CN111427348A - Automatic drive mining dump truck environmental perception system and mining dump truck - Google Patents
Automatic drive mining dump truck environmental perception system and mining dump truck Download PDFInfo
- Publication number
- CN111427348A CN111427348A CN202010211530.6A CN202010211530A CN111427348A CN 111427348 A CN111427348 A CN 111427348A CN 202010211530 A CN202010211530 A CN 202010211530A CN 111427348 A CN111427348 A CN 111427348A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- millimeter wave
- laser radar
- dump truck
- radar
- 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
- 238000005065 mining Methods 0.000 title claims abstract description 63
- 230000007613 environmental effect Effects 0.000 title claims description 13
- 230000008447 perception Effects 0.000 title claims description 7
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 description 29
- 238000009434 installation Methods 0.000 description 9
- 230000000007 visual effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007903 penetration ability Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012360 testing method Methods 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
- G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons in combination with a laser
-
- 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
- G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
-
- 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 environment sensing system for an automatic driving mining dump truck and the mining dump truck, which comprise a vehicle-mounted computing unit: receiving data of an environment sensing system, extracting and processing the data, and sending a processing result to a central control unit of a vehicle; the environment sensing system includes: laser radar, millimeter wave radar, image sensor and combination navigation equipment, wherein: laser radar: detecting target information right in front of and behind the vehicle; millimeter wave radar: detecting target information in the front and at two sides of the vehicle; an image sensor: detecting target information around the vehicle; the combined navigation equipment is provided with a GPS antenna: position information of the vehicle is acquired in real time. According to the invention, the environment information is obtained through the millimeter wave radar and the image sensor, and the environment information is fused with the laser radar data, so that the phenomenon of insufficient precision of the radar can be made up, the automatic driving safety is improved, and the cost is reduced as much as possible while the normal work and the vehicle safety are ensured.
Description
Technical Field
The invention relates to the technical field of automatic driving of mining dump trucks, in particular to an environment sensing system for automatically driving a mining dump truck and the mining dump truck.
Background
The automatic driving mining dump truck is also called unmanned mining truck, called unmanned mining truck for short as unmanned mining truck, and is mainly an intelligent mining dump truck which realizes the automatic driving technology through a vehicle-mounted computing unit. As an essential technical support for automatic driving, an on-board sensor is the most important carrier on which the on-board sensor depends, and therefore, the sensor layout is an important link of an automatic driving automobile. The premise that the mining dump truck can stably run is mainly through sensing the surrounding environment information of the mining dump truck. In detail, namely: the unmanned mine card mainly relies on components such as a laser radar, a millimeter wave radar, a vehicle-mounted image sensor and the like to obtain surrounding environment information of the mining dump truck, and identifies and navigates a driving road. The laser radar and the millimeter wave radar are core components for detecting the surrounding environment, and the combined inertial navigation sensor is a component for positioning the road. When the existing sensor of the automatic driving mining dump truck is designed and arranged, a plurality of laser radars and a set of combined navigation system are generally equipped to realize the main functions of the automatic driving mining dump truck.
In the prior art, the research on unmanned technology is mainly carried out on urban road passenger cars, logistics cars, scenic spot sightseeing cars, scientific research trolley test platforms and small mining dump trucks, and the corresponding layout of a sensor system is also determined based on the actual driving environment and the conditions of the vehicles. The research object and the driving environment are urban roads, expressways or scenic spot roads. The environment information is varied, and the development of the environment information is slow due to pedestrians and other uncertain factors. For example: patent application CN201710160870.9 discloses an environmental sensing system for a vehicle and a vehicle, and mainly describes an automatic driving sensor layout for a passenger vehicle. However, few people determine the target on the large-scale engineering mining dump truck, and the automatic driving system of the common passenger car cannot be directly transplanted to the large-scale engineering mining dump truck because the operating environment and the vehicle structure of the large-scale engineering mining dump truck are greatly different from those of the common passenger car.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an environment sensing system for an automatic driving mining dump truck and the mining dump truck, and solves the technical problems that the sensing scanning range is limited, the range of a blind area is reduced to the maximum extent, and the detection precision of environment sensing is not high in the prior art.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the utility model provides an automatic drive mining dump truck environmental perception system which characterized in that: the method comprises the following steps:
an in-vehicle computing unit: receiving data of an environment sensing system, extracting and processing the data, and sending a processing result to a central control unit of a vehicle;
the environment sensing system includes: laser radar, millimeter wave radar, image sensor and combination navigation equipment, wherein:
laser radar: detecting target information right in front of and behind the vehicle;
millimeter wave radar: detecting target information in the front and at two sides of the vehicle;
an image sensor: detecting target information around the vehicle;
the combined navigation equipment is provided with a GPS antenna: position information of the vehicle is acquired in real time.
