A mode switching method, device, equipment and medium of an automatic driving sanitation vehicle

Abstract

A mode switching method, device, equipment and medium of an automatic driving sanitation vehicle are disclosed. The method comprises: acquiring, by an automatic driving system in the automatic driving sanitation vehicle, a current position and a non-sweeping area of the automatic driving sanitation vehicle from a semantic map in real time; determining whether a distance to be traveled between the current position and the non-sweeping area is less than or equal to a preset switching threshold; if yes, continuously acquiring surrounding environment information and a green light countdown; determining whether the automatic driving sanitation vehicle meets a mode switching condition according to the surrounding environment information, the current position and the green light countdown; if yes, switching a driving mode of the automatic driving sanitation vehicle from a low-speed sweeping mode to a transition mode until the automatic driving sanitation vehicle passes through the non-sweeping area, thereby reducing the stopping of the automatic driving sanitation vehicle due to the change of a traffic light at an intersection, reducing the influence on the passing probability of other social vehicles and traffic participants, and significantly improving the passing ability of the automatic driving sanitation vehicle at the intersection.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a mode switching method, apparatus, device, and medium for an autonomous sanitation vehicle. Background Technology

[0002] With the continuous development of autonomous driving technology, it is being used in more and more scenarios, such as autonomous sanitation vehicles, which are usually used for low-speed sweeping and have relatively fixed routes, making them very suitable for the use of autonomous driving systems.

[0003] As an autonomous driving technology that makes driving motor vehicles more convenient, its driving methods should naturally comply with existing traffic rules. When autonomous sanitation vehicles pass through traffic light intersections, they are usually limited by a combination of factors such as traffic light timing, vehicle speed, and road conditions.

[0004] Currently, autonomous sanitation vehicles pass through intersections at normal low operating speeds. When they reach the middle of the intersection, the cross traffic light may have already turned green, and the autonomous sanitation vehicle may stop in the middle of the intersection, affecting the passage of other vehicles and traffic participants, thereby increasing driving safety risks. Summary of the Invention

[0005] This invention provides a mode switching method, device, equipment, and medium for autonomous sanitation vehicles, which solves the technical problem that autonomous sanitation vehicles may stop when passing through intersections under existing operating modes, affecting the passage of other vehicles and traffic participants, thereby increasing driving safety risks.

[0006] The first aspect of this invention provides a mode switching method for an autonomous sanitation vehicle, comprising:

[0007] The current location and non-cleaned areas of the autonomous sanitation vehicle are obtained in real time from the semantic map;

[0008] Determine whether the distance to be traveled between the current location and the non-cleaned area is less than or equal to a preset switching threshold;

[0009] If so, it will continue to acquire information about the surrounding environment and the green light countdown;

[0010] Based on the surrounding environment information, the current location, and the green light countdown, determine whether the autonomous sanitation vehicle meets the mode switching conditions;

[0011] If the conditions are met, the driving mode of the autonomous sanitation vehicle will be switched from low-speed sweeping mode to transfer mode until the autonomous sanitation vehicle passes through the non-sweeping area.

[0012] Optionally, the method further includes:

[0013] If it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions, then the autonomous sanitation vehicle shall be stopped.

[0014] Jump to execute the steps of continuously acquiring surrounding environmental information and green light countdown.

[0015] Optionally, the surrounding environment information includes following information and stop line position; the step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current position, and the green light countdown includes:

[0016] Calculate the relative distance between the current position and the stop line position;

[0017] The relative distance and the turning speed of the autonomous sanitation vehicle are used to calculate the vehicle's front movement time;

[0018] Calculate the first time difference between the vehicle's forward movement time and the green light countdown;

[0019] If the following information indicates that there is no preceding vehicle and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0020] If the following information indicates that there is no preceding vehicle, and the first time difference is less than or equal to a preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0021] Optionally, the step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current location, and the green light countdown further includes:

[0022] If the following information indicates the presence of a vehicle ahead and the green light countdown is obtained in real time, then the millimeter-wave radar is invoked to detect the first acceleration of the vehicle ahead.

[0023] If the first acceleration exceeds the acceleration threshold and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0024] If the first acceleration does not exceed the acceleration threshold, or the first time difference is less than or equal to the preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0025] Optionally, the step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current location, and the green light countdown further includes:

[0026] If the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing, then millimeter-wave radar and lidar are invoked to detect the traffic flow trend and the second acceleration corresponding to the vehicle ahead.

[0027] If the traffic flow trend is an accelerating trend, and the second acceleration exceeds the acceleration threshold, and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0028] If the traffic flow trend is a deceleration trend and the distance between the vehicle and the vehicle in front is less than a preset safe following distance threshold, then it is determined that the autonomous driving sanitation vehicle does not meet the mode switching conditions, and the current speed of the autonomous driving sanitation vehicle is reduced to the braking speed according to a preset ratio.

[0029] Optionally, the step of calling millimeter-wave radar and lidar to detect the traffic flow trend and the second acceleration corresponding to the preceding vehicle if the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing includes:

[0030] If the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing, then the millimeter-wave radar is invoked to detect the second acceleration corresponding to the vehicle ahead.

[0031] The lidar is invoked to obtain the vehicle point cloud corresponding to the adjacent lane, and the millimeter-wave radar is invoked to obtain the third acceleration corresponding to the vehicle point cloud;

[0032] If the third acceleration exceeds the first acceleration threshold, the traffic flow movement trend is determined to be an accelerating movement trend.

