CN112965494B - Control system and method for pure electric automatic driving special vehicle in fixed area - Google Patents
Control system and method for pure electric automatic driving special vehicle in fixed area Download PDFInfo
- Publication number
- CN112965494B CN112965494B CN202110183388.3A CN202110183388A CN112965494B CN 112965494 B CN112965494 B CN 112965494B CN 202110183388 A CN202110183388 A CN 202110183388A CN 112965494 B CN112965494 B CN 112965494B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- control
- module
- information
- track
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000007246 mechanism Effects 0.000 claims abstract description 30
- 238000013439 planning Methods 0.000 claims abstract description 7
- 230000033001 locomotion Effects 0.000 claims description 13
- 230000001133 acceleration Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 230000007774 longterm Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 abstract description 4
- 238000012384 transportation and delivery Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0285—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using signals transmitted via a public communication network, e.g. GSM network
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optics & Photonics (AREA)
- Electromagnetism (AREA)
- Acoustics & Sound (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a control system and a method for a special pure electric automatic driving vehicle in a fixed area, comprising an upper computer system, a lower computer system and a hardware platform, wherein the upper computer system comprises an industrial personal computer for running ROS, a laser radar, a GPS module, a voice module and an App module, the lower computer system comprises a control panel group, a dead reckoning module, an ultrasonic distance sensor, a motor and a driver thereof, and the hardware platform part comprises a frame, a carriage, a rear drive mechanism, a steering mechanism, a braking mechanism and a power supply module. The invention completes the functions of path planning, positioning information uploading and pedestrian voice reminding through the industrial personal computer in the upper computer system, and the lower computer system controls the special vehicle path tracking, remote control and emergency braking. The invention can control the special vehicle to automatically and safely transport the articles to the appointed position in the fixed area, improves the working efficiency, saves the labor cost, and provides a feasible implementation scheme for the application of the intelligent vehicle, thereby playing an important role in accelerating the development of the intelligent technology.
Description
Technical Field
The invention belongs to the technical field of intelligent vehicles, and particularly relates to a control system and method for a pure electric automatic driving special vehicle in a fixed area.
Background
With the continuous development of computer technology, people come into the intelligent era. From mobile phones, computers and sweeping robots to unmanned automobiles which are rapidly developed at present, intelligent technology walks into thousands of households. The intelligent vehicle is a brand new automobile concept and product which relates to various subjects such as environment perception, artificial intelligence, automatic control, vehicle engineering and the like. The development of intelligent vehicles attracts high importance to various departments, enterprises and schools at home and abroad, and certain research results are achieved. The intelligent vehicle is considered to be capable of greatly solving the traffic safety and traffic jam problems, and has wide application prospect. Urban environments are used as important application fields of intelligent vehicles, and are important and difficult to study intelligent vehicle technologies due to the complex road environments. The fixed area is a staged research object before the intelligent vehicle is completely applied to the urban environment.
With the economic development and strategic adjustment of economic structures in China, the status and effect of modern catering industry and logistics industry in national economy in China are increasing. And simultaneously, with the rise of the Internet, online meal ordering and online shopping are generated. Each large network platform provides great convenience for consumers. However, the social takeaway and online shopping articles are delivered by the delivery staff, so that the delivery of more goods takes place, the delivery time is different, the delivery efficiency is weakened, and the labor cost is increased. External delivery personnel enter fixed areas such as factories, corporate communities, residential communities or campuses, and the like, so that certain threats are brought to personnel and property safety, and the risk of comprehensive traffic control in the fixed areas is increased due to non-motor vehicles of the delivery personnel, and effective management is difficult.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a control system and a method for a special vehicle for pure electric automatic driving in a fixed area, which are based on ROS development, complete the functions of path planning, fixed-point parking, uploading of positioning information and voice reminding of pedestrians through an industrial control computer in an upper computer system, and control the movement and emergency obstacle avoidance of the special vehicle through a lower computer system; the control system of the special vehicle for the pure electric automatic driving in the fixed area can control the special vehicle to automatically and safely convey articles to a designated position in the fixed area.