The laser radar comprises thirty-two line laser radar, sixteen line laser radar and four line laser radar;
the thirty-two line laser radar is arranged in the middle position right in front of the vehicle and used for detecting target information right in front of the vehicle;
the sixteen-line laser radar is arranged in the middle part right behind the vehicle and used for detecting target information right behind the vehicle;
the four-line laser radar system comprises three four-line laser radars, wherein two of the three four-line laser radars are symmetrically arranged on two sides of the middle of the front of a vehicle and are used for detecting target information in the front of the vehicle; the other is arranged at the middle part right behind the vehicle, and the distance from the lower edge of the cargo box is about one half of the height from the edge of the cargo box line to the ground;
the millimeter wave radar comprises a long-distance millimeter wave radar and two short-distance millimeter wave radars;
the long-distance millimeter wave radar is arranged in the middle position right in front of the vehicle, and the transmitting surface faces the right front of the vehicle;
the two short-distance millimeter wave radars are arranged on the left side and the right side in front of the vehicle, and the transmitting surfaces of the two short-distance millimeter wave radars deviate towards the side part of the vehicle;
there are four image sensors, two of which are disposed at one side portion of the vehicle and the other two of which are disposed at the other side portion of the vehicle.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the on-board computing unit is disposed in a cabinet inside a vehicle cab.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the long-distance millimeter wave radar is a 76GHz millimeter wave radar, and the short-distance millimeter wave radar is a 76GHz millimeter wave radar.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the antenna emission surface of the short-distance millimeter wave radar is perpendicular to the ground, and the included angle between the antenna emission surface and the whole longitudinal symmetrical plane of the mining dump truck is 30 degrees.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the included angle between the central horizontal plane of the sixteen-line laser radar and the horizontal plane is 18.5 degrees.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the four-wire laser radar that the symmetry set up in the middle of the dead ahead of vehicle both sides is located each one in the dead ahead middle part left and right sides of automobile body, and is one tenth of vehicle width with the longitudinal symmetry plane distance of vehicle, and the axis of left side four-wire laser radar transmitting face is 30 degrees with the longitudinal symmetry plane contained angle of vehicle, and the axis of right side four-wire laser radar transmitting face is 40 degrees with the longitudinal symmetry plane contained angle of vehicle.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the included angle between the central horizontal plane of the four-wire laser radar arranged at the middle part right behind the vehicle and the horizontal plane is 8 degrees.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: thirty-two line laser radar, sixteen line laser radar, four line laser radar, network image sensor all pass through ethernet and vehicle-mounted computing unit connection, and long range millimeter wave radar and short range millimeter wave radar, combination navigation equipment pass through the CAN bus and are connected with vehicle-mounted computing unit.
As a preferred aspect of the present invention, the environment sensing system for an autonomous mining dump truck comprises: the two GPS antennas are respectively arranged on the left side and the right side right above the cab.
A mining dump truck, characterized in that: an environment awareness system for an autonomous mining dump truck comprising any of the foregoing.
The invention achieves the following beneficial effects:
compared with the prior art, the invention replaces sixty-four-wire or one hundred twenty-eight-wire laser radar in the prior art by the combined use of the sixteen-wire laser radar and the four-wire laser radar, and can greatly reduce the configuration cost of the automatic driving automobile; when the laser radar is installed and selected, the millimeter wave radar and the image sensor are adopted to obtain the environmental information, and the environmental information is fused with the laser radar data, so that the phenomenon of insufficient precision of the radar can be compensated, and the automatic driving safety is improved; the sensing scanning range almost covers the whole area of the mining dump truck by installing the millimeter wave radar, the laser radar and the image sensor around the mine truck, the range of blind areas is reduced to the maximum extent, and the detection precision of environment sensing is improved. In addition, the remote control can be carried out by utilizing the image sensor through the network, so that the running reliability and safety of the automatic driving mine car are improved, and the risk can be reduced.
The invention can meet the operating environment of the large-scale engineering mining dump truck and the use requirements of the vehicle structure, and reduces the cost as much as possible while ensuring the normal work and the vehicle safety.
Drawings
FIG. 1 is a system composition diagram of the present invention;
FIG. 2 is a top view of the layout of the environmental awareness system of the present invention;
FIG. 3 is a front view of the layout of the context awareness system of the present invention;
FIG. 4 is a left side view of the layout of the context awareness system of the present invention;
the meaning of the reference numerals: 1-thirty-two line lidar; 2-sixteen-line laser radar; 3-four line lidar; 4-long range millimeter wave radar; 5-short range millimeter wave radar; 6-an image sensor; 7-a GPS antenna; 8-radio antenna.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in fig. 1 to 4: the embodiment discloses an environmental perception system of an automatic driving mining dump truck, which comprises: on-vehicle computational unit and environmental perception system, wherein:
an in-vehicle computing unit: and receiving the data of the environment sensing system, extracting and processing the data, and sending the processing result to a central control unit of the vehicle, wherein the vehicle-mounted computing unit is preferably arranged in a cabinet in the cab of the vehicle.
The environment perception system comprises various sensors and an image acquisition device, and specifically comprises: laser radar, millimeter wave radar, image sensor 6 and combination navigation equipment, wherein:
laser radar: target information directly in front of and directly behind the vehicle is detected. The lidar of this embodiment includes thirty two-wire lidar 1, sixteen-wire lidar 2, four-wire lidar 3, and three kinds of lidar are 1, two respectively.