[0033] If the third acceleration does not exceed the second acceleration threshold, the traffic flow trend is determined to be a deceleration trend.

[0034] Optionally, the step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current location, and the green light countdown further includes:

[0035] If the following information indicates the presence of a vehicle ahead and the green light countdown is missing, then the movement strategy set up within the autonomous sanitation vehicle is detected.

[0036] If the movement strategy is a waiting-at-the-light strategy, the current speed of the autonomous sanitation vehicle is reduced to a slow braking speed according to a preset ratio until the green light countdown is obtained again, and then the step of calculating the relative distance between the current position and the stop line position is executed.

[0037] If the movement strategy is a guessing strategy, then the green light countdown in the last frame obtained will be used as the input time.

[0038] Calculate the second time difference between the vehicle head movement time and the input time;

[0039] If the second time difference is greater than the switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0040] If the second time difference is less than or equal to the switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0041] Optionally, if the condition is met, the step of switching the driving mode of the autonomous sanitation vehicle from low-speed cleaning mode to transfer mode until the autonomous sanitation vehicle passes through the non-cleaned area includes:

[0042] If the autonomous sanitation vehicle meets the mode switching conditions, the speed limit of the intersection corresponding to the non-sweeping area is read from the semantic map.

[0043] Based on the matching results between the speed limit at the intersection and the driving speed within each preset transfer mode, the corresponding transfer mode is determined;

[0044] The driving mode of the autonomous sanitation vehicle is switched from the low-speed cleaning mode to the transfer mode until the autonomous sanitation vehicle passes through the non-cleaned area.

[0045] Optionally, the method further includes:

[0046] After the autonomous sanitation vehicle passes through the non-sweeping area, the driving mode of the autonomous sanitation vehicle is switched from the transfer mode to the low-speed sweeping mode.

[0047] A second aspect of the present invention provides a mode switching device for an autonomous sanitation vehicle, comprising:

[0048] The data acquisition module is used to obtain the current location and non-cleaned areas of the autonomous sanitation vehicle from the semantic map in real time;

[0049] The distance judgment module is used to determine whether the distance to be traveled between the current position and the non-cleaned area is less than or equal to a preset switching threshold.

[0050] The continuous data acquisition module is used to continuously acquire surrounding environmental information and green light countdown if the condition is met.

[0051] The mode switching judgment module is used to determine whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current position and the green light countdown.

[0052] The mode switching module is used to switch the driving mode of the autonomous sanitation vehicle from low-speed sweeping mode to transfer mode if the conditions are met, until the autonomous sanitation vehicle passes through the non-sweeping area.

[0053] A third aspect of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the mode switching method for an autonomous sanitation vehicle as described in any one of the first aspects of the present invention.

[0054] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the mode switching method for an autonomous sanitation vehicle as described in any of the first aspects of the present invention.

[0055] As can be seen from the above technical solutions, the present invention has the following advantages:

[0056] This invention utilizes the autonomous driving system within the autonomous sanitation vehicle to obtain the vehicle's current location and non-sweeping areas in real-time from a semantic map. It then determines whether the distance between the current location and the non-sweeping area is less than or equal to a preset switching threshold. If so, it continuously acquires surrounding environmental information and a green light countdown. Based on this information, the vehicle's current location, and the green light countdown, it determines whether the autonomous sanitation vehicle meets the mode switching conditions. If so, it switches the vehicle's driving mode from low-speed sweeping mode to transfer mode until the vehicle passes through the non-sweeping area. This significantly reduces the likelihood of the autonomous sanitation vehicle stopping at intersections due to traffic light changes, thus affecting the passage of other vehicles and road users and greatly improving the vehicle's ability to pass through intersections. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart illustrating the steps of a mode switching method for an autonomous sanitation vehicle according to Embodiment 1 of the present invention;

[0059] Figure 2 The flowchart illustrates the steps of a mode switching method for an autonomous sanitation vehicle according to Embodiment 2 of the present invention.

[0060] Figure 3This is a structural block diagram of a mode switching device for an autonomous sanitation vehicle provided in Embodiment 3 of the present invention. Detailed Implementation

[0061] This invention provides a mode switching method, device, equipment, and medium for autonomous sanitation vehicles, which addresses the technical problem that autonomous sanitation vehicles may stop at intersections when passing through intersections under existing operating modes, affecting the passage of other vehicles and traffic participants, thereby increasing driving safety risks.

[0062] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0063] Please see Figure 1 , Figure 1 The flowchart illustrates the steps of a mode switching method for an autonomous sanitation vehicle provided in Embodiment 1 of the present invention.

[0064] This invention provides a mode switching method for an autonomous sanitation vehicle, comprising:

[0065] Step 101: Obtain the current location and non-cleaned areas of the autonomous sanitation vehicle in real time from the semantic map;

[0066] Semantic maps are high-precision maps containing a variety of semantic information. They acquire point cloud information of the physical world using LiDAR and then refine it to distinguish various objects and concepts such as lanes, cars, medians, roadside trees, signs, and the blue sky. Semantic information refers to the multi-layered and rich-dimensional information contained in high-precision maps that enables autonomous vehicles to better understand driving rules, perceive road traffic conditions, and plan driving routes.

[0067] Non-cleaned areas refer to areas pre-defined in the semantic map that do not require cleaning by autonomous sanitation vehicles, such as various intersections, including but not limited to crossroads, T-junctions, or road junctions.

