CN111258318A - Automatic driving system of sanitation vehicle and control method thereof - Google Patents
Automatic driving system of sanitation vehicle and control method thereof Download PDFInfo
- Publication number
- CN111258318A CN111258318A CN202010074713.8A CN202010074713A CN111258318A CN 111258318 A CN111258318 A CN 111258318A CN 202010074713 A CN202010074713 A CN 202010074713A CN 111258318 A CN111258318 A CN 111258318A
- Authority
- CN
- China
- Prior art keywords
- subsystem
- vehicle
- positioning
- information
- obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000004140 cleaning Methods 0.000 claims abstract description 54
- 230000008447 perception Effects 0.000 claims abstract description 11
- 230000003993 interaction Effects 0.000 claims abstract description 6
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 11
- 230000003068 static effect Effects 0.000 claims description 10
- 230000004888 barrier function Effects 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 230000003542 behavioural effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 230000001953 sensory effect Effects 0.000 claims 1
- 230000001133 acceleration Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010034719 Personality change Diseases 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010415 tidying Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Abstract
The invention discloses an automatic driving system of a sanitation vehicle and a control method thereof, relating to the field of automatic driving, wherein the automatic driving system comprises a positioning subsystem, a cleaning subsystem and a control subsystem, wherein the positioning subsystem is used for updating the pose information of the vehicle in real time and selecting a pre-recorded cleaning route; the positioning system is also used for automatically switching the positioning mode in real time according to the signal intensity; the perception subsystem is used for generating an information situation map according to the cleaning route; the decision-making subsystem is used for generating a driving situation map so as to generate a transverse control command and a longitudinal control command; the driving situation map comprises a path plan of the travel route; the control subsystem is also used for receiving and executing a transverse control command and a longitudinal control command, and synchronously executing a preset cleaning task; and the HMI subsystem is used for human-computer interaction. The automatic driving system disclosed by the invention does not need to acquire a high-precision map, can meet the positioning precision requirement of automatic driving of the sanitation vehicle under different scene environments, and completes the automatic driving and cleaning operation of the sanitation vehicle.
Description
Technical Field
The invention relates to the field of automatic driving, in particular to an automatic driving system of a sanitation vehicle and a control method thereof.
Background
The automatic driving technology of the automobile is always a research hotspot in the field of automobiles, and the aim is to enable the driving of the automobile to be simpler and more humanized. To improve driving safety, many vehicles are equipped with autonomous driving systems. However, the existing automatic driving system depends on a high-precision map, and the route planning can be realized only in an area covered by the high-precision map.
The sanitation vehicle is a special vehicle for cleaning and tidying urban appearance, the operation scene is complex, the restriction by factors such as road environment is large, and the existing automatic driving system cannot meet the automatic driving working condition of the sanitation vehicle. On the one hand, the coverage of the existing high-precision map is small, and the acquisition and maintenance cost is high, on the other hand, under an overhead bridge, a tunnel or other scenes with weak GPS signals, the positioning precision of a sanitation part cannot meet the requirement of automatic driving, certain potential safety hazards exist, and the safety and the reliability of automatic driving cannot be guaranteed.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an automatic driving system of a sanitation vehicle and a control method thereof, which can select a pre-recorded cleaning route without a high-precision map; the positioning mode can be selected according to the signal intensity.
The invention provides a sanitation vehicle automatic driving system in a first aspect, which comprises:
the positioning subsystem is used for updating the pose information of the vehicle in real time and selecting a pre-recorded cleaning route according to the initial pose information; the positioning system is also used for automatically switching the positioning mode in real time according to the signal intensity;
the perception subsystem is used for acquiring road environment information of a road sanitation vehicle and distance and speed information of barrier targets around the sanitation vehicle and generating an information situation map according to the cleaning route;
the decision-making subsystem is used for generating a driving situation map according to the information situation map so as to generate a transverse control command and a longitudinal control command; the driving situation map comprises a path plan of a travel route;
the control subsystem is also used for receiving and executing the transverse control command and the longitudinal control command and synchronously executing a preset cleaning task;
the HMI subsystem is used for man-machine interaction and determining to adopt an automatic driving mode or a manual driving mode; the system is also used for displaying vehicle pose information, road environment information and path planning in the automatic driving process.
Based on the first aspect, in a possible embodiment, the positioning subsystem comprises:
the high-precision positioning module is used for generating vehicle pose information according to the high-precision positioning signal;
the laser positioning module is used for generating vehicle pose information according to the laser positioning signals;
and the switching module is used for positioning by adopting the laser positioning module when the intensity of the high-precision positioning signal is smaller than a signal threshold value, or positioning by adopting the high-precision positioning module.