In order to achieve the purpose, the control system for the pure electric automatic driving special vehicle in the fixed area is designed and is characterized by comprising an upper computer system, a lower computer system and a hardware platform;
The upper computer system comprises: the system comprises a laser radar for acquiring distance information to form a point cloud data set, a GPS module for acquiring longitude and latitude information of a special vehicle, an APP module for transmitting vehicle position information and an industrial personal computer, wherein the industrial personal computer is used for calculating dynamic obstacle information and positioning information and planning a running path of the special vehicle;
the lower computer system comprises: the device comprises a control panel group, a dead reckoning module, an ultrasonic distance sensor, a motor and a driving module; wherein,
The dead reckoning module is used for calculating current speed and attitude information of the special vehicle;
The ultrasonic distance sensor is used for collecting surrounding obstacle distance information of the special vehicle and sending out a sound wave stopping instruction;
The control panel group consists of a control panel A and a control panel B, wherein the control panel A is communicated with the upper computer through a serial port, is connected with the control panel B through a CAN bus and is connected with the dead reckoning module through a USB; the control board B is connected with the driving motor controller and the steering motor controller through a CAN bus and is connected with the ultrasonic distance sensor through a serial port; the control board A receives the special vehicle driving path and positioning information transmitted by the upper computer and calculates to obtain expected special vehicle speed and angle control signals; the control board A calculates actual vehicle speed and angle information through the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module, and calculates control instructions of all motors through a PID controller; the control board B is used for analyzing the control information and communicating with the motor and the driving module;
the hardware platform comprises: the vehicle comprises a vehicle frame, a carriage, a rear drive mechanism, a steering mechanism, a braking mechanism and a power supply module, wherein the rear drive mechanism, the steering mechanism and the braking mechanism respectively execute motor control instructions sent by a motor and a driving module.
Further, the industrial personal computer is provided with the ROS system and is internally provided with the 5G communication module, a three-dimensional point cloud map is built by the industrial personal computer based on point cloud data uploaded by the laser radar in the first operation process, the parking fixed point position is marked, then the current environment is matched with the three-dimensional point cloud map to realize positioning, and the industrial personal computer is used for clustering and identifying dynamic obstacle information and predicting obstacle tracks.
Furthermore, the industrial personal computer obstacle track prediction adopts a comprehensive predicted track obtained by track prediction of an LSTM network and short-term behavior track prediction based on extended Kalman filtering.
Furthermore, the upper computer system further comprises a voice module communicated with the industrial personal computer through a USB, and the voice module is used for receiving and analyzing the voice command of the industrial personal computer and sending out a safety prompt.
Furthermore, the lower computer system also comprises a remote control module which is communicated with the control panel B through RS232, and an operator sends motor control instructions of front, back, left and right to the control panel B through the remote control module so as to control the movement of the special vehicle.
Further, the control priority of the remote control module is higher than that of the sound wave stopping command, and the control priority of the sound wave stopping command is higher than that of the control panel A.
Furthermore, the track reckoning module comprises an encoder and an inertia measuring unit, and linear speed and angular speed information output by the three-axis gyroscope, the three-axis accelerometer and the three-axis geomagnetic are calculated through a track reckoning algorithm to obtain odometer information and current speed and attitude information of the special vehicle.
Still further, ultrasonic wave distance sensor arranges around the special-purpose vehicle, and when the special-purpose vehicle is in the in-process of motion, ultrasonic wave sensor detects that barrier distance special-purpose vehicle is less than the safe distance of settlement, sends sound wave stop instruction control special-purpose vehicle stop motion.
Based on the control system of the pure electric automatic driving special vehicle in the fixed area, the invention also provides a control method, which comprises the following steps:
1) The industrial personal computer builds a three-dimensional point cloud map based on the point cloud data uploaded by the laser radar, and marks the parking fixed-point position;
2) The industrial personal computer judges whether a remote controller instruction intervenes, if so, the remote controller instruction is analyzed and goes to step 8), otherwise, goes to step 3);
3) The industrial personal computer is matched with the point cloud data to realize real-time positioning and dynamic obstacle detection, and a special vehicle driving path is planned according to the position information of the dead reckoning module uploaded by the lower computer;
4) The industrial personal computer collects GPS longitude and latitude information of the GPS module, judges whether the APP module sends a mobile phone APP inquiry position instruction, and if so, transmits special vehicle position information to the APP module;
5) The control panel group plans a path according to the point cloud data and the real-time positioning information output by the industrial personal computer, and calculates the real-time pose and speed of the expected vehicle;
6) The control board A of the control board group calculates the actual vehicle speed and angle information through the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module;
7) The PID controller of the control panel group calculates the control instruction of each motor according to the actual vehicle speed and angle information and the real-time pose and speed of the expected vehicle; when the ultrasonic sensor detects that an obstacle exists in a preset range, an emergency braking control instruction is sent out;
8) The rear drive mechanism, the steering mechanism and the braking mechanism of the hardware platform respectively execute motor control instructions;
9) And (3) the industrial personal computer judges whether the special vehicle reaches a specified parking point, otherwise, the step (2) is carried out, and if so, the control flow is finished.
Preferably, in the step 3), the obstacle track prediction in the dynamic obstacle detection adopts the track prediction of the LSTM network and the short-term behavior track prediction based on the extended kalman filter to obtain a comprehensive predicted track, and the calculation method of the comprehensive predicted track T fusion is as follows:
Tfusion＝W(t)TL+(I-W(t)TS
Wherein T L is a long-term predicted trajectory, T S is a short-term predicted trajectory, and W (T) is a weight ratio.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1. the invention belongs to the technical field of intelligent vehicle application, and has the functions of autonomous navigation, active obstacle avoidance, fixed-point parking, voice prompt, cargo transportation and mobile phone app display positioning information in a fixed area.