[0068] In this embodiment of the invention, the autonomous driving system inside the autonomous sanitation vehicle locates the current position of the autonomous sanitation vehicle in real time from the semantic map and obtains the non-sweeping area closest to its current position, so as to provide the data basis for the subsequent mode switching of the autonomous sanitation vehicle.

[0069] Step 102: Determine whether the distance to be traveled between the current location and the non-cleaned area is less than or equal to the preset switching threshold;

[0070] Step 103: If yes, continue to acquire information about the surrounding environment and the green light countdown;

[0071] The green light countdown refers to the time displayed by the green light in a traffic light system at the current moment.

[0072] While acquiring the current location and the non-sweeping area, the system determines whether the distance between them is less than or equal to a preset switching threshold. If so, it indicates that the autonomous sanitation vehicle is about to enter the non-sweeping area. At this point, the system utilizes the wide-angle and telephoto cameras on the front of the autonomous sanitation vehicle for continuous perception during the green light countdown. Simultaneously, it uses LiDAR or millimeter-wave radar for continuous perception of the surrounding environment to determine if there are any vehicles ahead of the autonomous sanitation vehicle and to acquire the green light countdown.

[0073] If the distance traveled is still greater than the preset switching threshold, it means that the autonomous sanitation vehicle has not yet entered the intersection. At this time, the low-speed sweeping mode of the autonomous sanitation vehicle can continue to sweep the current road along the edge.

[0074] Step 104: Based on the surrounding environment information, current location, and green light countdown, determine whether the autonomous sanitation vehicle meets the mode switching conditions;

[0075] After obtaining information about the surrounding environment and the current location, and combining this with the green light countdown, it is further determined whether the autonomous sanitation vehicle meets the conditions for mode switching.

[0076] For example, in situations where the surrounding environment information indicates that there are no vehicles in front of the autonomous sanitation vehicle, other vehicles are present, vehicles completely or partially obstruct the traffic lights, or the green light countdown is partially or completely missing, the conditions for switching the autonomous sanitation vehicle's mode are determined based on the combination of different situations to determine whether the driving mode of the autonomous sanitation vehicle needs to be switched.

[0077] Step 105: If the conditions are met, switch the driving mode of the autonomous sanitation vehicle from low-speed sweeping mode to transfer mode until the autonomous sanitation vehicle passes through the non-sweeping area.

[0078] After determining that the autonomous sanitation vehicle meets the mode switching conditions, the driving mode of the autonomous sanitation vehicle can be switched from the low-speed cleaning mode to the transfer mode that complies with the current intersection speed limit, so that the autonomous sanitation vehicle can pass through the non-cleaning area at a faster and safer speed.

[0079] In practical implementation, taking the new national standard traffic lights as an example, most green lights have a built-in 9-second countdown, turning yellow in 3 seconds, and finally turning red. Considering the weight of the autonomous sanitation vehicle, plus the 2-ton clean water and 1-ton sewage tank, the vehicle's center of gravity and curb weight are relatively high. For safety reasons related to autonomous driving, the logic of running yellow lights is proactively disabled in the planning. For example, in a standard four-lane intersection (left turn + left turn & straight + straight + straight), the semantic map shows that the distance required to pass through the intersection straight is 50m. However, the autonomous sanitation vehicle sweeps at a low speed of 7km / h. If it crosses the stop line into the intersection at this operating speed, the time required to leave the intersection is 50 / (7 / 3.6)≈26s, which is nearly half a minute. During this time, the traffic light may change, causing the autonomous sanitation vehicle to stop in the middle of the intersection, affecting the movement of other vehicles. If the vehicle switches to a non-operational transfer mode and travels at 20 km / h through the intersection, it will only take 50 / (20 / 3.6)≈9 seconds, saving about two-thirds of the time. This reduces the chance that the autonomous sanitation vehicle will get stuck in the middle of the intersection due to the predicted trajectory of lateral obstacles after the vehicle starts from the green light, thus affecting the passage of other vehicles.

[0080] In this embodiment of the invention, the autonomous driving system inside the autonomous sanitation vehicle obtains the vehicle's current location and non-sweeping areas in real time from a semantic map; it determines whether the distance between the current location and the non-sweeping area is less than or equal to a preset switching threshold; if so, it continuously obtains surrounding environmental information and green light countdown; based on the surrounding environmental information, current location, and green light countdown, it determines whether the autonomous sanitation vehicle meets the mode switching conditions; if so, it switches the autonomous sanitation vehicle's driving mode from low-speed sweeping mode to transfer mode until the autonomous sanitation vehicle passes through the non-sweeping area, thereby reducing the likelihood of the autonomous sanitation vehicle stopping at intersections due to traffic light changes, affecting the passage of other vehicles and traffic participants, and significantly improving the autonomous sanitation vehicle's ability to pass through intersections.

[0081] Please see Figure 2 , Figure 2 This is a flowchart illustrating the steps of a mode switching method for an autonomous sanitation vehicle provided in Embodiment 2 of the present invention.

[0082] This invention provides a mode switching method for an autonomous sanitation vehicle, comprising:

[0083] Step 201: Obtain the current location and non-cleaning areas of the autonomous sanitation vehicle in real time from the semantic map;

[0084] Step 202: Determine whether the distance to be traveled between the current location and the non-cleaned area is less than or equal to the preset switching threshold;

[0085] Step 203: If yes, continue to acquire information about the surrounding environment and the green light countdown;

[0086] In this embodiment of the invention, the specific implementation process of steps 201-203 is similar to that of steps 101-103, and will not be repeated here.