Based on the first aspect, in a possible embodiment, the perception subsystem comprises:
a monocular camera installed in the cab, the monocular camera detecting an obstacle target in front of the vehicle and on both sides of the front of the vehicle;
a vision sensor installed in the cab, the vision sensor identifying a type of an obstacle target ahead of travel, the type of the obstacle target including a pedestrian, a vehicle, and a lane line;
two laser radars respectively arranged below the left side and the right side of a cab, wherein the laser radars are used for detecting the types of obstacle targets in the driving front and the two sides of the driving front and detecting the road edges on the two sides of the driving front; the types of the obstacle targets comprise static obstacles and dynamic obstacles;
a millimeter wave radar installed in the lower middle part of the cab, the millimeter wave radar being used for performing supplementary detection on the type of the obstacle target and detecting a distant obstacle target ahead of travel, and also being used for calculating the distance between the distant obstacle target and the sanitation vehicle and the speed of the distant obstacle target;
the system comprises six ultrasonic radars, a driving cab and a driving system, wherein the six ultrasonic radars are arranged below the driving cab and symmetrically distributed on two sides of the millimeter wave radars, are used for detecting short-distance obstacle targets on two sides of the sanitation vehicle and calculating the distance between the short-distance obstacle targets and the sanitation vehicle and the speed of the short-distance obstacle targets;
the high-precision inertial navigation system is used for detecting the position and the posture of the sanitation vehicle;
and the information fusion module is respectively connected with the monocular camera, the laser radar, the millimeter wave radar, the ultrasonic radar and the high-precision inertial navigation.
Based on the first aspect, in a possible embodiment, the decision making subsystem is further configured to perform behavior planning according to the path planning; the behavior planning comprises bypassing overtaking, stopping and waiting, decelerating and following and keeping constant-speed running in a lane;
the lateral control commands and the longitudinal control commands are generated based on the behavioral plan.
Based on the first aspect, in a possible embodiment, the cleaning system further includes a storage subsystem, and the positioning subsystem is further configured to record the cleaning route in advance and store the cleaning route in the storage subsystem.
Based on the first aspect, in a possible embodiment, the system further includes a monitoring subsystem, where the monitoring subsystem is configured to monitor a working state of the sensing subsystem, and send abnormal information to the HMI subsystem and the control subsystem when the sensing subsystem is abnormal;
the HMI subsystem is also used for controlling and sending out an alarm according to the abnormal information;
the control subsystem is also used for controlling deceleration and parking according to the abnormal information.
A second aspect of the present invention provides a control method applied to the above-described automatic driving system, including the steps of:
when the automatic driving mode is determined, vehicle pose information is collected, and a pre-recorded cleaning route is selected according to the pose information; selecting a positioning mode in real time according to the signal intensity;
collecting road environment information of a road sanitation vehicle and distance and speed information of barrier targets around the sanitation vehicle, and generating an information situation map according to the cleaning route;
generating a driving situation map according to the information situation map, further generating a transverse control command and a longitudinal control command, wherein the driving situation map comprises a path plan of a traveling route,
and executing the transverse control command and the longitudinal control command, and synchronously executing a preset cleaning task.
Based on the second aspect, in a possible embodiment, the selecting a positioning manner in real time according to the magnitude of the signal strength specifically includes:
when the high-precision signal intensity is smaller than the signal threshold, a laser positioning module is adopted for positioning;
and when the high-precision signal intensity is greater than or equal to the signal threshold, positioning by adopting a high-precision positioning module.
Based on the second aspect, in a possible embodiment, after generating the driving situation map according to the information situation map, the method further includes:
performing behavior planning according to the driving situation map, wherein the behavior planning comprises bypassing overtaking, parking waiting, decelerating and following and keeping constant-speed running in a lane;
the lateral control commands and the longitudinal control commands are generated based on the behavioral plan.
Based on the second aspect, in a possible embodiment, performing behavior planning according to the driving situation map specifically includes:
when the obstacle target in front of the vehicle is a static obstacle, if the size of the static obstacle is smaller than the bypassing range, determining that the behavior plan is bypassing overtaking, and otherwise, stopping and waiting;
and when the obstacle target in front of the running is a dynamic obstacle, if the speed of the dynamic obstacle is less than that of the sanitation vehicle, determining that the behavior plan is a deceleration following vehicle, wherein the following vehicle target is the dynamic obstacle, and otherwise, keeping the uniform running in the lane.
Compared with the prior art, the invention has the advantages that:
(1) the automatic driving system of the sanitation vehicle can select the pre-recorded cleaning route according to the pose information of the sanitation vehicle, does not need to acquire a high-precision map, can automatically switch the positioning mode in real time according to the signal intensity, and can meet the positioning precision requirement of automatic driving of the sanitation vehicle under different scene environments; the automatic driving and cleaning operation of the sanitation vehicle is completed by the cooperation of the positioning subsystem, the sensing subsystem, the decision subsystem and the control subsystem.
(2) According to the automatic driving system of the sanitation vehicle, the laser positioning module and the switching module are arranged, so that the defect of large positioning error caused by poor high-precision positioning signal intensity can be overcome, and the positioning accuracy and the automatic driving safety are ensured.
(3) According to the automatic driving system of the sanitation vehicle, multiple obstacle targets can be accurately identified through sensing redundancy among the monocular camera, the laser radar, the millimeter wave radar, the ultrasonic radar and the high-precision inertial navigation, sensing blind areas are reduced, complex road environments in the actual operation working conditions of the sanitation vehicle and road participants including motor vehicles and pedestrians are effectively detected, and automatic driving safety is guaranteed.
(4) The automatic driving system of the sanitation vehicle provided by the invention utilizes the characteristic that cleaning routes of the sanitation vehicle are complex but relatively fixed, and is driven manually, and a positioning subsystem is used for prerecording a plurality of cleaning routes and storing the cleaning routes to a storage subsystem, so that the cleaning routes can be selected automatically according to vehicle pose information during each automatic driving.