2. The invention adopts a modularized design, all components can be detached and replaced, an expansion space is provided for the subsequent updating and upgrading of the platform, and the invention can be modified by combining with specific scenes to form external equipment, such as campus meal delivery trucks, factory logistics trucks, mining area transportation trucks and the like, and has quite great flexibility.
3. Aiming at fixed areas such as factories, corporate communities, residential communities or campuses, the invention adopts comprehensive driving strategies of low-speed operation, laser radar obstacle avoidance, emergency stop of an ultrasonic module and voice reminding, and greatly improves the driving safety of the special vehicle.
4. The invention is provided with the remote control module, and under the common condition, the special vehicle for pure electric automatic driving in the fixed area can be driven in a remote control mode, and if an emergency condition occurs in an autonomous navigation state, an operator can be involved in the current state of the special vehicle at any time to operate, so that the safety is ensured.
5. The mobile phone APP interaction system has the mobile phone APP interaction function, and operators can use the mobile phone APP to inquire the position of the special vehicle at any time and monitor the running condition of the special vehicle in real time.
6. The platform provided by the invention can independently run in a fixed route to transport goods, so that not only can the labor cost be saved and the working efficiency be improved, but also traffic management and personnel and property safety in a fixed area are facilitated, and a practical and feasible implementation scheme is provided for the application of intelligent vehicles, so that an important role is played in accelerating the development of intelligent technology.
Drawings
Fig. 1 is a schematic diagram of a hardware structure of a control system of a special vehicle according to an embodiment of the present invention.
Fig. 2 is a flowchart of a control method of a control system for a special vehicle according to an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and specific examples.
As shown in FIG. 1, the control system for the special pure electric automatic driving vehicle in the fixed area provided by the invention comprises an upper computer system, a lower computer system and a hardware platform.
The upper computer system comprises a laser radar, a GPS module, an industrial personal computer, a voice module and an APP module. The laser radar can acquire distance information to form a point cloud data set, and the point cloud data set is uploaded to the industrial personal computer. The GPS module can collect longitude and latitude information of the special vehicle in real time and upload the information to the industrial personal computer.
The industrial personal computer is used for calculating dynamic obstacle information and positioning information and planning a special vehicle driving path. The industrial personal computer is provided with an ROS system and a built-in 5G communication module, a three-dimensional point cloud map is built by the industrial personal computer based on point cloud data uploaded by a laser radar in the first operation process, the parking fixed point position is marked, the current environment is matched with the three-dimensional point cloud map to realize positioning, dynamic obstacle information is used for clustering identification, and if the pedestrian is a pedestrian, a pedestrian voice reminding instruction is transmitted to the voice module; receiving longitude and latitude position information of a GPS; receiving the position information of the dead reckoning module uploaded by the lower computer; simultaneously, the industrial personal computer plans a special vehicle driving path; vehicle location information may also be communicated with the APP module via a 5G network. The industrial personal computer obstacle track prediction adopts an LSTM network track prediction and an extended Kalman filtering-based short-term behavior track prediction to obtain a comprehensive prediction track.
The dynamic obstacle recognition and track prediction method is characterized in that the comprehensive prediction track is obtained by combining the track prediction of an LSTM network with better processing capacity on the time sequence problem and the short-term behavior track prediction based on the extended Kalman filtering. Based on the track prediction of the LSTM network, historical track information in the running process of the vehicle is excavated, a running prediction model is constructed by taking the longitudinal coordinate x (t) of the vehicle, the transverse coordinate y (t) of the vehicle, the vehicle speed v (t), the longitudinal acceleration alpha x (t), the transverse acceleration alpha y (t) and the yaw rate omega (t) as running characteristics of the vehicle, and a mapping relation between the historical vehicle track and future vehicle track characteristic data is established. Establishing a t-moment track characteristic expression s (t):
s(t)＝{x(t),y(t),v(t),ay(t),ax(t),ω(t)}
The vehicle running track at k continuous moments (k steps) is taken as a network input characteristic, and the model output is a vehicle longitudinal coordinate x (t+1) and a vehicle transverse coordinate y (t+1) at the moment t+1. Establishing a vehicle track prediction model:
TL＝f({s(t-k-1),…,s(t-1),s(t)})
500 sequences are selected as the whole data set, 80% of the sequences are used as training sets, 20% of the sequences are used as test sets, the initial input characteristic step length k= {5,10,20,30}, the input layer node is set to 10, the output layer node is set to 3, the hidden layer size is set to 200, the batch size is set to 32, the training round is set to 10, and the initial learning rate is set to 0.001.