[0087] Step 204: Based on the surrounding environment information, current location, and green light countdown, determine whether the autonomous sanitation vehicle meets the mode switching conditions;

[0088] Optionally, the surrounding environment information includes following information and stop line position, and step 204 may include the following steps S11-S15:

[0089] S11. Calculate the relative distance between the current position and the stop line position;

[0090] S12. Calculate the vehicle head movement time using the relative distance and the transfer speed of the autonomous sanitation vehicle;

[0091] S13. Calculate the first time difference between the time it takes for the car to move and the countdown to the green light.

[0092] Following information refers to the perception information obtained by autonomous sanitation vehicles within a certain distance in front of their current position through semantic maps or LiDAR, including whether there is a vehicle in front or not.

[0093] The stop line position refers to the location of the stop line at an intersection, which can be obtained through LiDAR or semantic maps.

[0094] In this embodiment of the invention, after obtaining the following vehicle information and the stop line position, the autonomous driving system can calculate the relative distance between the current position and the stop line position, and further calculate the quotient between the relative distance and the transfer speed of the autonomous sanitation vehicle in transfer mode to obtain the vehicle's head movement time. The system then calculates the first time difference between the vehicle's head movement time and the obtained green light countdown.

[0095] The current position can be the position of the front wheels of the autonomous sanitation vehicle.

[0096] S14. If the following information indicates that there is no preceding vehicle and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0097] S15. If the following information indicates that there is no preceding vehicle, and the first time difference is less than or equal to the preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0098] In this embodiment, if the following information indicates that there is no vehicle in front, it means that the autonomous sanitation vehicle is in the first position at the intersection and there is no obstruction to the acquisition of the green light countdown. If it is determined at the same time that the first time difference is greater than the preset switching time threshold, such as the switching time threshold being set to 1s or 2s, it means that when there is 1s left in the green light countdown, the front wheels of the autonomous sanitation vehicle have already passed the stop line position. At this time, it can be directly determined that the autonomous sanitation vehicle meets the mode switching conditions.

[0099] If the following information indicates that there is no preceding vehicle, and the first time difference is less than or equal to the preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0100] In one example of the present invention, step 204 may further include the following sub-steps S21-S23:

[0101] S21. If the following information indicates that there is a vehicle in front and the green light countdown is obtained in real time, then the millimeter-wave radar is called to detect the first acceleration of the vehicle in front.

[0102] S22. If the first acceleration exceeds the acceleration threshold and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0103] S23. If the first acceleration does not exceed the acceleration threshold, or the first time difference is less than or equal to the preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0104] In one example of this invention, if the following information indicates the presence of a vehicle ahead, it means the autonomous sanitation vehicle is not currently in the first position at the intersection, and the acquisition of the green light countdown may be obstructed. If the green light countdown can be acquired in real time, millimeter-wave radar can be used to detect the first acceleration of the vehicle ahead. If this first acceleration exceeds a first acceleration threshold, and the first time difference is greater than a preset switching time threshold, it indicates that the vehicle ahead is accelerating. When the green light countdown has 1 second remaining, the front wheels of the autonomous sanitation vehicle have already passed the stop line, at which point it can be determined that the autonomous sanitation vehicle meets the mode switching conditions.

[0105] In practice, the following conditions must be met: the green light countdown must be greater than 1 second. Additionally, point cloud radar can be used to determine if the front vehicle has crossed the stop line, and millimeter-wave radar can detect if the front vehicle is accelerating. If these conditions are met, the main vehicle will choose to accelerate to pass through the intersection.

[0106] If the first acceleration does not exceed the acceleration threshold, or the first time difference is less than or equal to the preset switching time threshold, it indicates that the vehicle in front is not yet in an accelerated state, or that the front wheels of the autonomous sanitation vehicle fail to pass the stop line position when the vehicle in front passes the intersection. In this case, it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions and can maintain the current low-speed sweeping mode and brake gently before the stop line position, waiting for the next green light countdown to be obtained.

[0107] It should be noted that millimeter-wave radar can obtain the target's velocity relative to the radar by calculating the frequency change of the radar wave returning to the receiving antenna based on the Doppler effect. Simply put, the relative velocity is proportional to the frequency change. After obtaining the velocity, the derivative is taken to obtain the first acceleration.

[0108] In another example of the present invention, step 204 may further include the following sub-steps S31-S33:

[0109] S31. If the following information indicates that there is a vehicle in front and the green light countdown is completely missing, then the millimeter-wave radar and lidar are used to detect the traffic flow trend and the second acceleration corresponding to the vehicle in front.

[0110] Furthermore, step S31 may also include the following sub-steps:

[0111] If the following information indicates that there is a vehicle ahead and the green light countdown is completely missing, then the millimeter-wave radar is used to detect the second acceleration corresponding to the vehicle ahead.

[0112] The lidar is used to obtain the vehicle point cloud corresponding to the adjacent lane, and the millimeter-wave radar is used to obtain the third acceleration corresponding to the vehicle point cloud.

[0113] If the third acceleration exceeds the first acceleration threshold, the traffic flow trend is determined to be an accelerating trend.

[0114] If the third acceleration does not exceed the second acceleration threshold, the traffic flow trend is determined to be a deceleration trend.