For better collecting target information, the thirty-two line laser radar 1 is arranged in the middle position right in front of the vehicle and used for detecting the target information right in front of the vehicle, the distance between the thirty-two line laser radar 1 and the roof of the vehicle is one third of the height of the vehicle, and the distance between the thirty-two line laser radar 1 and the two sides of the vehicle is equal, for example, the thirty-two line laser radar 1 can be arranged in the middle position above a radiator frame right in front, the installation height of the thirty-two line laser radar is higher than the middle position in front of the vehicle, the horizontal visual angle of the radar scanning range is 360 degrees, the vertical visual angle.
The sixteen-line laser radar 2 is arranged in the middle of the right rear portion of the vehicle and used for detecting target information of the right rear portion of the vehicle, is located at a position which is one half of the height from the edge of the cargo box line to the ground and is equal to the distance between the lower edge of the cargo box line and the two sides of the vehicle, and has an included angle of 18.5 degrees (assuming the ground level) between the central horizontal plane of the radar and the ground, and can be arranged in the middle of a tail lamp support of the frame of the right rear portion of the vehicle and the installation height of about 1. The sixteen-line laser radar 2 scans 360 degrees horizontally, the vertical visual angle is 15 degrees respectively from top to bottom, and the installation inclination angle is 18.5 degrees downwards, so that the blind area close to a vehicle can be reduced.
Three four-line laser radars 3 are provided, two of which are symmetrically arranged at two sides of the middle of the front of the vehicle (symmetrically arranged by taking the center line of the vehicle as the center) and are used for detecting target information in the front of the vehicle; the two laser radars are arranged right in front of the vehicle, are respectively positioned on the left side and the right side of the middle part right in front of the vehicle body, have a distance of one tenth of the width of the vehicle from a longitudinal symmetrical plane of the vehicle, can be arranged on two sides of the middle part of a bumper right in front of the vehicle, for example, the laser radars can be horizontally arranged at the emitting points, and the installation height is between 0.25 and 0.3 meter. Furthermore, the included angle between the longitudinal symmetry axis of the left laser radar emitting surface and the longitudinal symmetry plane of the vehicle is 30 degrees (the included angle between the emitting center and the center line of the vehicle is 30 degrees), and the included angle between the longitudinal symmetry axis of the right laser radar emitting surface and the longitudinal symmetry plane of the vehicle is 40 degrees (the included angle between the emitting center and the center line of the vehicle is 30 degrees). The two four-line laser radars 3 arranged in front of the vehicle are mainly used for detecting target information in a short distance in front of the vehicle and compensating blind areas in short distance detection at two sides of the thirty-two-line radar 1, including information such as distance, angle, reflection intensity and speed of the target.
The other four-line laser radar 3 is arranged in the middle part right behind the vehicle, the distance from the lower edge of the cargo box is about one half of the height from the edge of the cargo box line to the ground, and the included angle between the central horizontal plane of the radar and the ground is preferably 8 degrees (assuming the ground level).
The millimeter wave radar is used for detecting target information in the front of the vehicle and on two sides of the vehicle, and comprises a long-distance millimeter wave radar 4 and two short-distance millimeter wave radars 5. Wherein long range millimeter wave radar 4 sets up the intermediate position in the dead ahead of vehicle, mountable in the bumper in the front for survey the target information in the dead ahead of vehicle, and two short range millimeter wave radars 5 set up in the left and right sides place ahead position of vehicle (be in the outside of two four-wire laser radar 3), mountable in the both sides of bumper in the front for survey the target information in vehicle both sides place ahead. The vertical surface of the millimeter wave radar needs to be perpendicular to the driving road surface of the mining dump truck, and the maximum error of an included angle between a radar wave emission plane and the horizontal plane can reach +/-4.5 degrees (including +/-0.5-degree emission plane error generated by the internal installation of the radar); the mounted Yaw angle and the advancing direction of the mining dump truck form an angle of 30 degrees, and a mounting error of +/-5 degrees can be achieved. The actual installation is kept horizontal, the actual installation height is 0.25-0.35 meter, the included angle between the installation position of the millimeter wave radar on the left side of the front and the advancing direction of the mining dump truck is 30 degrees, the included angle between the installation position of the millimeter wave radar on the right side of the front and the advancing direction of the mining dump truck is-30 degrees, the radar has medium-distance and long-distance scanning capabilities, the detectable distance in a medium-distance mode is 50m, the horizontal visual angle is +/-75 degrees, the vertical scanning range is +/-5 degrees, and the detection of the side area is completed by the short-distance millimeter wave radar.
Further, the long-range millimeter wave radar 4 of the present embodiment is preferably a 76GHz millimeter wave radar, with the transmission face directed toward the front of the vehicle body, and the transmission face of the antenna being perpendicular to the ground (assuming that the ground remains horizontal). The emitting surfaces of the two short-distance millimeter wave radars 5 face outwards towards the two sides in front of the vehicle head, the emitting surfaces of the antennas are perpendicular to the ground (the ground is assumed to be horizontal), and the included angle between the emitting surfaces of the antennas and the longitudinal symmetry plane of the vehicle is 30 degrees (30 degrees of outward deflection).