In short-term prediction, a state transition equation and an observation equation are established as follows:
Wherein, Z (k) = [ x, y, v, theta, a, omega ] respectively represents the transverse coordinates of the vehicle, the longitudinal coordinates of the vehicle, the vehicle speed of the vehicle, the course angle, the acceleration of the whole vehicle and the yaw rate; w (k) is system noise, V (k) is observation noise, and W (k) and V (k) are uncorrelated Gaussian random vectors with average value of 0.
Solving a jacobian matrix:
Predicting and updating parameters:
The speed of the vehicle can be calculated by combining the vehicle kinematic model:
The speed is calculated to obtain track information T S:
Where x 0,y0 is the vehicle initial position, v 0 is the initial vehicle speed, θ 0 is the initial heading angle, a 0 is the initial acceleration, and ω 0 is the initial yaw rate. The comprehensive predicted track T fusion can be obtained through fusion processing, wherein T L is a long-term predicted track, T S is a short-term predicted track, and W (T) is a weight proportion.
Tfusion＝W(t)TL+(I-W(t))TS
The voice module is communicated with the industrial personal computer through the USB by adopting the voice module for receiving the instruction of the industrial personal computer and analyzing and sending out voice prompt. When the laser radar scans that the dynamic obstacle is within the range of 1 meter to 3 meters, the industrial control computer sends out instructions to the voice module, the voice module receives and analyzes the instructions, then the voice module sends out safety prompt voice, and when the dynamic obstacle is within the range of 1 meter to 0.4 meter, the voice module sends out safety warning voice.
The APP module can be communicated with the industrial personal computer through a 5G network, and a user can inquire the position information of the special vehicle through the mobile phone APP.
The lower computer system comprises: the device comprises a control panel group, a dead reckoning module, an ultrasonic distance sensor, a remote control module, a motor and a driving module; wherein,
The dead reckoning module is used for calculating the current speed and attitude information of the special vehicle; the dead reckoning module comprises an encoder and an inertia measuring unit, and calculates linear velocity and angular velocity information output by the three-axis gyroscope, the three-axis accelerometer and the three-axis geomagnetism through a dead reckoning algorithm to obtain odometer information and current velocity and attitude information of the special vehicle.
The ultrasonic distance sensor is used for collecting surrounding obstacle distance information of the special vehicle and sending out a sound wave stopping instruction. The ultrasonic distance sensor is arranged around the special vehicle, and when the ultrasonic sensor detects that the obstacle distance is smaller than the set safety distance, the ultrasonic distance sensor sends out an acoustic stop instruction to control the special vehicle to stop moving.
The control panel group consists of a control panel A and a control panel B, wherein the control panel A selects 32-bit microcontrollers of ARM Cortex-M cores, and the control panel B selects MC9S12 series 16-bit microcontrollers. The control board A is communicated with the upper computer through a serial port, is connected with the control board B through a CAN bus and is connected with the dead reckoning module through a USB; the control board B is connected with the driving motor controller and the steering motor controller through a CAN bus and is connected with the ultrasonic distance sensor through a serial port; the control board A receives the special vehicle driving path and positioning information transmitted by the upper computer and calculates to obtain expected special vehicle speed and angle control signals; the control board A calculates actual vehicle speed and angle information through the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module, and calculates control instructions of all motors through a PID controller; the control board B is used for analyzing the control information and communicating with the motor and the driving module.
The remote control module is communicated with the control panel B through RS232, and an operator sends motor control instructions of front, back, left and right to the control panel B through the remote control module, so that the movement of the special vehicle is controlled. The control priority of the remote control module is higher than that of the sound wave stopping instruction, and the control priority of the sound wave stopping instruction is higher than that of the control panel A.
The hardware platform comprises: the vehicle comprises a vehicle frame, a carriage, a rear drive mechanism, a steering mechanism, a braking mechanism and a power supply module, wherein the rear drive mechanism, the steering mechanism and the braking mechanism respectively execute motor control instructions sent by a motor and a driving module. The frame and carriage frame structure is reasonably designed after the positions and the spaces of all the moving parts are considered, and modeling is carried out by using CATIA drawing software according to the size parameters of the whole vehicle, so that the moving parts of all the mechanical structures and the sensors cannot generate motion interference or signal interference. The power supply module consists of a 60V50AH lithium battery, a plurality of DC/DC voltage reduction modules and a battery management system. The braking motor and the steering motor are servo motors, the driving motor is a direct current traction motor, the overload coefficient is 3-4, and the requirements of vehicle starting, climbing and speed regulation can be met.