[0115] In this embodiment of the invention, if the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing, it indicates that the autonomous sanitation vehicle is stopped and obstructed by the vehicle ahead, making it unable to obtain the green light countdown. In this case, millimeter-wave radar can be used to detect the second acceleration corresponding to the vehicle ahead. Simultaneously, lidar is used to obtain vehicle point clouds corresponding to adjacent lanes, and millimeter-wave radar is used to obtain the third acceleration corresponding to the vehicle in the vehicle point cloud. For example, if adjacent lanes are both straight lanes, and the vehicle currently in the lead vehicle is also in a straight lane, the third acceleration and its trend in the left and right straight lanes are evaluated based on millimeter-wave radar and lidar.

[0116] If the third acceleration exceeds the first acceleration threshold, the traffic flow trend is determined to be an accelerating trend, and step S33 is executed.

[0117] If the third acceleration does not exceed the second acceleration threshold, the traffic flow trend is determined to be a deceleration trend, and step S34 is executed.

[0118] The first acceleration threshold is positive, and the second acceleration threshold is negative. Multiple vehicle point clouds in the same lane can be acquired simultaneously.

[0119] S33. If the traffic flow trend is an accelerating trend, and the second acceleration exceeds the acceleration threshold, and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0120] In one example of the present invention, if the traffic flow trend is an accelerating trend, and the second acceleration exceeds the acceleration threshold, and the first time difference is greater than the preset switching time threshold, then it indicates that the traffic flow is in the forward acceleration phase, and the vehicle in front is also in the acceleration phase. When the autonomous sanitation vehicle passes through the intersection with a certain number of green light countdowns remaining, the front wheels of the autonomous sanitation vehicle can pass the stop line position. At this time, it can be determined that the autonomous sanitation vehicle meets the mode switching conditions.

[0121] S33. If the traffic flow trend is a deceleration trend and the distance between the vehicle in front is less than the preset safe following distance threshold, it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions, and the current speed of the autonomous sanitation vehicle is reduced to the slow braking speed according to the preset ratio.

[0122] In another example of the present invention, when it is found that the traffic flow in the left and right lanes has a significant deceleration trend (the third acceleration does not exceed the second acceleration threshold, that is, the deceleration is higher than the threshold), and the relative position of the vehicle in front is also reduced to below the safe following distance threshold, the logic of slow braking and speed reduction by 50% is triggered to maintain a distance from the vehicle in front until the traffic light is not obstructed and the traffic light information of the perception input is obtained again, before deciding whether to speed up to pass through the intersection.

[0123] Optionally, step 204 may also include the following sub-steps S41-S46:

[0124] S41. If the following information indicates that there is a vehicle in front and the green light countdown is missing, then the movement strategy set up in the autonomous sanitation vehicle is detected.

[0125] S42. If the movement strategy is the waiting-at-the-light strategy, the current speed of the autonomous sanitation vehicle will be reduced to the braking speed according to the preset ratio until the green light countdown is obtained again, and then the process will jump to the step of calculating the relative distance between the current position and the stop line position.

[0126] In this embodiment of the invention, if the following information indicates the presence of a vehicle ahead and the green light countdown is missing, it indicates that the autonomous sanitation vehicle encountered a situation where the vehicle ahead blocked its view during dynamic driving, and only a portion of the green light countdown was obtained.

[0127] At this point, the movement strategy built into the autonomous sanitation vehicle can be detected. If the movement strategy is a waiting-at-the-light strategy, the current speed of the autonomous sanitation vehicle can be reduced according to a preset ratio until the green light countdown is obtained again. Then, step S11 is executed to calculate the relative distance between the autonomous sanitation vehicle and the stop line position when the green light countdown is obtained again, and the judgment on the satisfaction of the mode switching condition continues.

[0128] S43. If the movement strategy is a guessing strategy, then the last green light countdown obtained is used as the input time.

[0129] S44. Calculate the second time difference between the vehicle head movement time and the input time;

[0130] S45. If the second time difference is greater than the switching time threshold, the autonomous sanitation vehicle is determined to meet the mode switching conditions.

[0131] S46. If the second time difference is less than or equal to the switching time threshold, it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions.

[0132] In an optional embodiment of the present invention, if the movement strategy is a guessing strategy, it indicates that the autonomous sanitation vehicle needs to pass through the intersection relatively quickly. In this case, the last green light countdown obtained can be used as the input time.

[0133] At the same time, a second time difference between the vehicle's head movement time and the input time is calculated. If the second time difference is greater than the switching time threshold, the autonomous sanitation vehicle is determined to meet the mode switching conditions. If the second time difference is less than or equal to the switching time threshold, the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

[0134] Optionally, the method further includes the following steps:

[0135] If it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions, then the autonomous sanitation vehicle shall be stopped.

[0136] Jump to execute the steps of continuously acquiring surrounding environmental information and green light countdown.

[0137] In an optional embodiment of the present invention, if it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions, it indicates that although the autonomous sanitation vehicle is in a non-sweeping area, it cannot pass through the non-sweeping area due to the incompatibility of surrounding environmental information or the green light countdown. At this time, the movement of the autonomous sanitation vehicle can be stopped, and steps 203-204 can be executed to continuously acquire surrounding environmental information and green light countdown until it is determined that the mode switching conditions are met.

[0138] Step 205: If the autonomous sanitation vehicle meets the mode switching conditions, then read the speed limit of the intersection corresponding to the non-sweeping area from the semantic map.

[0139] In this embodiment, if the autonomous sanitation vehicle meets the mode switching conditions, it means that the autonomous sanitation vehicle can switch modes at this time, and then the speed limit of the intersection corresponding to the non-sweeping area is read from the semantic map.