Drawings
FIG. 1 is a schematic structural diagram of an automatic driving system of a sanitation truck according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the distribution of the perception sub-system in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a perception subsystem in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Referring to fig. 1, the present invention provides an embodiment of an automatic driving system of a sanitation vehicle, which includes a positioning subsystem, a sensing subsystem, a decision-making subsystem, a control subsystem and an HMI (Human Machine Interface) subsystem.
When the automatic driving mode is determined, the positioning subsystem is used for updating the pose information of the vehicle in real time and selecting a pre-recorded cleaning route according to the initial pose information; the positioning subsystem is also used for automatically switching the positioning mode in real time according to the signal intensity.
The current pose information of the sanitation vehicle is position information and attitude information of the sanitation vehicle at the current moment, and for example, the current pose information of the sanitation vehicle can comprise position coordinates, a course angle and the like.
The perception subsystem is used for collecting road environment information of the road sanitation vehicle and distance and speed information of barrier targets around the sanitation vehicle, and generating an information situation map according to the cleaning route.
And the decision-making subsystem is used for generating a driving situation map in real time according to the information situation map so as to generate a transverse control command and a longitudinal control command. The driving situation map includes a path plan of the travel route.
The control subsystem is used for receiving and executing the transverse control command and the longitudinal control command and synchronously executing a preset cleaning task.
The HMI subsystem is used for human-computer interaction and determines to adopt an automatic driving mode or a manual driving mode according to the intention of a driver. The HMI subsystem is also used for displaying vehicle pose information, road environment information and path planning in the automatic driving process.
The automatic driving system of the embodiment can select the pre-recorded cleaning route according to the pose information of the sanitation vehicle, does not need to acquire a high-precision map, and can automatically switch the positioning mode according to the signal intensity in real time, thereby meeting the positioning precision requirement of the sanitation vehicle automatic driving under different scene environments; the automatic driving and cleaning operation of the sanitation vehicle is completed by the cooperation of the positioning subsystem, the sensing subsystem, the decision subsystem and the control subsystem.
On the basis of the above embodiment, in this embodiment, the positioning subsystem includes a high-precision positioning module, a laser positioning module, and a switching module.
And the high-precision positioning module is used for generating vehicle pose information according to the high-precision positioning signal. The high-precision positioning module obtains pose data through a combination/inertia device, and combines vehicle state data obtained through a vehicle body network and received centimeter-level RTK (Real-time kinematic) differential positioning information to realize centimeter-level high-precision positioning.
The laser positioning module is used for generating vehicle pose information according to the laser positioning signals. The laser positioning module is connected with a 16-line laser radar, and the 16-line laser radar is arranged above the cab. The laser radar is used as a high-precision distance measuring device in a three-dimensional space, and is very suitable for high-precision positioning, because the Point cloud output by the laser radar is huge in quantity and is easy to be disturbed by the influence of the environment when being processed in real time, the laser Point cloud needs to be firstly subjected to feature extraction, then ICP (Iterative Closest Point) registration is carried out according to the feature Point clouds of two adjacent frames, the position and attitude change of the two adjacent frames is calculated, and finally the position and attitude of the current self-vehicle are calculated.
The switching module is used for positioning by adopting the laser positioning module when the intensity of the high-precision positioning signal is smaller than a signal threshold value, or positioning by adopting the high-precision positioning module.
Therefore, in general, the high-precision positioning module is the default positioning module for positioning. Under the operating mode that positioning signal is relatively poor and the combination is used to lead positioning accuracy not high (be greater than 20cm positioning accuracy) such as overhead or tunnel, sanitation car during operation, high accuracy positioning module can send the signal warning that positioning error is bigger than normal, switch to laser positioning module by switching module, laser positioning module fixes a position according to laser SLAM (simultaneous localization and mapping, instant location and map are built), guarantee that whole journey can both provide stable high accuracy location.
In the embodiment, the laser positioning module and the switching module are arranged, so that the defect of large positioning error caused by poor high-precision positioning signal intensity can be overcome, and the positioning accuracy and the safety of automatic driving are ensured.
The positioning subsystem of the embodiment can also provide a large amount of historical prior data, provide redundancy and enhanced sensing effects for the sensing subsystem, and further provide more reliable input for the decision-making subsystem.
Referring to fig. 2 and fig. 3, on the basis of the above embodiment, in the present embodiment, the sensing subsystem includes a monocular camera, a vision sensor, a laser radar, a millimeter wave radar, an ultrasonic radar, and a high-precision inertial navigation and information fusion module. The information fusion module is respectively connected with the monocular camera, the vision sensor, the laser radar, the millimeter wave radar, the ultrasonic radar and the high-precision inertial navigation. The positioning subsystem provides pose information in actual world coordinates of the vehicle to the perception subsystem.
The monocular camera is provided one and is installed in the cab, and the monocular camera is used for detecting the obstacle targets in the front of the vehicle and on both sides of the front of the vehicle. The detection distance of the monocular camera obstacle target is within 80 m.