Based on the system, the invention also provides a control method of the special pure electric automatic driving vehicle in the fixed area, which comprises the following steps:
1) The industrial personal computer builds a three-dimensional point cloud map based on the point cloud data uploaded by the laser radar, and marks the parking fixed-point position;
2) The industrial personal computer judges whether a remote controller instruction intervenes, if so, the remote controller instruction is analyzed and goes to step 8), otherwise, goes to step 3);
3) The industrial personal computer is matched with the point cloud data to realize real-time positioning and dynamic obstacle detection, and a special vehicle driving path is planned according to the position information of the dead reckoning module uploaded by the lower computer; the obstacle track prediction in dynamic obstacle detection adopts the track prediction of an LSTM network and the short-term behavior track prediction based on the extended Kalman filtering to obtain a comprehensive predicted track, and the calculation method of the comprehensive predicted track T fusion comprises the following steps:
Tfusion＝W(t)TL+(I-W(t)TS
Wherein T L is a long-term predicted trajectory, T S is a short-term predicted trajectory, and W (T) is a weight ratio.
4) The industrial personal computer collects GPS longitude and latitude information of the GPS module, judges whether the APP module sends a mobile phone APP inquiry position instruction, and if so, transmits special vehicle position information to the APP module;
5) The control panel group plans a path according to the point cloud data and the real-time positioning information output by the industrial personal computer, and calculates the real-time pose and speed of the expected vehicle;
6) The control board A of the control board group calculates the actual vehicle speed and angle information through the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module;
7) The PID controller of the control panel group calculates the control instruction of each motor according to the actual vehicle speed and angle information and the real-time pose and speed of the expected vehicle; when the ultrasonic sensor detects that an obstacle exists in a preset range, an emergency braking control instruction is sent out;
8) The rear drive mechanism, the steering mechanism and the braking mechanism of the hardware platform respectively execute motor control instructions;
9) And (3) the industrial personal computer judges whether the special vehicle reaches a specified parking point, otherwise, the step (2) is carried out, and if so, the control flow is finished.
When the implementation example is implemented, firstly, different voltage levels are provided through a power supply module, normal operation of electric equipment of the whole vehicle is guaranteed, secondly, an upper computer system and a lower computer system are started, surrounding environment is detected through a laser radar, and the obtained point cloud data of the distance is uploaded to an industrial personal computer running an ROS system; when the system runs for the first time, the industrial personal computer firstly builds a three-dimensional point cloud map of the whole fixed area environment, marks a parking fixed point, and if the fixed point is changed, the map should be recorded again; when the method runs for the first time, the industrial personal computer utilizes the laser radar point cloud data returned in real time to match the established three-dimensional point cloud map with the relative position information and combines the absolute positioning information of the GPS, so that the high-precision positioning information is obtained; then planning a motion track according to the parking fixed point, the high-precision positioning information and the map and sending the motion track to a lower computer system; the control board A in the lower computer system is connected with the industrial personal computer through a serial port, receives the path planned by the upper computer and the positioning information and calculates to obtain the expected speed and angle control signal of the special vehicle; the control board A calculates actual vehicle speed and angle information through Kalman filtering according to the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module, calculates control instructions of all motors through a PID controller by combining an expected value and an actual value, packages the control instructions into a CAN bus protocol, sends the CAN bus protocol to the control board B, receives the speed information and the rotation angle information through the CAN bus, and controls the movement of the control board B through the CAN bus, the driving motor, the braking motor and the steering motor after the control board B receives the speed information and the rotation angle information through the CAN bus and the control board B receives the control instructions after the control board B receives the operation priority arrangement;
In this example, if dynamic obstacles such as pedestrians, vehicles and the like appear in the operation of the fixed route, the special vehicle will adopt a comprehensive obstacle avoidance strategy to effectively avoid the obstacle. When the laser radar scans that the dynamic obstacle is within the range of 1 meter to 3 meters, the industrial control machine sends an instruction to the voice module, the voice module receives the instruction and analyzes the instruction, then the voice module sends a safety prompt voice, when the dynamic obstacle is within the range of 1 meter to 0.4 meter, the voice module sends a safety warning voice, when the dynamic obstacle is within the range of 0.4 meter, the voice module sends a safety warning voice, the ultrasonic distance sensor is triggered at the same time, and the control panel B shields the instruction of the control panel A and performs emergency braking; when the obstacle is far away from the special vehicle, if the distance is greater than 0.4 meter, the control panel B cancels the emergency braking instruction and receives the control panel A instruction again.
When the method is implemented, the industrial personal computer uploads the positioning information of the special vehicle to the mobile phone app of the user through the 5G network. No matter the special pure electric automatic driving vehicle in the fixed area is in an autonomous navigation state or a common state, an operator can intervene in the original state through the remote control module and send front, back, left and right instructions to the control panel B, so that the special vehicle is controlled to move.