[0140] It should be noted that since different roads have different speed limits at intersections, when an autonomous sanitation vehicle needs to switch modes, the speed limit corresponding to that intersection can be read from the semantic map first.

[0141] Step 206: Determine the corresponding transfer mode based on the matching result between the intersection speed limit and the driving speed within each preset transfer mode;

[0142] After determining the speed limit at the intersection, the system can match the target speed, which is lower than the speed limit and closest to it, from among the multiple preset transfer modes in the autonomous driving system. The transfer mode to which this target speed belongs will be used by the autonomous sanitation vehicle in the current mode switch.

[0143] Step 207: Switch the driving mode of the autonomous sanitation vehicle from low-speed cleaning mode to transfer mode until the autonomous sanitation vehicle passes through the non-cleaning area.

[0144] Furthermore, the method also includes:

[0145] When the autonomous sanitation vehicle passes through a non-sweeping area, the driving mode of the autonomous sanitation vehicle will be switched from the transfer mode to the low-speed sweeping mode.

[0146] In another example of the present invention, after the autonomous sanitation vehicle passes through the non-sweeping area, it needs to continue cleaning along the edge. At this time, its driving mode can be switched from the transfer mode to the low-speed cleaning mode.

[0147] It should be noted that the low-speed cleaning mode can also be adaptively adjusted according to the amount of garbage sensed by the autonomous sanitation vehicle. For example, when the amount of garbage is greater than a certain threshold, the speed of the autonomous sanitation vehicle can be reduced to facilitate better cleaning. If the amount of garbage is less than or equal to a certain threshold, the normal low-speed cleaning mode is maintained, such as cleaning along the edge at a speed of 7 km / h, until it is detected again that the distance between the current position of the autonomous sanitation vehicle and the non-cleaned area is less than or equal to the preset switching threshold.

[0148] In this embodiment of the invention, the autonomous driving system within the autonomous sanitation vehicle obtains the vehicle's current location and non-sweeping areas in real time from a semantic map; it determines whether the distance between the current location and the non-sweeping area is less than or equal to a preset switching threshold; if so, it continuously acquires surrounding environmental information and green light countdown; based on the surrounding environmental information, current location, and green light countdown, it determines whether the autonomous sanitation vehicle meets the mode switching conditions; if so, it switches the autonomous sanitation vehicle's driving mode from low-speed sweeping mode to transfer mode until the vehicle passes through the non-sweeping area. This reduces the likelihood of the autonomous sanitation vehicle stopping at intersections due to traffic light changes, affecting the passage of other vehicles and road users, significantly improving its ability to pass through intersections, reducing the impact on other road users, and increasing the sweeping efficiency of the autonomous sanitation vehicle. It also avoids wasting time and resources in non-sweeping areas such as intersections. Furthermore, it increases the maximum mileage and coverage area of ​​a single operation for the autonomous sanitation vehicle.

[0149] Please see Figure 3 , Figure 3 The diagram shows a structural block diagram of a mode switching device for an autonomous sanitation vehicle according to Embodiment 3 of the present invention.

[0150] This invention provides a mode switching device for an autonomous sanitation vehicle, comprising:

[0151] The data acquisition module 301 is used to obtain the current location and non-cleaning area of ​​the autonomous sanitation vehicle from the semantic map in real time;

[0152] The distance judgment module 302 is used to determine whether the distance to be traveled between the current position and the non-cleaned area is less than or equal to a preset switching threshold.

[0153] The data acquisition module 303 is used to continuously acquire surrounding environmental information and green light countdown if the condition is met.

[0154] The mode switching judgment module 304 is used to determine whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, current location and green light countdown.

[0155] The mode switching module 305 is used to switch the driving mode of the autonomous sanitation vehicle from low-speed sweeping mode to transfer mode if the conditions are met, until the autonomous sanitation vehicle passes through the non-sweeping area.

[0156] Optionally, the device further includes:

[0157] The vehicle stop module is used to stop the autonomous sanitation vehicle if it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions.

[0158] The first jump module is used to jump to the execution of the steps of continuously obtaining surrounding environmental information and green light countdown.

[0159] Optionally, the surrounding environment information includes following information and stop line position; the mode switching judgment module 304 includes:

[0160] The relative distance calculation submodule is used to calculate the relative distance between the current position and the stop line position;

[0161] The vehicle head movement time calculation submodule is used to calculate the vehicle head movement time using relative distance and the transfer speed of the autonomous sanitation vehicle;

[0162] The first time difference calculation submodule is used to calculate the first time difference between the vehicle head movement time and the green light countdown.

[0163] The first judgment submodule is used to determine that the autonomous sanitation vehicle meets the mode switching conditions if the following information indicates that there is no preceding vehicle and the first time difference is greater than the preset switching time threshold.

[0164] The second judgment submodule is used to determine that the autonomous sanitation vehicle does not meet the mode switching conditions if the following information indicates that there is no preceding vehicle and the first time difference is less than or equal to the preset switching time threshold.

[0165] Optionally, the mode switching determination module 304 further includes:

[0166] The first acceleration calculation submodule is used to call the millimeter-wave radar to detect the first acceleration of the vehicle in front if the following information indicates that there is a vehicle in front and the green light countdown is obtained in real time.

[0167] The third judgment submodule is used to determine that the autonomous sanitation vehicle meets the mode switching conditions if the first acceleration exceeds the acceleration threshold and the first time difference is greater than the preset switching time threshold.