The image sensors 6 are used for detecting target information around the vehicle, and the number of the image sensors 6 in the present embodiment is four, and the four image sensors 6 are respectively arranged at the side part of the vehicle and used for detecting the target information of the environment around the vehicle. The image sensor is convenient for remotely and directly observing the surrounding states of the vehicle, including the information of a drivable area, road information, vehicle information, other ground road conditions and the like.
The combined navigation equipment is used for acquiring the position information of the vehicle in real time, and is arranged in a cab and rigidly connected with the vehicle body. The combined navigation equipment is also connected with two GPS antennae 7, preferably, the two GPS antennae 7 are provided, and the 2 GPS antennae 7 are arranged at the left side and the right side right above the cab and are used for acquiring information such as the position, the course, the yaw angle, the speed and the like of the mining dump truck in real time. The invention also includes a radio antenna 8, the radio antenna 8 being mounted on the top of the cargo box of the vehicle for better providing accurate positioning information.
The vehicle-mounted computing unit is arranged in a cabinet in the cab and is connected with the laser radar, the millimeter wave radar, the camera and the combined navigation equipment through a CAN bus or an Ethernet.
When the system works, the vehicle-mounted computing unit acquires information detected by the 4 image sensors 6 to obtain real-time environment information in a surrounding feasible region range; the vehicle-mounted computing unit acquires information detected by the thirty-two-line laser radar 1 to obtain middle-distance and long-distance environment information right in front of the vehicle; the vehicle-mounted computing unit acquires information detected by the sixteen-line laser radar 2 to obtain long-distance environment information in the front and rear of the vehicle; the vehicle-mounted computing unit acquires information detected by the four-wire laser radar 3 to obtain the environmental information of short distance right behind and in front of the vehicle; the vehicle-mounted computing unit acquires the information of the detected long-distance millimeter wave radar 4 to obtain the long-distance and medium-distance environment information right in front of the vehicle; the vehicle-mounted computing unit acquires the information of the detected short-distance millimeter wave radar 5 to obtain the information of the close-distance environment at the left side and the right side of the vehicle; and finally, the vehicle-mounted computing unit performs fusion computing processing on the obtained information to determine the optimal running path of the automatic driving mining dump truck, so that the automatic driving function is realized.
And respectively converting the obstacle data acquired by the laser radar and the millimeter wave radar into corresponding vehicle body coordinate systems. Since there are many types of lidar, and there may be more than one of each, multi-sensor data fusion is required.
And the ground data is detected by adopting a plurality of planes to fit the road surface and combining the height difference of the grid map and the neighborhood difference value. The traditional laser radar processing scheme needs to separate ground points from elevated points. On a structured road (mainly comprising an expressway and an urban arterial road), the road surface can be approximate to a plane, and the road surface is extracted by a plane extraction method. On an unstructured road, the road is rugged, and a plurality of planes are adopted to fit the road surface. And the height difference of the grid map is combined with the detection method of the neighborhood difference, but the method of extracting through the plane in the prior art has larger errors.
In the embodiment, the grid map height difference and neighborhood difference detection method is adopted, so that the ground can be stably and effectively detected.
And drawing a 0 and 1 binary image of the ground-elevated point by combining the height difference of the grid map with the ground detection of the neighborhood difference value. Firstly, rasterizing the laser radar point cloud data to obtain a grid map of N x N; then calculating the difference between the maximum value and the minimum value of the point cloud elevation in each grid, calculating the gradient of the point cloud elevation, comparing the difference A with a preset threshold D1, filtering out the points (A is larger than D1) with the difference larger than the threshold as ' overhead points ', reserving the points (A is smaller than D1) with the difference smaller than the threshold, considering the points (A is smaller than D1) with the difference smaller than the threshold as the ground, performing neighborhood difference calculation on the points (A is smaller than D1) with the difference smaller than the threshold, and selecting the neighborhood related to the size of the grid, wherein the selection principle of the embodiment is to consider the grid within 2 meters around the grid as ' the neighborhood; and dividing the point clouds belonging to the ground into a plurality of point cloud intervals according to the vehicle distance distribution, performing plane fitting on the point cloud intervals, and connecting the fitted planes to obtain the road surface. Thus, a 0, 1 binary map of the ground-overhead point is plotted.
And clustering the overhead points by adopting a multi-parameter model. And clustering the 0 and 1 binary images of the ground-elevated points by adopting an eight-connected domain method to obtain elevated point cluster clusters. Due to the fact that the mine scene mine card is large in size and has the characteristic that the outer contour is not a standard rectangle, the situations that point clouds are sparse, target feature points are shielded by the laser radar and a single target is clustered into a plurality of clusters after clustering can occur during laser radar detection. And combining a plurality of clusters into one by adopting a post-processing method of a multi-parameter model to finish the target extraction of the point cloud. Different merging parameters are set according to the size and the density of the clusters, and the clusters with different sizes are merged into one cluster according to the parameters, so that the problem of clustering inaccuracy caused by point cloud sparseness or target irregularity is solved.