The vision sensor is arranged in the cab and used for identifying the type of the obstacle target in front of the vehicle to classify the obstacle target. The above-mentioned types of obstacle objects include pedestrians, vehicles, and lane lines. Optionally, the visual sensor is a mobiley camera. The detection distance of the obstacle target of the Mobileye camera is within 60 m.
The laser radars are arranged in two numbers and are respectively arranged below the left side and the right side of the cab. The laser radar is used for detecting the types of the barrier targets in the driving front and on two sides of the driving front and detecting the road edges on two sides of the driving front; the above classes of obstacle targets include static obstacles and dynamic obstacles. Considering that the sanitation vehicle needs to operate in both day and night, in this embodiment, the lidar is a 16-line lidar, and the obstacle target detection distance of the lidar is within 100 m.
The millimeter wave radar is arranged in the middle below the cab, and is used for performing supplementary detection on the type of the obstacle target and detecting the long-distance obstacle target in front of the vehicle according to the characteristics of the millimeter wave radar. In this embodiment, the millimeter wave radar adopts a forward millimeter wave radar ESR, and the long-distance threshold interval for detecting the obstacle target of the forward millimeter wave radar is 100-175 m.
The millimeter wave radar is also used for calculating the distance between the remote obstacle target and the sanitation vehicle and the speed of the remote obstacle target.
Above-mentioned ultrasonic radar is equipped with six, and installs in above-mentioned driver's cabin below, and six ultrasonic radar symmetric distribution are in above-mentioned millimeter wave radar both sides, and three ultrasonic radar sets up in millimeter wave radar one side promptly, and three ultrasonic radar sets up in millimeter wave radar's opposite side in addition.
According to the characteristics of the ultrasonic radar, the ultrasonic radar is used for detecting the short-distance obstacle targets on two sides of the sanitation vehicle, and is also used for calculating the distance between the short-distance obstacle target and the sanitation vehicle and the speed of the short-distance obstacle target. The installation height limitation of the laser radar is made up through the ultrasonic radar, and the short-distance blind area is supplemented. In this embodiment, the short-distance threshold for detecting the obstacle target of the ultrasonic radar is 2.5m, that is, the obstacle target detection distance of the ultrasonic radar is within 2.5 m.
The high-precision inertial navigation is used for detecting the position and the posture of the sanitation vehicle, and can achieve centimeter-level positioning precision.
The millimeter wave radar, the ultrasonic radar and the Mobileye camera are respectively communicated with the information fusion module through CAN (Controller area network) lines, the laser radar and the monocular camera are communicated with the information fusion module through Ethernet, and the high-precision inertial navigation module is communicated with the information fusion module through a serial port. And classifying the obstacle targets by a Mobiley camera, and detecting and tracking the obstacle targets by a millimeter wave radar, an ultrasonic radar, a laser radar, a monocular camera and high-precision inertial navigation.
On the basis of detecting the obstacle target, basic information such as the current position, angle, speed, acceleration and the like of the target can be calculated through target fusion among the devices. In order to improve the precision and stability of dynamic target detection, a redundant sensor design is adopted, namely, sensing redundancy existing among a monocular camera, a laser radar, a millimeter wave radar, an ultrasonic radar and a Mobiley camera is utilized simultaneously to calculate the state information of a detected target. On this basis, the Kalman filter is designed to sense and fuse the detection result, the detection result of different sensors is used as the observation value of the Kalman filter, various obstacle targets can be accurately identified, sensing blind areas are reduced, the accuracy and stability of dynamic obstacle detection are improved, and then the complex road environment in the actual operation working condition of the sanitation vehicle is effectively detected, and the automatic driving safety is ensured by road participants including motor vehicles and pedestrians.
In this embodiment, the information situation map includes information such as an obstacle target list, road information, and a cleaning route.
In this embodiment, the driving situation map further includes an expected track, an expected speed, an expected acceleration, and other auxiliary planning information.
Further, the decision-making subsystem is also used for carrying out behavior planning according to the driving situation diagram, and further carrying out corresponding motion planning based on the behavior planning. The behavior planning comprises the steps of bypassing and overtaking, parking and waiting, decelerating and following and keeping the sanitation vehicle running at a constant speed in the lane. Wherein the motion plan is a horizontal control command and a vertical control command.
After the decision subsystem carries out Control algorithm operation on the expected track, the expected speed and the acceleration, the obtained expected Steering wheel angle, the accelerator and the brake amount are sent to the Control subsystem through a CAN (controller area network) line, and the Control subsystem controls the response of executing mechanisms such as a motor, an automatic Steering engine, an EBS (Electric Braking System), a BCM (Body Control Module), an EPS (Electric Power Steering), and the like, so that the automatic Control of Steering, acceleration and deceleration and other auxiliary functions (Steering lamps, brake lamps, and the like) of the sanitation vehicle is realized, and the vehicle CAN keep the expected running track, the expected speed and the acceleration.
Therefore, when an obstacle target or other road participants appear in front of the cleaning path, the decision-making subsystem can perform secondary path planning in real time according to the actual situation, determine operations such as deceleration vehicle following, parking collision avoidance or bypassing overtaking and the like, and send corresponding transverse control commands and longitudinal control commands to the control subsystem.
On the basis of the above embodiment, the automatic driving system of this embodiment further includes a storage subsystem, and the positioning subsystem is further configured to record the cleaning route in advance, and store the cleaning route in the storage subsystem.