It will be readily appreciated by those skilled in the art that the foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. The control system for the pure electric automatic driving special vehicle in the fixed area is characterized by comprising an upper computer system, a lower computer system and a hardware platform;
The upper computer system comprises: the system comprises a laser radar for acquiring distance information to form a point cloud data set, a GPS module for acquiring longitude and latitude information of a special vehicle, an APP module for transmitting vehicle position information and an industrial personal computer, wherein the industrial personal computer is used for calculating dynamic obstacle information and positioning information and planning a running path of the special vehicle; the industrial personal computer is provided with an ROS system and a built-in 5G communication module, a three-dimensional point cloud map is built based on point cloud data uploaded by a laser radar in the first operation process, a parking fixed point position is marked, then the current environment is matched with the three-dimensional point cloud map to realize positioning, and the industrial personal computer is used for clustering and identifying dynamic obstacle information and predicting obstacle tracks;
the lower computer system comprises: the device comprises a control panel group, a dead reckoning module, an ultrasonic distance sensor, a motor and a driving module; wherein,
The dead reckoning module is used for calculating current speed and attitude information of the special vehicle;
The ultrasonic distance sensor is used for collecting surrounding obstacle distance information of the special vehicle and sending out a sound wave stopping instruction;
The control panel group consists of a control panel A and a control panel B, wherein the control panel A is communicated with the upper computer through a serial port, is connected with the control panel B through a CAN bus and is connected with the dead reckoning module through a USB; the control board B is connected with the driving motor controller and the steering motor controller through a CAN bus and is connected with the ultrasonic distance sensor through a serial port; the control board A receives the special vehicle driving path and positioning information transmitted by the upper computer and calculates to obtain expected special vehicle speed and angle control signals; the control board A calculates actual vehicle speed and angle information through the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module, and calculates control instructions of all motors through a PID controller; the control board B is used for analyzing the control information and communicating with the motor and the driving module, receives the speed information and the corner information through the CAN bus, and communicates with the driving motor, the braking motor and the steering motor through the CAN bus after the operation priority is arranged, so as to control the movement of the motor and the steering motor;
The hardware platform comprises: the vehicle comprises a vehicle frame, a carriage, a rear drive mechanism, a steering mechanism, a braking mechanism and a power supply module, wherein the rear drive mechanism, the steering mechanism and the braking mechanism respectively execute motor control instructions sent by a motor and a driving module;
the upper computer system and the lower computer system are started, the surrounding environment is detected through a laser radar, and the obtained point cloud data of the distance is uploaded to an industrial personal computer running the ROS system; the industrial personal computer utilizes the laser radar point cloud data returned in real time to match the established three-dimensional point cloud map with the relative position information and combines the absolute positioning information of the GPS, so that high-precision positioning information is obtained; then planning a motion track according to the parking fixed point, the high-precision positioning information and the map and sending the motion track to a lower computer system; the industrial personal computer obstacle track prediction adopts an LSTM network track prediction and an extended Kalman filtering-based short-term behavior track prediction to obtain a comprehensive prediction track;
The method comprises the steps of constructing a running prediction model by taking a longitudinal coordinate x (t) of a vehicle, a transverse coordinate y (t) of the vehicle, a vehicle speed v (t) of a vehicle, a longitudinal acceleration alpha x (t), a transverse acceleration alpha y (t) and a yaw rate omega (t) as running characteristics of the vehicle, establishing a mapping relation between a historical vehicle track and future vehicle track characteristic data, and establishing a track characteristic expression s (t) at the moment of t:
s(t)＝{x(t)，y(t)，v(t)，ay(t),ax(t)，ω(t)}
Taking the vehicle running tracks at k continuous moments as network input features, outputting a model as a vehicle longitudinal coordinate x (t+1) and a vehicle transverse coordinate y (t+1) at the moment t+1, and establishing a vehicle track prediction model:
TL＝f({s(t-k-1)，...，s(t-1)，s(t)})
calculating the speed of the vehicle:
The speed is calculated to obtain track information T S:
Where x 0,y0 is the initial position of the vehicle, v 0 is the initial vehicle speed, θ 0 is the initial heading angle, a 0 is the initial acceleration, and ω 0 is the initial yaw rate;
The comprehensive predicted track T fusion is obtained through fusion processing, wherein T L is a long-term predicted track, T S is a short-term predicted track, and W (T) is a weight ratio:
Tfusion＝W(t)TL+(1-W(t))TS。
2. The fixed-area all-electric automatic driving special vehicle control system according to claim 1, characterized in that: the upper computer system also comprises a voice module communicated with the industrial personal computer through a USB, and the voice module is used for receiving and analyzing the voice instruction of the industrial personal computer and sending a safety prompt.
3. The fixed-area all-electric automatic driving special vehicle control system according to claim 1, characterized in that: the lower computer system also comprises a remote control module which is communicated with the control panel B through RS232, and an operator sends motor control instructions of front, back, left and right to the control panel B through the remote control module so as to control the movement of the special vehicle.
