of road elements.

29. The non-transitory computer readable medium according to claim 20 wherein at least one actual identifier is a visual actual identifier.