In the embodiment, the sanitation vehicle cleaning route is manually driven by utilizing the characteristic that the sanitation vehicle cleaning route is complex but fixed, and a plurality of cleaning routes are prerecorded by using the positioning subsystem and stored in the storage subsystem, so that the cleaning route can be automatically selected according to vehicle pose information during automatic driving each time or manually selected by the HMI subsystem. The method not only gets rid of the limitation of the high-precision map, enlarges the range of the scene working conditions, but also reduces the cost for manufacturing the high-precision map.
The HMI subsystem runs on a tablet personal computer, receives and displays automatic driving information through an LAN (Local Area Network), can display vehicle speed state, sensor state, fault lamp display and the like besides vehicle position and attitude information, road environment information and path planning, and can also be provided with one-key start/exit automatic driving mode operation to improve the convenience of man-machine interaction.
In this embodiment, when the automatic driving mode is determined, the HMI subsystem may further perform basic parameter setting for automatic driving through a human-computer interaction interface of the tablet computer. The basic parameters include a target vehicle speed and a cleaning route selection.
Further, the automatic driving system of the embodiment further includes a monitoring Monitor subsystem, and the monitoring subsystem is configured to Monitor a working state of the sensor subsystem in real time and send abnormal information to the HMI subsystem and the control subsystem when the sensor subsystem is abnormal.
The HMI subsystem is also used for controlling and sending out an alarm according to the abnormal information; the control subsystem is also used for controlling deceleration and parking according to the abnormal information.
In this embodiment, the monitoring subsystem is further configured to monitor states of the execution mechanisms such as the EBS and the EPS in real time, and when the EBS or the EPS fails, the monitoring subsystem also sends the abnormal information to the HMI subsystem and the control subsystem, so as to further increase driving safety.
In the embodiment, the selected cleaning route is taken as a primary planned route for tracking driving, a sensing subsystem is used for accurately detecting the target condition of obstacles around the vehicle and the road environment, when the obstacle target appears on the cleaning route, a decision subsystem is used for sampling a pre-aiming point, generating an alternative route, searching an optimal route and the like according to an information situation map provided by the sensing subsystem, a driving situation map is generated in real time to serve as a secondary planned route, behavior planning is determined, a transverse control command and a longitudinal control command are generated and sent to a control subsystem, the control subsystem controls the environmental sanitation vehicle to realize automatic control of steering, acceleration and deceleration and other auxiliary functions (steering lamps, brake lamps and the like), and the vehicle keeps an expected driving track and expected speed and acceleration.
The control system is not restricted by factors such as road environment and the like, effectively ensures the reliability and safety of automatic driving, and can realize the automatic driving control of the sanitation vehicle under all scene working conditions.
The invention also provides an embodiment of a control method applied to the automatic driving system, which comprises the following steps:
s1, collecting vehicle pose information after an automatic driving mode is determined, and selecting a pre-recorded cleaning route according to the pose information; selecting a positioning mode in real time according to the signal intensity;
s2, acquiring road environment information of a road sanitation vehicle and distance and speed information of barrier targets around the sanitation vehicle, and generating an information situation map according to the cleaning route;
and S3, generating a driving situation map according to the information situation map, and further generating a transverse control command and a longitudinal control command, wherein the driving situation map comprises a path plan of a traveling route.
The driving situation map generation comprises two main parts of data updating and decision element extraction, so that a transverse control command and a longitudinal control command can be generated subsequently.
And S4, executing the transverse control command and the longitudinal control command, and synchronously executing a preset cleaning task.
Further, in step S1, selecting a positioning method in real time according to the magnitude of the signal strength includes:
and when the high-precision signal intensity is smaller than the signal threshold, positioning by adopting a laser positioning module.
And when the high-precision signal intensity is greater than or equal to the signal threshold, positioning by adopting a high-precision positioning module.
On the basis of the foregoing embodiment, in this embodiment, the generating the information situation map in step S2 specifically includes:
firstly, data obtained by a monocular camera, a laser radar, a millimeter wave radar, an ultrasonic radar and high-precision inertial navigation are read, and time and space synchronization is carried out by combining the data and a cleaning route.
And then, performing feature extraction and road information extraction on the data and the cleaning route, and combining the vehicle pose information through a perception fusion algorithm to generate the information situation map.
On the basis of the foregoing embodiment, in this embodiment, after the step S3 generates the driving situation map according to the information situation map, the method further includes: and performing behavior planning according to the driving situation diagram. The behavior planning comprises bypassing overtaking, parking waiting, decelerating and following and keeping constant-speed running in a lane.
The lateral control commands and the longitudinal control commands are generated based on the behavioral plan.
On the basis of the foregoing embodiment, in this embodiment, performing behavior planning according to the driving situation map specifically includes:
when the obstacle target in front of the vehicle is a static obstacle, if the size of the static obstacle is smaller than the bypassing range, determining that the behavior plan is bypassing overtaking; and if the size of the static barrier is larger than the bypassing range, determining the behavior plan as parking waiting to avoid collision.