Obstacle detection and judgment are performed in a safety detection area based on a vehicle target driving route: converting the clustered clusters into two-dimensional data, calculating convex hull (obstacle) information of the two-dimensional data, and judging whether the two-dimensional data is an obstacle or not according to the convex hull information;
the running track of the vehicle is led into the system, and the left and the right of the running track are respectively expanded by certain width to be used as a safety area for the running of the mine card. And calculating the distance between each convex wrap point and the driving track, and judging whether the cluster is in the safety detection area of the mine card or not according to the distance value and the width of the safety area. If one convex package point distance value is smaller than the width of the safety zone, the obstacle is considered to be in the safety zone, otherwise, the obstacle is not in the safety zone.
Whether the vehicle is in the drivable region is detected. As shown in fig. 3: in order to ensure the safe driving of the mine card, the edge of the road must be effectively detected, and the mine card is prevented from driving into the space outside the road under the condition that the positioning information is invalid.
A travelable region detection method based on a region growing algorithm is adopted. For a 0 and 1 binary image of a ground-elevated point, selecting a central point in front of the mine truck as a seed point, and extracting a non-obstacle area in front of the mine truck by adopting a four-neighborhood growing mode to obtain a driving area. And calculating the distance value between the center point in front of the mine card and the boundary point of the travelable area, sequencing the distance value data to obtain the minimum value, comparing the minimum value with a preset threshold value, and if the minimum value is smaller than the preset threshold value, the vehicle is in danger of touching the obstacle, otherwise, the vehicle is considered not to touch the obstacle in the travelable area.
And matching the laser radar data with the millimeter wave radar data based on the matching distance threshold value, and outputting a final result. Laser radar's advantage lies in that its detection scope is wider, and detection precision is higher, but the performance is relatively poor under extreme weather such as sleet fog, and millimeter wave radar's penetration ability is strong, consequently for the accuracy nature and the security that promote system detection, this embodiment has still adopted millimeter wave radar data to match, specifically as follows:
firstly, the millimeter wave radar data is converted into a vehicle body coordinate system,
and accessing the millimeter wave radar into a noise removal filter, and performing noise removal and tracking processing on a target detected by the millimeter wave radar. The millimeter wave radar is not influenced by conditions such as rain, snow and dust, so that the false detection rate is reduced by matching the detection result of the laser radar with the detection result of the millimeter wave radar. The matching method comprises the following steps: respectively judging whether the millimeter wave radar detection result is matched with the laser radar detection result according to the distance, dynamically distributing the distance threshold value through the dimension information of the obstacle detected by the laser radar, if the matching is successful, saving the laser radar detection result as a final detection result, keeping the distance, the size and the orientation information of the obstacle, if the matching is failed, filtering out the matching failure in the laser radar obstacle, keeping the matching success, and then outputting the effective obstacle information which is successfully matched.
Compared with the prior art, the invention replaces sixty-four-wire or one hundred twenty eight-wire laser radar in the prior art by combining the sixteen-wire laser radar 2 and the four-wire laser radar 3, so that the configuration cost of the automatic driving automobile can be greatly reduced; when the laser radar is installed and selected, the millimeter wave radar and the image sensor 6 are adopted to obtain the environmental information, and the environmental information is fused with the laser radar data, so that the phenomenon of insufficient precision of the radar can be made up, and the automatic driving safety is improved; the sensing scanning range almost covers the whole area of the mining dump truck by installing the millimeter wave radar, the laser radar and the image sensor around the mine truck, the range of blind areas is reduced to the maximum extent, and the detection precision of environment sensing is improved. In addition, can utilize image sensor to carry out remote control through the network, not only improve the reliability and the security of automatic drive mine car traveling, can also reduce the risk, the image sensor of this embodiment is the image sensor who takes infrared function for obstacle detection when laser radar inefficacy, when causing the parking because of the obstacle to the obstacle manual work confirm and remote control.
The invention can meet the operating environment of the large-scale engineering mining dump truck and the use requirements of the vehicle structure, and reduces the cost as much as possible while ensuring the normal work and the vehicle safety.
The invention also aims at the practical application environment of the mining dump truck to effectively detect the obstacles in the road, prevent missing detection and accurately cluster; the method can effectively detect the road edge, ensures the safety, and is particularly suitable for unstructured road environments such as mines and the like. And the method is also suitable for severe conditions such as rain, snow, strong and weak light, dust raising and the like, and has good robustness. From the perspective of an applicable scene, the detection target of the method comprises a structured road besides a mine scene (unstructured road), and the mine card is prevented from entering a space except the road under the condition that the positioning information is invalid.
The invention has better robustness, and adopts a scheme of fusing various radars according to the working principle and the advantages and the disadvantages of the laser radar, and reduces the false detection rate by matching the detection result of the laser radar with the detection result of the millimeter wave radar.