[0168] The fourth judgment submodule is used to determine that the autonomous sanitation vehicle does not meet the mode switching conditions if the first acceleration does not exceed the acceleration threshold or the first time difference is less than or equal to the preset switching time threshold.

[0169] Optionally, the mode switching determination module 304 further includes:

[0170] The second acceleration calculation submodule is used to call millimeter-wave radar and lidar to detect the traffic flow trend and the second acceleration corresponding to the vehicle in front if the following information indicates that there is a vehicle in front and the green light countdown is completely missing.

[0171] The extraction and judgment submodule is used to determine that the autonomous sanitation vehicle meets the mode switching conditions if the traffic flow trend is an accelerating trend, the second acceleration exceeds the acceleration threshold, and the first time difference is greater than the preset switching time threshold.

[0172] The deceleration judgment submodule is used to determine that the autonomous sanitation vehicle has not met the mode switching conditions if the traffic flow trend is decelerating and the distance between it and the vehicle in front is less than the preset safe following distance threshold. The submodule then reduces the current speed of the autonomous sanitation vehicle to the braking speed according to a preset ratio.

[0173] Optionally, the second acceleration calculation submodule is specifically used for:

[0174] If the following information indicates that there is a vehicle ahead and the green light countdown is completely missing, then the millimeter-wave radar is used to detect the second acceleration corresponding to the vehicle ahead.

[0175] The lidar is used to obtain the vehicle point cloud corresponding to the adjacent lane, and the millimeter-wave radar is used to obtain the third acceleration corresponding to the vehicle point cloud.

[0176] If the third acceleration exceeds the first acceleration threshold, the traffic flow trend is determined to be an accelerating trend.

[0177] If the third acceleration does not exceed the second acceleration threshold, the traffic flow trend is determined to be a deceleration trend.

[0178] Optionally, the mode switching determination module 304 further includes:

[0179] The movement strategy detection submodule is used to detect the movement strategy set up in the autonomous sanitation vehicle if the following information indicates that there is a vehicle in front and the green light countdown is missing.

[0180] The waiting-at-the-lights submodule is used to reduce the current speed of the autonomous sanitation vehicle to a slow braking speed according to a preset ratio if the movement strategy is a waiting-at-the-lights strategy, until the green light countdown is obtained again, and then jump to the step of calculating the relative distance between the current position and the stop line position.

[0181] The "Guess the Light" submodule is used to take the last green light countdown frame as the input time if the movement strategy is "Guess the Light".

[0182] The second time difference calculation submodule is used to calculate the second time difference between the vehicle head movement time and the input time.

[0183] The fifth judgment submodule is used to determine that the autonomous sanitation vehicle meets the mode switching conditions if the second time difference is greater than the switching time threshold.

[0184] The sixth judgment submodule is used to determine that the autonomous sanitation vehicle does not meet the mode switching conditions if the second time difference is less than or equal to the switching time threshold.

[0185] Optionally, the mode switching module 305 is specifically used for:

[0186] If the autonomous sanitation vehicle meets the mode switching conditions, the speed limit of the intersection corresponding to the non-sweeping area is read from the semantic map.

[0187] The corresponding transfer mode is determined based on the matching result between the speed limit at the intersection and the driving speed within each preset transfer mode;

[0188] Switch the autonomous sanitation vehicle's driving mode from low-speed cleaning mode to transfer mode until the autonomous sanitation vehicle passes through the non-cleaned area.

[0189] Optionally, the device further includes:

[0190] The low-speed switching module is used to switch the autonomous sanitation vehicle's driving mode from transfer mode to low-speed cleaning mode after the autonomous sanitation vehicle passes through a non-cleaned area.

[0191] This invention provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the mode switching method for an autonomous sanitation vehicle as described in any embodiment of this invention.

[0192] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed, implements a mode switching method for an autonomous sanitation vehicle as described in any embodiment of this invention.

[0193] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, modules, and sub-modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0194] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0195] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0196] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0197] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0198] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A mode switching method of an automatic driving sanitation vehicle, characterized by, include: The current location and non-cleaned areas of the autonomous sanitation vehicle are obtained in real time from the semantic map; Determine whether the distance to be traveled between the current location and the non-cleaned area is less than or equal to a preset switching threshold; If so, it will continue to acquire information about the surrounding environment and the green light countdown; Based on the surrounding environment information, the current location, and the green light countdown, determine whether the autonomous sanitation vehicle meets the mode switching conditions; If the conditions are met, the driving mode of the autonomous sanitation vehicle will be switched from low-speed sweeping mode to transfer mode until the autonomous sanitation vehicle passes through the non-sweeping area. The surrounding environment information includes following information and stop line position; the step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current position, and the green light countdown includes: Calculate the relative distance between the current position and the stop line position; The relative distance and the turning speed of the autonomous sanitation vehicle are used to calculate the vehicle's front movement time; Calculate the first time difference between the vehicle's forward movement time and the green light countdown; If the following information indicates that there is no preceding vehicle and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions. If the following information indicates that there is no preceding vehicle, and the first time difference is less than or equal to a preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

2. The method of claim 1, wherein, The method further includes: If it is determined that the autonomous sanitation vehicle does not meet the mode switching conditions, then the autonomous sanitation vehicle shall be stopped. Jump to execute the steps of continuously acquiring surrounding environmental information and green light countdown.