When the obstacle target in front of the vehicle is a dynamic obstacle, if the speed of the dynamic obstacle is lower than that of the sanitation vehicle, determining that the behavior is planned to be a deceleration following vehicle, wherein the following target is the dynamic obstacle; and if the speed of the dynamic barrier is greater than or equal to that of the sanitation vehicle, determining the behavior plan to keep the vehicle running at a constant speed in the lane.
The control method of the embodiment is suitable for the respective automatic driving systems, can record the cleaning route in advance, and then selects the cleaning route according to the pose information of the sanitation vehicle; meanwhile, the running track is planned in real time, all scene requirements of automatic driving of the sanitation vehicle are met, and safety and reliability of automatic driving are effectively guaranteed.
The present invention is not limited to the above-described embodiments, and it will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the principle of the present invention, and such modifications and improvements are also considered to be within the scope of the present invention. Those not described in detail in this specification are within the skill of the art.
Claims (10)
1. An automatic driving system of a sanitation vehicle, which is characterized by comprising:
the positioning subsystem is used for updating the pose information of the vehicle in real time and selecting a pre-recorded cleaning route according to the initial pose information; the positioning system is also used for automatically switching the positioning mode in real time according to the signal intensity;
the perception subsystem is used for acquiring road environment information of a road sanitation vehicle and distance and speed information of barrier targets around the sanitation vehicle and generating an information situation map according to the cleaning route;
the decision-making subsystem is used for generating a driving situation map according to the information situation map so as to generate a transverse control command and a longitudinal control command; the driving situation map comprises a path plan of a travel route;
the control subsystem is also used for receiving and executing the transverse control command and the longitudinal control command and synchronously executing a preset cleaning task;
the HMI subsystem is used for man-machine interaction and determining to adopt an automatic driving mode or a manual driving mode; the system is also used for displaying vehicle pose information, road environment information and path planning in the automatic driving process.
2. The sanitation vehicle autopilot system of claim 1, wherein the positioning subsystem comprises:
the high-precision positioning module is used for generating vehicle pose information according to the high-precision positioning signal;
the laser positioning module is used for generating vehicle pose information according to the laser positioning signals;
and the switching module is used for positioning by adopting the laser positioning module when the intensity of the high-precision positioning signal is smaller than a signal threshold value, or positioning by adopting the high-precision positioning module.
3. The sanitation vehicle autopilot system of claim 1 wherein the sensory subsystem comprises:
a monocular camera installed in the cab, the monocular camera being configured to detect an obstacle target in front of a vehicle and on both sides of the front of the vehicle;
a vision sensor mounted in the cab, the vision sensor for identifying obstacle target types ahead of travel, the obstacle target types including pedestrians, vehicles, and lane lines;
two laser radars respectively arranged below the left side and the right side of the cab, wherein the laser radars are used for detecting the types of the obstacle targets in the driving front and the two sides of the driving front and detecting the road edges on the two sides of the driving front; the classes of obstacle targets include static obstacles and dynamic obstacles;
the millimeter wave radar is arranged in the middle below the cab and used for performing supplementary detection on the category of the obstacle target, detecting a long-distance obstacle target in front of driving, and calculating the distance between the long-distance obstacle target and the sanitation vehicle and the speed of the long-distance obstacle target;
the system comprises six ultrasonic radars, a driving cab and a driving cab, wherein the six ultrasonic radars are arranged below the driving cab and symmetrically distributed on two sides of the millimeter wave radars, are used for detecting short-distance obstacle targets on two sides of the sanitation vehicle and are also used for calculating the distance between the short-distance obstacle targets and the sanitation vehicle and the speed of the short-distance obstacle targets;
the high-precision inertial navigation system is used for detecting the position and the posture of the sanitation vehicle;
and the information fusion module is respectively connected with the monocular camera, the laser radar, the millimeter wave radar, the ultrasonic radar and the high-precision inertial navigation.
4. The sanitation vehicle autopilot system of claim 1, wherein: the decision-making subsystem is also used for carrying out behavior planning according to the path planning; the behavior planning comprises bypassing overtaking, parking waiting, decelerating and following and keeping constant-speed running in a lane;
the lateral control commands and the longitudinal control commands are generated based on the behavioral plan.
5. The sanitation vehicle autopilot system of claim 1, wherein: the cleaning system also comprises a storage subsystem, and the positioning subsystem is also used for recording the cleaning route in advance and storing the cleaning route in the storage subsystem.
6. The sanitation vehicle autopilot system of claim 1, wherein: the monitoring subsystem is used for monitoring the working state of the perception subsystem and sending abnormal information to the HMI subsystem and the control subsystem when the perception subsystem is abnormal;
the HMI subsystem is also used for controlling to send out an alarm according to the abnormal information;
the control subsystem is also used for controlling deceleration and parking according to the abnormal information.
7. A control method applied to the automatic driving system according to claim 1, characterized by comprising the steps of:
when the automatic driving mode is determined, vehicle pose information is collected, and a pre-recorded cleaning route is selected according to the pose information; selecting a positioning mode in real time according to the signal intensity;
collecting road environment information of a road sanitation vehicle and distance and speed information of barrier targets around the sanitation vehicle, and generating an information situation map according to the cleaning route;
generating a driving situation map according to the information situation map, further generating a transverse control command and a longitudinal control command, wherein the driving situation map comprises a path plan of a traveling route,
and executing the transverse control command and the longitudinal control command, and synchronously executing a preset cleaning task.
8. The control method according to claim 7, wherein the selecting a positioning manner in real time according to the magnitude of the signal strength specifically comprises:
when the high-precision signal intensity is smaller than the signal threshold, a laser positioning module is adopted for positioning;
and when the high-precision signal intensity is greater than or equal to the signal threshold, positioning by adopting a high-precision positioning module.
9. The control method of claim 7, after generating the driving situation map from the information situation map, further comprising:
performing behavior planning according to the driving situation map, wherein the behavior planning comprises bypassing and overtaking, stopping and waiting, decelerating and following and keeping constant-speed running in a lane;
the lateral control commands and the longitudinal control commands are generated based on the behavioral plan.
10. The control method according to claim 9, wherein performing a behavior plan according to the driving situation map specifically includes:
when the obstacle target in front of the vehicle is a static obstacle, if the size of the static obstacle is smaller than the bypassing range, determining that the behavior plan is bypassing overtaking, and otherwise, stopping and waiting;
when the obstacle target in front of the vehicle is a dynamic obstacle, if the speed of the dynamic obstacle is smaller than that of the sanitation vehicle, the behavior plan is determined to be deceleration vehicle following, the vehicle following target is the dynamic obstacle, and otherwise the vehicle keeps running at a constant speed in a lane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010074713.8A CN111258318A (en) | 2020-01-22 | 2020-01-22 | Automatic driving system of sanitation vehicle and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010074713.8A CN111258318A (en) | 2020-01-22 | 2020-01-22 | Automatic driving system of sanitation vehicle and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111258318A true CN111258318A (en) | 2020-06-09 |
Family
ID=70949187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010074713.8A Pending CN111258318A (en) | 2020-01-22 | 2020-01-22 | Automatic driving system of sanitation vehicle and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111258318A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111781937A (en) * | 2020-08-07 | 2020-10-16 | 江苏普达迪泰科技有限公司 | Unmanned formation control system of foreign matter detection and cleaning system and control method thereof |
| CN111962436A (en) * | 2020-08-26 | 2020-11-20 | 吉林大学 | Unmanned automatic planning environment-friendly sweeper for non-motor vehicle lane and sweeping method |
| CN112526997A (en) * | 2020-12-07 | 2021-03-19 | 中国第一汽车股份有限公司 | Automatic driving perception system and method and vehicle |
| CN112622890A (en) * | 2020-11-26 | 2021-04-09 | 深兰人工智能(深圳)有限公司 | Cleaning vehicle |
| CN112833899A (en) * | 2020-12-31 | 2021-05-25 | 吉林大学 | Full-coverage path planning method for unmanned sanitation vehicle |
| CN114056351A (en) * | 2021-11-26 | 2022-02-18 | 文远苏行(江苏)科技有限公司 | Automatic driving method and device |
| CN114252086A (en) * | 2021-12-22 | 2022-03-29 | 北京百度网讯科技有限公司 | Prompt message output method, device, equipment, medium and vehicle |
| CN114440928A (en) * | 2022-01-27 | 2022-05-06 | 杭州申昊科技股份有限公司 | Combined calibration method for laser radar and odometer, robot, equipment and medium |
| CN114435400A (en) * | 2022-01-29 | 2022-05-06 | 苏州挚途科技有限公司 | Starting method of unmanned sanitation vehicle, unmanned sanitation vehicle and electronic equipment |
| CN115246417A (en) * | 2021-07-29 | 2022-10-28 | 上海仙途智能科技有限公司 | Job execution method, device, equipment and computer readable storage medium |
| WO2023232046A1 (en) * | 2022-05-31 | 2023-12-07 | 武汉路特斯汽车有限公司 | Vehicle control method and control system based on vehicle-to-everything |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2177965A2 (en) * | 2008-10-15 | 2010-04-21 | Deere & Company | High integrity coordination for multiple off-road machines |
| CN103995537A (en) * | 2014-05-09 | 2014-08-20 | 上海大学 | Indoor and outdoor mixed autonomous cruising system and method of aircraft |
| CN108445885A (en) * | 2018-04-20 | 2018-08-24 | 鹤山东风新能源科技有限公司 | A kind of automated driving system and its control method based on pure electric vehicle logistic car |
| CN108490941A (en) * | 2018-03-29 | 2018-09-04 | 奇瑞汽车股份有限公司 | Applied to the automated driving system and its control method of road sweeper, device |
| CN109827574A (en) * | 2018-12-28 | 2019-05-31 | 中国兵器工业计算机应用技术研究所 | A kind of unmanned plane indoor and outdoor switching navigation system |
-
2020
- 2020-01-22 CN CN202010074713.8A patent/CN111258318A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2177965A2 (en) * | 2008-10-15 | 2010-04-21 | Deere & Company | High integrity coordination for multiple off-road machines |
| CN103995537A (en) * | 2014-05-09 | 2014-08-20 | 上海大学 | Indoor and outdoor mixed autonomous cruising system and method of aircraft |