The embodiment also discloses a mining dump truck: the environment sensing system of the automatic driving mining dump truck comprises the embodiment.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. The utility model provides an automatic drive mining dump truck environmental perception system which characterized in that: the method comprises the following steps:
an in-vehicle computing unit: receiving data of an environment sensing system, extracting and processing the data, and sending a processing result to a central control unit of a vehicle;
the environment sensing system includes: laser radar, millimeter wave radar, image sensor and combination navigation equipment, wherein:
laser radar: detecting target information right in front of and behind the vehicle;
millimeter wave radar: detecting target information in the front and at two sides of the vehicle;
an image sensor: detecting target information around the vehicle;
the combined navigation equipment is provided with a GPS antenna: acquiring the position information of the vehicle in real time;
the laser radar comprises thirty-two line laser radar, sixteen line laser radar and four line laser radar;
the thirty-two-line laser radar is arranged in the middle position right in front of the vehicle and used for detecting target information right in front of the vehicle;
the sixteen-line laser radar is arranged in the middle part right behind the vehicle and used for detecting target information right behind the vehicle;
the four-line laser radar system comprises three four-line laser radars, wherein two of the three four-line laser radars are symmetrically arranged on two sides of the middle of the front of a vehicle and are used for detecting target information in the front of the vehicle; the other is arranged at the middle part right behind the vehicle, and the distance from the lower edge of the cargo box is about one half of the height from the edge of the cargo box line to the ground;
the millimeter wave radar comprises a long-range millimeter wave radar and two short-range millimeter wave radars;
the long-distance millimeter wave radar is arranged in the middle position right in front of the vehicle, and the transmitting surface faces the right front of the vehicle;
the two short-distance millimeter wave radars are arranged on the left side and the right side in front of the vehicle, and the radar transmitting surfaces are offset towards the side of the vehicle;
the image sensors are four in number, two image sensors are arranged on one side portion of the vehicle, and the other two image sensors are arranged on the other side portion of the vehicle.
2. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the on-board computing unit is disposed in a cabinet inside a vehicle cab.
3. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the long-distance millimeter wave radar is a 76GHz millimeter wave radar, and the short-distance millimeter wave radar is a 76GHz millimeter wave radar.
4. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the antenna emission surface of the short-distance millimeter wave radar is perpendicular to the ground, and the included angle between the antenna emission surface and the whole longitudinal symmetrical plane of the mining dump truck is 30 degrees.
5. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: and the included angle between the central horizontal plane of the sixteen-line laser radar and the horizontal plane is 18.5 degrees.
6. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the four-wire laser radar that the symmetry set up in the middle of the dead ahead of vehicle both sides is located each one in the dead ahead middle part left and right sides of automobile body, and is one tenth of vehicle width with the longitudinal symmetry plane distance of vehicle, and the axis of left side four-wire laser radar transmitting face is 30 degrees with the longitudinal symmetry plane contained angle of vehicle, and the axis of right side four-wire laser radar transmitting face is 40 degrees with the longitudinal symmetry plane contained angle of vehicle.
7. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the included angle between the central horizontal plane of the four-wire laser radar arranged at the middle part right behind the vehicle and the horizontal plane is 8 degrees.
8. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the thirty-two line laser radar, the sixteen line laser radar, the four line laser radar and the network image sensor are all connected with the vehicle-mounted computing unit through the Ethernet, and the long-distance millimeter wave radar, the short-distance millimeter wave radar and the combined navigation equipment are connected with the vehicle-mounted computing unit through the CAN bus.
9. The context awareness system of the autonomous mining dump truck according to claim 1, wherein: the GPS antennas are arranged on the left side and the right side right above the cab respectively.
10. A mining dump truck, characterized in that: the environment awareness system comprising the autonomous mining dump truck of any of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010211530.6A CN111427348A (en) | 2020-03-24 | 2020-03-24 | Automatic drive mining dump truck environmental perception system and mining dump truck |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010211530.6A CN111427348A (en) | 2020-03-24 | 2020-03-24 | Automatic drive mining dump truck environmental perception system and mining dump truck |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111427348A true CN111427348A (en) | 2020-07-17 |
Family
ID=71548717
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010211530.6A Pending CN111427348A (en) | 2020-03-24 | 2020-03-24 | Automatic drive mining dump truck environmental perception system and mining dump truck |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111427348A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111824053A (en) * | 2020-07-24 | 2020-10-27 | 江苏徐工工程机械研究院有限公司 | Mining truck |
CN112147632A (en) * | 2020-09-23 | 2020-12-29 | 中国第一汽车股份有限公司 | Method, device, equipment and medium for testing vehicle-mounted laser radar perception algorithm |
CN112396043A (en) * | 2021-01-21 | 2021-02-23 | 北京主线科技有限公司 | Vehicle environment information perception method and device, electronic equipment and storage medium |
CN112596050A (en) * | 2020-12-09 | 2021-04-02 | 上海商汤临港智能科技有限公司 | Vehicle, vehicle-mounted sensor system and driving data acquisition method |
CN112614171A (en) * | 2020-11-26 | 2021-04-06 | 厦门大学 | Air-ground integrated dynamic environment sensing system for cluster operation of engineering machinery |
CN112644517A (en) * | 2020-12-29 | 2021-04-13 | 北京宸控科技有限公司 | Automatic driving algorithm for underground vehicle |
CN113009434A (en) * | 2021-02-20 | 2021-06-22 | 纳瓦电子(上海)有限公司 | Millimeter wave radar failure auxiliary device and method thereof |
CN113022408A (en) * | 2021-04-15 | 2021-06-25 | 中国矿业大学 | 360-degree self-adaptive loading and unloading unmanned mining dump truck and control method thereof |
CN113093746A (en) * | 2021-03-31 | 2021-07-09 | 上海三一重机股份有限公司 | Working machine environment sensing method, device and system and working machine |
CN113135181A (en) * | 2021-06-22 | 2021-07-20 | 北京踏歌智行科技有限公司 | Mining area automatic driving loading and unloading point accurate parking method based on visual assistance |
CN113160589A (en) * | 2021-03-04 | 2021-07-23 | 腾讯科技(深圳)有限公司 | Vehicle early warning method and device, electronic equipment and computer readable storage medium |
CN113281783A (en) * | 2021-05-13 | 2021-08-20 | 江苏徐工工程机械研究院有限公司 | Mining truck |
CN113484872A (en) * | 2021-06-16 | 2021-10-08 | 国能榆林能源有限责任公司 | Laser radar underground slope depth detection method and detection vehicle |
CN113820714A (en) * | 2021-09-07 | 2021-12-21 | 重庆驰知科技有限公司 | Dust fog weather road environment perception system based on multi-sensor fusion |
CN114715024A (en) * | 2022-04-15 | 2022-07-08 | 东风柳州汽车有限公司 | Automobile acousto-optic reminding method, automobile acousto-optic reminding equipment, storage medium and automobile acousto-optic reminding device |
WO2022183871A1 (en) * | 2021-03-04 | 2022-09-09 | 上海申传电气股份有限公司 | Construction method for dynamic envelope line for electric locomotive for mine railway |
CN117111058A (en) * | 2023-10-24 | 2023-11-24 | 青岛慧拓智能机器有限公司 | Unmanned perception system and method for mining truck |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106909152A (en) * | 2017-03-17 | 2017-06-30 | 奇瑞汽车股份有限公司 | A kind of automobile-used context aware systems and automobile |
CN208149310U (en) * | 2018-05-11 | 2018-11-27 | 北京智行者科技有限公司 | A kind of context aware systems for automatic driving vehicle |
CN109375635A (en) * | 2018-12-20 | 2019-02-22 | 安徽江淮汽车集团股份有限公司 | A kind of autonomous driving vehicle road environment sensory perceptual system and method |
CN109678055A (en) * | 2018-11-07 | 2019-04-26 | 上海图森未来人工智能科技有限公司 | Mobile hanging device control system and method, server, mobile hanging device |
CN209852236U (en) * | 2019-03-07 | 2019-12-27 | 北京主线科技有限公司 | Environment sensing device for unmanned truck |
CN110879595A (en) * | 2019-11-29 | 2020-03-13 | 江苏徐工工程机械研究院有限公司 | Unmanned mine card tracking control system and method based on deep reinforcement learning |
-
2020
- 2020-03-24 CN CN202010211530.6A patent/CN111427348A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106909152A (en) * | 2017-03-17 | 2017-06-30 | 奇瑞汽车股份有限公司 | A kind of automobile-used context aware systems and automobile |
CN208149310U (en) * | 2018-05-11 | 2018-11-27 | 北京智行者科技有限公司 | A kind of context aware systems for automatic driving vehicle |
CN109678055A (en) * | 2018-11-07 | 2019-04-26 | 上海图森未来人工智能科技有限公司 | Mobile hanging device control system and method, server, mobile hanging device |
CN109375635A (en) * | 2018-12-20 | 2019-02-22 | 安徽江淮汽车集团股份有限公司 | A kind of autonomous driving vehicle road environment sensory perceptual system and method |
CN209852236U (en) * | 2019-03-07 | 2019-12-27 | 北京主线科技有限公司 | Environment sensing device for unmanned truck |
CN110879595A (en) * | 2019-11-29 | 2020-03-13 | 江苏徐工工程机械研究院有限公司 | Unmanned mine card tracking control system and method based on deep reinforcement learning |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111824053A (en) * | 2020-07-24 | 2020-10-27 | 江苏徐工工程机械研究院有限公司 | Mining truck |
CN112147632A (en) * | 2020-09-23 | 2020-12-29 | 中国第一汽车股份有限公司 | Method, device, equipment and medium for testing vehicle-mounted laser radar perception algorithm |
CN112614171A (en) * | 2020-11-26 | 2021-04-06 | 厦门大学 | Air-ground integrated dynamic environment sensing system for cluster operation of engineering machinery |