3. The method of claim 1, wherein, The step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current location, and the green light countdown further includes: If the following information indicates the presence of a vehicle ahead and the green light countdown is obtained in real time, then the millimeter-wave radar is invoked to detect the first acceleration of the vehicle ahead. If the first acceleration exceeds the first acceleration threshold and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions. If the first acceleration does not exceed the first acceleration threshold, or the first time difference is less than or equal to the preset switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

4. The method of claim 1, wherein, The step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current location, and the green light countdown further includes: If the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing, then millimeter-wave radar and lidar are invoked to detect the traffic flow trend and the second acceleration corresponding to the vehicle ahead. If the traffic flow trend is an accelerating trend, and the second acceleration exceeds the first acceleration threshold, and the first time difference is greater than the preset switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions. If the traffic flow trend is a deceleration trend and the distance between the vehicle and the vehicle in front is less than a preset safe following distance threshold, then it is determined that the autonomous driving sanitation vehicle does not meet the mode switching conditions, and the current speed of the autonomous driving sanitation vehicle is reduced to the braking speed according to a preset ratio.

5. The method of claim 4, wherein, The step of calling millimeter-wave radar and lidar to detect the traffic flow trend and the second acceleration corresponding to the preceding vehicle if the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing includes: If the following information indicates the presence of a vehicle ahead and the green light countdown is completely missing, then the millimeter-wave radar is invoked to detect the second acceleration corresponding to the vehicle ahead. The lidar is invoked to obtain the vehicle point cloud corresponding to the adjacent lane, and the millimeter-wave radar is invoked to obtain the third acceleration corresponding to the vehicle point cloud; If the third acceleration exceeds the first acceleration threshold, the traffic flow movement trend is determined to be an accelerating movement trend. If the third acceleration does not exceed the second acceleration threshold, the traffic flow trend is determined to be a deceleration trend.

6. The method of claim 1, wherein, The step of determining whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current location, and the green light countdown further includes: If the following information indicates the presence of a vehicle ahead and the green light countdown is missing, then the movement strategy set up within the autonomous sanitation vehicle is detected. If the movement strategy is a waiting-at-the-light strategy, the current speed of the autonomous sanitation vehicle is reduced to a slow braking speed according to a preset ratio until the green light countdown is obtained again, and then the step of calculating the relative distance between the current position and the stop line position is executed. If the movement strategy is a guessing strategy, then the green light countdown in the last frame obtained will be used as the input time. Calculate the second time difference between the vehicle head movement time and the input time; If the second time difference is greater than the switching time threshold, then the autonomous sanitation vehicle is determined to meet the mode switching conditions. If the second time difference is less than or equal to the switching time threshold, then the autonomous sanitation vehicle is determined not to meet the mode switching conditions.

7. The method of claim 1, wherein, If the condition is met, the driving mode of the autonomous sanitation vehicle is switched from low-speed cleaning mode to transfer mode until the autonomous sanitation vehicle passes through the non-cleaned area. This step includes: If the autonomous sanitation vehicle meets the mode switching conditions, the speed limit of the intersection corresponding to the non-sweeping area is read from the semantic map. Based on the matching results between the speed limit at the intersection and the driving speed within each preset transfer mode, the corresponding transfer mode is determined; The driving mode of the autonomous sanitation vehicle is switched from the low-speed cleaning mode to the transfer mode until the autonomous sanitation vehicle passes through the non-cleaned area.

8. The method of claim 1, wherein, The method further includes: After the autonomous sanitation vehicle passes through the non-sweeping area, the driving mode of the autonomous sanitation vehicle is switched from the transfer mode to the low-speed sweeping mode.

9. A mode switching device of an automatic driving sanitation vehicle, characterized by, include: The data acquisition module is used to obtain the current location and non-cleaned areas of the autonomous sanitation vehicle from the semantic map in real time; The distance judgment module is used to determine whether the distance to be traveled between the current position and the non-cleaned area is less than or equal to a preset switching threshold. The continuous data acquisition module is used to continuously acquire surrounding environmental information and green light countdown if the condition is met. The mode switching judgment module is used to determine whether the autonomous sanitation vehicle meets the mode switching conditions based on the surrounding environment information, the current position and the green light countdown. The mode switching module is used to switch the driving mode of the autonomous sanitation vehicle from low-speed sweeping mode to transfer mode if the conditions are met, until the autonomous sanitation vehicle passes through the non-sweeping area. The surrounding environment information includes following vehicle information and stop line position; the mode switching judgment module includes: The relative distance calculation submodule is used to calculate the relative distance between the current position and the stop line position; The vehicle front movement time calculation submodule is used to calculate the vehicle front movement time using the relative distance and the turning speed of the autonomous sanitation vehicle; The first time difference calculation submodule is used to calculate the first time difference between the vehicle head movement time and the green light countdown. The first judgment submodule is used to determine that the autonomous sanitation vehicle meets the mode switching conditions if the following information indicates that there is no preceding vehicle and the first time difference is greater than a preset switching time threshold. The second judgment submodule is used to determine that the autonomous sanitation vehicle does not meet the mode switching conditions if the following information indicates that there is no preceding vehicle and the first time difference is less than or equal to a preset switching time threshold.

10. An electronic device, comprising: The system includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the mode switching method for an autonomous sanitation vehicle as described in any one of claims 1-8.

11. A computer readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed, it implements the mode switching method for the autonomous sanitation vehicle as described in any one of claims 1-8.

Images