4. The fixed-area all-electric-automatic special-purpose vehicle control system according to claim 3, characterized in that: the control priority of the remote control module is higher than that of the sound wave stopping instruction, and the control priority of the sound wave stopping instruction is higher than that of the control panel A.
5. The fixed-area all-electric automatic driving special vehicle control system according to claim 1, characterized in that: the track calculation module comprises an encoder and an inertia measurement unit, and linear speed and angular speed information output by the three-axis gyroscope, the three-axis accelerometer and the three-axis geomagnetism are calculated through a track calculation algorithm to obtain odometer information and current speed and attitude information of the special vehicle.
6. The fixed-area all-electric automatic driving special vehicle control system according to claim 1, characterized in that: the ultrasonic distance sensor is arranged around the special vehicle, and when the ultrasonic sensor detects that the obstacle distance is smaller than the set safety distance, the ultrasonic distance sensor sends out an acoustic stop instruction to control the special vehicle to stop moving.
7. A method of a fixed area all-electric-automatic special-purpose vehicle control system according to any one of claims 1 to 6, characterized by: the method comprises the following steps:
1) The industrial personal computer builds a three-dimensional point cloud map based on the point cloud data uploaded by the laser radar, and marks the parking fixed-point position;
2) The industrial personal computer judges whether a remote controller instruction intervenes, if so, the remote controller instruction is analyzed and goes to step 8), otherwise, goes to step 3);
3) The industrial personal computer is matched with the point cloud data to realize real-time positioning and dynamic obstacle detection, and a special vehicle driving path is planned according to the position information of the dead reckoning module uploaded by the lower computer;
4) The industrial personal computer collects GPS longitude and latitude information of the GPS module, judges whether the APP module sends a mobile phone APP inquiry position instruction, and if so, transmits special vehicle position information to the APP module;
5) The control panel group plans a path according to the point cloud data and the real-time positioning information output by the industrial personal computer, and calculates the real-time pose and speed of the expected vehicle;
6) The control board A of the control board group calculates the actual vehicle speed and angle information through the motor rotation speed and rotation angle information uploaded by the control board B and the vehicle speed and attitude information of the dead reckoning module;
7) The PID controller of the control panel group calculates the control instruction of each motor according to the actual vehicle speed and angle information and the real-time pose and speed of the expected vehicle; when the ultrasonic sensor detects that an obstacle exists in a preset range, an emergency braking control instruction is sent out;
8) The rear drive mechanism, the steering mechanism and the braking mechanism of the hardware platform respectively execute motor control instructions;
9) And (3) the industrial personal computer judges whether the special vehicle reaches a specified parking point, otherwise, the step (2) is carried out, and if so, the control flow is finished.
8. The method of a fixed area electric only vehicle control system of claim 7, wherein: the step 3) of obstacle track prediction in dynamic obstacle detection adopts track prediction of an LSTM network and short-term behavior track prediction based on extended Kalman filtering to obtain a comprehensive predicted track, and the calculation method of the comprehensive predicted track T fusion is as follows:
Tfusion＝W(t)TL+(I-W(t))TS
Wherein T L is a long-term predicted trajectory, T S is a short-term predicted trajectory, and W (T) is a weight ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110183388.3A CN112965494B (en) | 2021-02-09 | 2021-02-09 | Control system and method for pure electric automatic driving special vehicle in fixed area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110183388.3A CN112965494B (en) | 2021-02-09 | 2021-02-09 | Control system and method for pure electric automatic driving special vehicle in fixed area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112965494A CN112965494A (en) | 2021-06-15 |
| CN112965494B true CN112965494B (en) | 2024-06-14 |
Family
ID=76284802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110183388.3A Active CN112965494B (en) | 2021-02-09 | 2021-02-09 | Control system and method for pure electric automatic driving special vehicle in fixed area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112965494B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113909207A (en) * | 2021-09-01 | 2022-01-11 | 苏州鑫格雅电子科技有限公司 | Ultrasonic cleaning method and system for glass manufacturing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774291A (en) * | 2016-12-26 | 2017-05-31 | 清华大学苏州汽车研究院（吴江） | A kind of electric-control system of automatic Pilot electric automobile |