CN112614171B (en) * | 2020-11-26 | 2023-12-19 | 厦门大学 | Air-ground integrated dynamic environment sensing system for engineering machinery cluster operation |
CN112596050B (en) * | 2020-12-09 | 2024-04-12 | 上海商汤临港智能科技有限公司 | Vehicle, vehicle-mounted sensor system and driving data acquisition method |
CN112596050A (en) * | 2020-12-09 | 2021-04-02 | 上海商汤临港智能科技有限公司 | Vehicle, vehicle-mounted sensor system and driving data acquisition method |
CN112644517A (en) * | 2020-12-29 | 2021-04-13 | 北京宸控科技有限公司 | Automatic driving algorithm for underground vehicle |
CN112644517B (en) * | 2020-12-29 | 2022-01-25 | 北京宸控科技有限公司 | Automatic driving algorithm for underground vehicle |
CN112396043A (en) * | 2021-01-21 | 2021-02-23 | 北京主线科技有限公司 | Vehicle environment information perception method and device, electronic equipment and storage medium |
CN113009434A (en) * | 2021-02-20 | 2021-06-22 | 纳瓦电子(上海)有限公司 | Millimeter wave radar failure auxiliary device and method thereof |
CN113160589A (en) * | 2021-03-04 | 2021-07-23 | 腾讯科技(深圳)有限公司 | Vehicle early warning method and device, electronic equipment and computer readable storage medium |
WO2022183871A1 (en) * | 2021-03-04 | 2022-09-09 | 上海申传电气股份有限公司 | Construction method for dynamic envelope line for electric locomotive for mine railway |
CN113093746A (en) * | 2021-03-31 | 2021-07-09 | 上海三一重机股份有限公司 | Working machine environment sensing method, device and system and working machine |
CN113093746B (en) * | 2021-03-31 | 2024-01-23 | 上海三一重机股份有限公司 | Working machine environment sensing method, device and system and working machine |
CN113022408A (en) * | 2021-04-15 | 2021-06-25 | 中国矿业大学 | 360-degree self-adaptive loading and unloading unmanned mining dump truck and control method thereof |
CN113281783A (en) * | 2021-05-13 | 2021-08-20 | 江苏徐工工程机械研究院有限公司 | Mining truck |
CN113484872A (en) * | 2021-06-16 | 2021-10-08 | 国能榆林能源有限责任公司 | Laser radar underground slope depth detection method and detection vehicle |
CN113484872B (en) * | 2021-06-16 | 2024-01-09 | 国能榆林能源有限责任公司 | Laser radar underground slope depth detection method and detection vehicle |
CN113135181B (en) * | 2021-06-22 | 2021-08-24 | 北京踏歌智行科技有限公司 | Mining area automatic driving loading and unloading point accurate parking method based on visual assistance |
CN113135181A (en) * | 2021-06-22 | 2021-07-20 | 北京踏歌智行科技有限公司 | Mining area automatic driving loading and unloading point accurate parking method based on visual assistance |
CN113820714A (en) * | 2021-09-07 | 2021-12-21 | 重庆驰知科技有限公司 | Dust fog weather road environment perception system based on multi-sensor fusion |
CN113820714B (en) * | 2021-09-07 | 2024-04-12 | 重庆驰知科技有限公司 | Dust fog weather road environment sensing system based on multi-sensor fusion |
CN114715024A (en) * | 2022-04-15 | 2022-07-08 | 东风柳州汽车有限公司 | Automobile acousto-optic reminding method, automobile acousto-optic reminding equipment, storage medium and automobile acousto-optic reminding device |
CN117111058A (en) * | 2023-10-24 | 2023-11-24 | 青岛慧拓智能机器有限公司 | Unmanned perception system and method for mining truck |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111427348A (en) | Automatic drive mining dump truck environmental perception system and mining dump truck | |
CN113002396B (en) | A environmental perception system and mining vehicle for automatic driving mining vehicle | |
EP3867118B1 (en) | Lidar-based trailer tracking | |
CN108490941B (en) | Automatic driving system applied to road sweeper and control method and device thereof | |
US11772719B2 (en) | Efficient autonomous trucks | |
CN111537994B (en) | Unmanned mine card obstacle detection method | |
US20220032955A1 (en) | Vehicle control device and vehicle control method | |
US20220169254A1 (en) | Systems and techniques for field-of-view improvements in autonomous trucking systems | |
CN112009524B (en) | System and method for tramcar obstacle detection | |
CN104149782A (en) | Automatic driving system of magnetic-navigation based multi-sensor fusion intelligent vehicle | |
CN106114357A (en) | Device and method for preventing scratching during turning of vehicle | |
CN114442101B (en) | Vehicle navigation method, device, equipment and medium based on imaging millimeter wave radar | |
CN110596731A (en) | Active obstacle detection system and method for metro vehicle | |
CN210502571U (en) | Vehicle environment perception system | |
CN111026118A (en) | Mining wide-body vehicle and automatic driving system thereof | |
CN211943272U (en) | Automatic driving controller, automatic driving system of vehicle and vehicle | |
CN219056229U (en) | Perception system of unmanned ore deposit card and unmanned ore deposit card | |
CN114120275A (en) | Automatic driving obstacle detection and recognition method and device, electronic equipment and storage medium | |
CN215678774U (en) | Mining truck and sensing system thereof | |
CN220855184U (en) | Ore card and environment sensing system thereof | |
CN215669752U (en) | Unmanned excavator sensing system and excavator | |
CN219277433U (en) | Mining trackless rubber-tyred vehicle and automatic driving system thereof | |
CN215264496U (en) | Automatic driving passenger car | |
CN211844341U (en) | Automatic driving passenger car | |
CN214450670U (en) | Electric automobile environment perception system |
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: 20200717 |