| CN108490941A (en) * | 2018-03-29 | 2018-09-04 | 奇瑞汽车股份有限公司 | Applied to the automated driving system and its control method of road sweeper, device |
| CN108445885A (en) * | 2018-04-20 | 2018-08-24 | 鹤山东风新能源科技有限公司 | A kind of automated driving system and its control method based on pure electric vehicle logistic car |
| CN109827574A (en) * | 2018-12-28 | 2019-05-31 | 中国兵器工业计算机应用技术研究所 | A kind of unmanned plane indoor and outdoor switching navigation system |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111781937A (en) * | 2020-08-07 | 2020-10-16 | 江苏普达迪泰科技有限公司 | Unmanned formation control system of foreign matter detection and cleaning system and control method thereof |
| CN111962436A (en) * | 2020-08-26 | 2020-11-20 | 吉林大学 | Unmanned automatic planning environment-friendly sweeper for non-motor vehicle lane and sweeping method |
| CN111962436B (en) * | 2020-08-26 | 2021-05-07 | 吉林大学 | Unmanned automatic planning environment-friendly sweeper for non-motor vehicle lane and sweeping method |
| CN112622890A (en) * | 2020-11-26 | 2021-04-09 | 深兰人工智能(深圳)有限公司 | Cleaning vehicle |
| CN112526997A (en) * | 2020-12-07 | 2021-03-19 | 中国第一汽车股份有限公司 | Automatic driving perception system and method and vehicle |
| CN112833899A (en) * | 2020-12-31 | 2021-05-25 | 吉林大学 | Full-coverage path planning method for unmanned sanitation vehicle |
| CN112833899B (en) * | 2020-12-31 | 2022-02-15 | 吉林大学 | Full-coverage path planning method for unmanned sanitation vehicle |
| CN115246417A (en) * | 2021-07-29 | 2022-10-28 | 上海仙途智能科技有限公司 | Job execution method, device, equipment and computer readable storage medium |
| CN115246417B (en) * | 2021-07-29 | 2023-08-25 | 上海仙途智能科技有限公司 | Job execution method, apparatus, device, and computer-readable storage medium |
| CN114056351A (en) * | 2021-11-26 | 2022-02-18 | 文远苏行(江苏)科技有限公司 | Automatic driving method and device |
| CN114056351B (en) * | 2021-11-26 | 2024-02-02 | 文远苏行(江苏)科技有限公司 | Automatic driving method and device |
| CN114252086A (en) * | 2021-12-22 | 2022-03-29 | 北京百度网讯科技有限公司 | Prompt message output method, device, equipment, medium and vehicle |
| CN114252086B (en) * | 2021-12-22 | 2023-03-03 | 北京百度网讯科技有限公司 | Prompt message output method, device, equipment, medium and vehicle |
| CN114440928A (en) * | 2022-01-27 | 2022-05-06 | 杭州申昊科技股份有限公司 | Combined calibration method for laser radar and odometer, robot, equipment and medium |
| CN114435400A (en) * | 2022-01-29 | 2022-05-06 | 苏州挚途科技有限公司 | Starting method of unmanned sanitation vehicle, unmanned sanitation vehicle and electronic equipment |
| WO2023232046A1 (en) * | 2022-05-31 | 2023-12-07 | 武汉路特斯汽车有限公司 | Vehicle control method and control system based on vehicle-to-everything |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111258318A (en) | Automatic driving system of sanitation vehicle and control method thereof | |
| US11835959B1 (en) | Determining the stationary state of detected vehicles | |
| EP3795457B1 (en) | Preparing autonomous vehicles for turns | |
| US9862364B2 (en) | Collision mitigated braking for autonomous vehicles | |
| CN111169479A (en) | Cruise control method, device and system, vehicle and storage medium | |
| EP3175311A1 (en) | Traffic signal response for autonomous vehicles | |
| CN117485240A (en) | Reporting device | |
| US11702087B2 (en) | Autonomous driving monitoring system | |
| US20220366175A1 (en) | Long-range object detection, localization, tracking and classification for autonomous vehicles | |
| CN112824175A (en) | Vehicle parking system | |
| US20200250980A1 (en) | Reuse of Surroundings Models of Automated Vehicles | |
| WO2023010043A1 (en) | Complementary control system for an autonomous vehicle | |
| US20220055659A1 (en) | Mode selection according to system conditions | |
| WO2023010042A1 (en) | Complementary control system for an autonomous vehicle | |
| CN113022552B (en) | Automatic parking system based on laser radar and V2I technology and control method | |
| JP7291015B2 (en) | Surrounding object recognition method and surrounding object recognition device | |
| US11325529B2 (en) | Early brake light warning system for autonomous driving vehicle | |
| JP2019043431A (en) | Travel control device, and travel control method and program | |
| CN114274978A (en) | Obstacle avoidance method for unmanned logistics vehicle | |
| JP2021160399A (en) | Vehicle control device, vehicle control method, and program | |
| CN113728324A (en) | Low-height obstacle detection system based on point cloud | |
| CN212172193U (en) | Intelligent networking automatic driving system suitable for mini bus | |
| US20230249680A1 (en) | Systems and methods for navigating a trailer with a vehicle when a physical connection disconnects | |
| US20230406293A1 (en) | Secondary fallback software stack for autonomous vehicle | |
| US20230047336A1 (en) | Time gaps for autonomous vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |
|
| RJ01 | Rejection of invention patent application after publication |