| CN110647089A (en) * | 2019-10-28 | 2020-01-03 | 天津中德应用技术大学 | Intelligent warehouse logistics robot control system and control method |
| CN111308490A (en) * | 2020-02-05 | 2020-06-19 | 浙江工业大学 | Balance car indoor positioning and navigation system based on single-line laser radar |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216406B (en) * | 2013-06-05 | 2017-07-14 | 中国石油天然气集团公司 | The control device and control method on a kind of four-wheel drive omnidirectional chassis |
| CN107422730A (en) * | 2017-06-09 | 2017-12-01 | 武汉市众向科技有限公司 | The AGV transportation systems of view-based access control model guiding and its driving control method |
| CN110083163A (en) * | 2019-05-20 | 2019-08-02 | 三亚学院 | A kind of 5G C-V2X bus or train route cloud cooperation perceptive method and system for autonomous driving vehicle |
| CN110208740A (en) * | 2019-07-09 | 2019-09-06 | 北京智芯微电子科技有限公司 | TDOA-IMU data adaptive merges positioning device and method |
| CN110341496B (en) * | 2019-07-09 | 2022-11-04 | 武汉理工大学 | Ramp low-speed working condition running control method for distributed driving cross-country vehicle |
| CN110631592B (en) * | 2019-10-28 | 2022-03-29 | 华南理工大学 | Indoor autonomous navigation AGV (automatic guided vehicle) motion track fusion method based on LSTM (least squares metric model) |
| CN110889350B (en) * | 2019-11-18 | 2023-05-23 | 四川西南交大铁路发展股份有限公司 | Line obstacle monitoring and alarming system and method based on three-dimensional imaging |
| CN111161325B (en) * | 2019-12-31 | 2023-05-23 | 广州视声智能科技有限公司 | Three-dimensional multi-target tracking method based on Kalman filtering and LSTM |
| CN111413932A (en) * | 2020-03-29 | 2020-07-14 | 河南工程学院 | Information management and scheduling system and method for unmanned electric cleaning vehicle |
| CN111422196A (en) * | 2020-04-16 | 2020-07-17 | 金龙联合汽车工业（苏州）有限公司 | Intelligent networking automatic driving system and method suitable for mini bus |
| CN112214019B (en) * | 2020-09-21 | 2023-05-23 | 国网浙江省电力有限公司 | Unmanned inspection equipment non-blind area intelligent feedback control system, method and terminal |
-
2021
- 2021-02-09 CN CN202110183388.3A patent/CN112965494B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106774291A (en) * | 2016-12-26 | 2017-05-31 | 清华大学苏州汽车研究院（吴江） | A kind of electric-control system of automatic Pilot electric automobile |
| CN110647089A (en) * | 2019-10-28 | 2020-01-03 | 天津中德应用技术大学 | Intelligent warehouse logistics robot control system and control method |
| CN111308490A (en) * | 2020-02-05 | 2020-06-19 | 浙江工业大学 | Balance car indoor positioning and navigation system based on single-line laser radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112965494A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | The role of the hercules autonomous vehicle during the covid-19 pandemic: An autonomous logistic vehicle for contactless goods transportation | |
| CN112518739B (en) | Track-mounted chassis robot reconnaissance intelligent autonomous navigation method | |
| Kolski et al. | Autonomous driving in structured and unstructured environments | |
| US11740624B2 (en) | Advanced control system with multiple control paradigms | |
| CN106054896A (en) | Intelligent navigation robot dolly system | |
| CN112068574A (en) | Control method and system for unmanned vehicle in dynamic complex environment | |
| Shimchik et al. | Golf cart prototype development and navigation simulation using ROS and Gazebo | |
| CN206833250U (en) | A kind of unmanned investigation dolly based on laser radar | |
| CN113071518B (en) | Automatic unmanned driving method, minibus, electronic equipment and storage medium | |
| CN112684791A (en) | Unmanned logistics vehicle based on 5G | |
| CN214846390U (en) | Dynamic environment obstacle avoidance system based on automatic guided vehicle | |
| US20230063845A1 (en) | Systems and methods for monocular based object detection | |
| CN108279681A (en) | A kind of two-wheel drive type low speed cruiser system and working method | |
| CN113954858A (en) | Method for planning vehicle driving route and intelligent automobile | |
| CN108469820A (en) | A kind of round-the-clock unmanned cruiser system of two-wheel drive low speed | |
| US20230415736A1 (en) | Systems and methods for controlling longitudinal acceleration based on lateral objects | |
| CN114792149A (en) | Track prediction method and device and map | |
| Gomez et al. | Ros-based architecture for autonomous intelligent campus automobile (icab) | |
| US20230415739A1 (en) | Systems and methods for controlling longitudinal acceleration based on lateral objects | |
| CN112965494B (en) | Control system and method for pure electric automatic driving special vehicle in fixed area | |
| CN108287553A (en) | A kind of unmanned cruiser system of two-wheel drive low speed and working method | |
| CN113218384B (en) | Indoor AGV self-adaptive positioning method based on laser SLAM | |
| CN109799832A (en) | A kind of unmanned cruiser system of four-wheel drive low speed and working method | |
| CN116700246A (en) | Unmanned vehicle navigation and obstacle avoidance method in mining area environment | |
| US20230415781A1 (en) | Systems and methods for controlling longitudinal acceleration based on lateral objects |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |