Method for Implementing Autonomous Driving, Medium, Vehicle-Mounted Computer, and Control System
20230331248 ยท 2023-10-19
Inventors
Cpc classification
B60W2552/53
PERFORMING OPERATIONS; TRANSPORTING
B60W60/001
PERFORMING OPERATIONS; TRANSPORTING
G06V20/52
PHYSICS
International classification
B60W60/00
PERFORMING OPERATIONS; TRANSPORTING
Abstract
A method for implementing autonomous driving and a vehicle-mounted control system includes: obtaining a first signal from at least one first sensor fixedly arranged at a specific location, where the first signal indicates static travelling information related to a lane; obtaining, from a vehicle-mounted sensor, a second signal indicating dynamic travelling information related to a vehicle travelling road; and establishing a travelling route corridor on the basis of at least one of the first signal and the second signal.
Claims
1. A method for implementing autonomous driving, comprising: obtaining a first signal from at least one first sensor that is fixedly arranged at a specific location, wherein the first signal indicates static travelling information related to a lane; obtaining, from a vehicle-mounted sensor, a second signal indicating dynamic travelling information related to a vehicle travelling road; and establishing a travelling route corridor on the basis of at least one of the first signal and the second signal.
2. The method of claim 1, further comprising: obtaining the first signal when a travelling vehicle enters a predetermined range of the specific location.
3. The method of claim 1, wherein the establishing of the travelling route corridor comprises: combining the first signal and the second signal to establish the corridor; or replacing the second signal with the first signal to establish the corridor on the basis of only the first signal, wherein, before a vehicle approaches a predetermined range of the specific location, the corridor is established by using the second signal.
4. The method of claim 3, wherein, within the predetermined range of the specific location, the first signal is continuously received until the first signal can no longer be received.
5. The method of claim 3, wherein: the first sensor comprises a first image sensor configured to capture lane information of a current lane as the first signal; and the vehicle-mounted sensor comprises a second image sensor and a radar device, and the second signal comprises (i) a third signal indicating information about the current lane of the travelling vehicle and that is captured by the second image sensor, and (ii) a fourth signal indicating information about a surrounding environment of the current lane and that is obtained by the radar device, wherein the method further comprises: when the travelling vehicle enters the predetermined range of the specific location, using the first signal to take over the third signal, and establishing the route corridor on the basis of the first signal and the fourth signal.
6. The method of claim 3, wherein: the specific location is a tunnel or bridge opening; and the predetermined range is a predetermined distance before entering and after leaving the tunnel or bridge opening and the entire tunnel or bridge opening.
7. A vehicle-mounted control system, comprising: a receiver configured to obtain a first signal from at least one first sensor fixedly arranged at a specific location, the first signal indicating static travelling information related to a current lane; at least one vehicle-mounted sensor configured to detect dynamic travelling information of a vehicle and output a second signal indicating dynamic travelling information; and a vehicle-mounted computer that establishes a travelling route corridor on the basis of at least one of the first signal and the second signal.
8. The vehicle-mounted control system of claim 7, further comprising: a positioning sensor configured to, when detecting that the travelling vehicle enters a predetermined range of the specific location, trigger the receiver to receive the first signal.
9. The vehicle-mounted control system of claim 7, wherein the vehicle-mounted computer is further configured to: combine the first signal and the second signal to establish the corridor; or use the first signal to take over the second signal to establish the corridor on the basis of only the first signal, wherein, before a vehicle approaches a predetermined range of the specific location, the corridor is established by using the second signal.
10. The vehicle-mounted control system of claim 9, wherein, within the predetermined range of the specific location, the receiver is configured to continuously receive the first signal until the first signal can no longer be received.
11. The vehicle-mounted control system of claim 9, wherein: the first sensor comprises a first image sensor configured to capture lane information of a current lane as the first signal; the vehicle-mounted sensor comprises a second image sensor and a radar device, and the second signal comprises (i) a third signal indicating information about the current lane of the travelling vehicle and that is captured by the second image sensor, and (ii) a fourth signal indicating information about a surrounding environment of the current lane and that is obtained by the radar device, wherein the vehicle-mounted computer is configured to: when the travelling vehicle enters the predetermined range of the specific location, use the first signal to take over the third signal; and establish the route corridor on the basis of the first signal and the fourth signal.
12. The vehicle-mounted control system of claim 9, wherein: the specific location is a tunnel or bridge opening; and the predetermined range is a predetermined distance before entering and after leaving the tunnel or bridge opening and the entire tunnel or bridge opening.
13. The vehicle-mounted control system of claim 8, wherein the positioning sensor is a vehicle-mounted GPS or a vehicle-mounted radar.
14. A vehicle-mounted computer, comprising: a processor; and a memory storing instructions that, when executed by the processor, cause the processor to perform the method of claim 1.
15. A machine-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a vehicle-mounted computer, cause the vehicle-mounted computer to perform the method of claim 1.
Description
BRIEF DESCRIPTION OF THE DRAWINGS
[0009]
[0010]
[0011]
[0012]
[0013]
DETAILED DESCRIPTION OF EMBODIMENTS
[0014] According to embodiments of the present invention, in order to ensure that stable and reliable lane information and lane environment information are provided for vehicles at a specific location such as a tunnel, as shown in
[0015] Therefore, road conditions, such as lane lines, in the tunnel can be clearly seen, and accurate lane information (denoted as Sig_Lane hereinafter) can be obtained. Herein, the lane information includes, but is not limited to, road edges, lane line markings, etc. In addition, laser radars (not shown in the figure) are provided in the tunnel and its turning, so that lane environment conditions, such as a wall of the tunnel, can be detected without any difficulty, and wall location information (denoted as Sig_Wall hereinafter) can be formed. Certainly, it is easily understood that with suitable light and capturing angles, the wall location information Sig_Wall of the tunnel may also be directly obtained from imaging of the camera mounted in the tunnel. The camera S and the radar R may continuously broadcast the lane information Sig_Lane and the environment information Sig_Wall generated after processing, for use by an upcoming vehicle.
[0016] Herein, the lane information Sig_Lane and the environment information Sig_Wall such as a wall are collectively referred to as a road conditions signal SIG. Herein, a wireless transmitter integrated with or discrete from the sensor S or R may be used to send out the road conditions signal SIG. The wireless transmitter herein may be implemented using a known short-range communications protocol in the prior art, such as a cellular V2X protocol, or a 5G new radio V2X protocol, or using other Internet of things protocols.
[0017]
[0018] The vehicle-mounted sensor 102 on the vehicle can collect, in real time, information about road conditions around the current vehicle during travelling. For example, such a vehicle-mounted sensor 102 may be a vision camera and/or a radar, etc., and is configured to capture travelling lane information and lane surrounding environment information. Such lane information is, for example, lane line distribution and the number of lanes on the current road; and the lane environment information is, for example, information about other vehicles on the current lane or an adjacent lane, median strips, and obstacles. Because the lane information and the lane environment information may change at any time during the travelling of the vehicle, the road conditions information captured by the vehicle-mounted sensor 102 is referred to as a dynamic travelling signal dyn_SIG herein. The vehicle-mounted computer 103 may be, for example, a vehicle-mounted MCU, which uses the dynamic road conditions information collected by the vehicle-mounted sensor 102 to establish a travelling corridor, so as to implement safe autonomous driving. Herein, the vehicle-mounted computer 103 may use an existing corridor generation algorithm in the prior art to establish the travelling corridor on the basis of the dynamic road conditions information collected by the vehicle-mounted sensor 102.
[0019] For the entire autonomous driving system, it is highly difficult to achieve comprehensive and accurate environment information detection by capturing data only relying on vehicle sensor information. High-precision maps and positioning, as a type of previously-proven information, can make up for defects in functions of autonomous driving sensors and provide a beyond-line-of-sight awareness capability. For example, information about longitudinal slope and transverse slope at a turning cannot be accurately output by the sensors themselves. When the line of sight is blocked or a curvature is small, beyond-line-of-sight information provided by a high-precision map is more required for planning and controlling the vehicle with a more solid basis. Therefore, as an example, the present invention further integrates a high-precision map for environment prediction. On the basis of a high-precision map provided by a vehicle-mounted positioning sensor (as shown by 104 in
[0020] Apparently, when a vehicle enters a tunnel, for example, from a normal travelling road section, due to a sudden change of ambient light, it is difficult for a visual sensor to collect lane information in the tunnel, or even misjudgment occurs, and the travelling corridor cannot be established. Therefore, according to the present invention, when the vehicle enters the tunnel, a static road conditions signal provided by a sensor S or R in the tunnel is used to independently complete the establishment of the travelling corridor or assist the vehicle-mounted computer 103 to complete the establishment of the travelling corridor. According to an embodiment of the present invention, when the vehicle-mounted sensor detects that the vehicle is approaching the tunnel, the vehicle-mounted computer 103 may receive the static road conditions signal SIG from the tunnel sensor S or R by using the transceiver 101. According to another embodiment, the positioning sensor 104 provided in the vehicle may also be used to detect the existence of a specific location, such as the tunnel. When the positioning sensor 104 detects that the vehicle is about to enter the tunnel, the vehicle-mounted computer 103 receives the static road conditions signal sta_SIG from the tunnel sensor S or R by using the transceiver 101. According to the present invention, in order to distinguish whether the signal from the transceiver 101 is a road conditions signal SIG from the tunnel sensor or a signal from another external device such as an RSU, the road conditions signal SIG may be set to a predetermined format. For example, a fixed identifier ID is set in a packet header of the signal. In this way, the vehicle-mounted computer 103 can perform verification on the basis of the identifier ID when receiving the signal provided by the transceiver.
[0021] When the vehicle-mounted computer 103 confirms that the road conditions signal SIG from the tunnel sensor is received, a corridor generation algorithm may be used to establish the travelling corridor on the basis of the road conditions signal sta_SIG, or the detection signal dyn_SIG of the vehicle-mounted sensor. It should be noted here that when the road conditions signal sta_SIG from the tunnel sensor is used to establish the travelling corridor, the road conditions signal sta_SIG of the tunnel sensor is regarded as a signal dyn_SIG of the vehicle-mounted sensor, and therefore the corridor generation algorithm pre-stored in the vehicle-mounted computer can still be used for implementation, without making any changes to the algorithm.
[0022]
[0023] At step 403, when the vehicle travels into a predetermined range of the tunnel, the vehicle-mounted control system 100 may obtain, by using the transceiver 101, a static road conditions signal sta_SIG in the tunnel from one or more sensors fixedly arranged in the tunnel, including lane conditions and/or lane environment information of the current travelling road, such as information about a location of a tunnel wall relative to a lane. The predetermined range herein may be a predetermined distance before entering the tunnel and the entire length of the tunnel.
[0024] At step 405, the vehicle-mounted computer 103 establishes a travelling route corridor on the basis of at least one of the dynamic travelling signal dyn_SIG and the static road conditions signal sta_SIG. According to an example, although the vehicle has entered the predetermined distance before the tunnel, it is still possible to establish the travelling corridor on the basis of only the dynamic travelling signal dyn_SIG from the vehicle-mounted sensor. However, when the vehicle is about to enter the tunnel, the static road conditions signal sta_SIG from the tunnel sensor may be used instead of the dynamic travelling signal dyn_SIG, to establish the travelling corridor. According to another embodiment, because a radar has no requirement for ambient light, the vehicle may combine the static road conditions signal sta_SIG and the dynamic travelling signal dyn_SIG to establish the travelling corridor. For example, the travelling corridor may be established on the basis of the lane information contained in the static road conditions signal sta_SIG and the wall location information, detected by the radar, in the dynamic travelling signal dyn_SIG, so that the most reliable signal can be optimally used to establish the corridor.
[0025]
[0026] At step 503, the vehicle-mounted control system 100 detects whether the vehicle is approaching the tunnel. Herein, an image captured by the vehicle-mounted visual sensor 102 may be analyzed to determine whether there is a tunnel or a bridge opening, or a positioning signal of a GPS sensor 104 may be used to determine whether a tunnel or a bridge opening is about to appear ahead.
[0027] At step 505, when the vehicle travels into a predetermined range of the tunnel, the transceiver 101 is instructed to obtain a static road conditions signal sta_SIG in the tunnel from one or more sensors fixedly arranged in the tunnel, including lane conditions in the tunnel and/or information about a location of a tunnel wall relative to a lane, for example. The predetermined range herein may be a predetermined distance before entering the tunnel.
[0028] At step 507, the vehicle-mounted control system verifies the static road conditions signal sta_SIG received by using the transceiver 101, including signal quality detection. For example, if a bit error rate is too high, the current signal is discarded, and a subsequent signal continues to be received. When the signal quality detection succeeds, a source of the signal is further to be confirmed. For example, on the basis of an identifier ID in a packet header of the signal, it is determined that the signal comes from a tunnel sensor instead of a roadside unit, and can be used to establish a travelling corridor.
[0029] At step 509, a travelling route corridor is established on the basis of at least one of the dynamic travelling signal dyn_SIG and the static road conditions signal sta_SIG. According to an example, before the vehicle enters the tunnel, the dynamic travelling signal dyn_SIG of the vehicle-mounted sensor is used to establish the travelling corridor. However, when the vehicle is about to enter the tunnel, the static road conditions signal sta_SIG from the tunnel sensor is used instead of the dynamic travelling signal dyn_SIG, to establish the travelling corridor. According to another embodiment, because a radar has no requirement for ambient light, the vehicle may combine the static road conditions signal sta_SIG and the dynamic travelling signal dyn_SIG to establish the travelling corridor. For example, the travelling corridor may be established on the basis of the lane information contained in the static road conditions signal sta_SIG and the wall location information, detected by the radar, in the dynamic travelling signal dyn_SIG.
[0030] At step 511, when the vehicle is about to leave the tunnel, the dynamic signal dyn_SIG obtained by the vehicle-mounted sensor may be used again to establish the travelling corridor. For example, such switching may be initiated when the static signal sta_SIG from the tunnel sensor can no longer be received; or such switching may be initiated on the basis of the positioning signal from the GPS system 104.
[0031] The vehicle-mounted control system and the method of the present invention have been described above in conjunction with specific embodiments, but the present invention is not limited to the foregoing embodiments. For example, the method of the present invention may be implemented by a processor in a vehicle-mounted computer executing a program or instructions stored in a storage medium. A machine-readable medium provided in another embodiment of the present invention stores machine-readable instructions, where the machine-readable instructions, when executed by a vehicle-mounted computer, cause the vehicle-mounted computer to perform any of the foregoing methods. It should be noted that the execution order of the steps in the embodiments of the present invention is not fixed, and can be adjusted as required.
[0032] The present invention is illustrated and described in detail above by means of drawings and preferred embodiments; however, the present invention is not limited to these disclosed embodiments. Based on the plurality of embodiments described above, those skilled in the art would know that code checking means in different embodiments above may be combined to obtain more embodiments of the present invention, and these embodiments also fall within the scope of protection of the present invention.