CN110687908B - Park unmanned vehicle track generation system based on ROS and control method thereof - Google Patents
Park unmanned vehicle track generation system based on ROS and control method thereof Download PDFInfo
- Publication number
- CN110687908B CN110687908B CN201910911263.0A CN201910911263A CN110687908B CN 110687908 B CN110687908 B CN 110687908B CN 201910911263 A CN201910911263 A CN 201910911263A CN 110687908 B CN110687908 B CN 110687908B
- Authority
- CN
- China
- Prior art keywords
- module
- planning
- information
- track
- target
- 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 29
- 230000008447 perception Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000011160 research Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, 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
- G05D1/0212—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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a park unmanned vehicle track generation system based on ROS and a control method thereof, comprising a target release module, a combined navigation module, a waypoint loading module, a sensing module, a track generation module and a bottom layer control module; the system comprises a target issuing module, an integrated navigation module, a waypoint loading module, a sensing module, a track generating module and a bottom layer control module, wherein the target issuing module provides planning information and position information of a target, the integrated navigation module provides state information of a vehicle, the waypoint loading module provides map information of a road, the sensing module provides position information of an obstacle, the track generating module collects the information provided by the above modules to carry out global planning and local planning to generate specific track planning information, and the bottom layer control module controls the vehicle through the generated track planning information. And the ROS-carrying track generation system carries out comprehensive analysis on the current external environment for planning.
Description
Technical Field
The invention belongs to an unmanned vehicle planning technology, and particularly relates to a park unmanned vehicle trajectory generation system based on ROS and a control method thereof.
Background
Unmanned vehicles have been a hot research problem in the field of robotics over the last decades. For an unmanned vehicle, generating a trajectory from an initial state to a target state is the basis for its autonomous navigation behavior. In recent years, researchers have conducted a lot of research on this problem, and the main research content is how to generate a trajectory, however, relatively little research is conducted on whether the generated trajectory satisfies kinematic constraints, sideslip constraints, and actuator constraints, i.e., the feasibility of the trajectory.
For unmanned vehicles, a non-integrity constrained system, researchers typically perform trajectory planning based on vehicle body models. The trajectory planning method may be further classified into a Model Predictive Control (MPC) based planning method and a geometric trajectory based planning method according to the degree of accuracy of the vehicle body Model. An unmanned vehicle trajectory planning method based on model prediction is firstly proposed by Kelly and the like. In this type of method, the curvature of the unmanned vehicle with respect to the distance traveled is characterized by a parameterized polynomial. The polynomial parameters are continuously adjusted by an optimization method, such as a gradient descent method, so that the end state of the trajectory is continuously close to the desired target state. And finally, obtaining a group of parameters, so that the unmanned vehicle can reach the target state from the initial state. The literature further extends this approach to robotic systems driven by different movement mechanisms in different scenarios. The speed planning of the unmanned vehicle is carried out by adopting a constant speed and a constant adding/decelerating speed. This type of process suffers from the following 3 major problems:
1) For an actual unmanned vehicle system, the feasibility of generating the trajectory cannot be guaranteed, and in order to solve the problem, a plurality of candidate trajectories need to be generated first, and then a feasible trajectory is selected from the trajectories to serve as an execution trajectory of the unmanned vehicle. Thus, a significant amount of time is wasted in generating infeasible traces.
2) This method is extremely sensitive to the initial curvature parameters. If the initial parameters deviate far from the optimal parameters, the method generally fails to converge to the target state.
3) When the method is used for generating the track, forward simulation needs to be continuously carried out on the vehicle body model, and a large amount of time is consumed in the simulation process.
To solve problems 2) and 3), researchers typically pre-store a large number of correspondence tables of parameters and states in a memory. In an actual unmanned vehicle system, the correspondence table usually consumes several hundred megabits of memory. Some researchers use geometric trajectories, such as line segment arcs, spiral curves, spline curves, bezier curves, etc., to approximate the kinematic constraints of the unmanned vehicle, thereby performing trajectory planning. However, these methods have less concern over actuator constraints of the vehicle body. Gomez-Bravo et al were based on spline curves and studied for parking, a typical operation. The method generates a curve with continuous curvature and simultaneously meets collision avoidance constraints, but does not make constraints on curvature boundaries. Gomez-Bravo et al have only performed experiments on small electric vehicles with strong steering ability. Jolly et al studied the multi-robot trajectory planning problem based on the third-order Bezier curve. Since Jolly et al mainly studied robots with differential steering, the proposed method does not consider curvature constraints, but only acceleration constraints. Choi et al planned a trajectory with a continuous curvature based on bezier curves. To ensure both curvature continuity and numerical stability, choi et al concatenate low-order bezier curves to generate a trajectory with continuous curvature. However, choi et al do not constrain the curvature boundaries, nor do they give a real-time analysis of the algorithm.
Liu Xiao Saan and Zhao Bin in the text of "mobile robot platform system design based on ROS", propose a mobile robot platform based on ROS. The mobile robot platform has the characteristics of programmable software and hardware, strong flexibility, modularization and the like, and the controller of the mobile robot platform adopts an Android system. The mobile robot platform motion control module perfects a scheduling algorithm of path tracking aiming at path planning generated by a navigation module, changes the path planning generated once into 2s, and aims to reduce the problem of back and forth swing of a robot in the motion process caused by frequent path planning of a system and realize an autonomous obstacle avoidance function. The scheme has the following problems: 1. the mobile robot platform has a single function. 2. The mobile robot platform has poor expansibility.
Disclosure of Invention
The invention aims to provide a park unmanned vehicle trajectory generation system based on ROS in a static scene and a control method thereof, and the unmanned vehicle trajectory planning function is realized.
The technical solution for realizing the purpose of the invention is as follows: a park unmanned vehicle track generation system based on ROS comprises a target release module, a combined navigation module, a waypoint loading module, a sensing module, a track generation module and a bottom layer control module; the system comprises a target issuing module, an integrated navigation module, a waypoint loading module, a sensing module, a track generating module, a bottom layer control module and a ground control module, wherein the target issuing module provides planning information and position information of a target, the integrated navigation module provides state information of a vehicle, the waypoint loading module provides map information of a road, the sensing module provides position information of an obstacle, the track generating module collects the information provided by the above modules to perform global planning and local planning to generate specific track planning information, and the bottom layer control module controls the vehicle through the generated track planning information. The track generation module is respectively connected with the target release module, the integrated navigation module, the waypoint loading module, the sensing module and the bottom layer control module, and the track generation module carrying the ROS carries out comprehensive analysis on the current external environment for planning.
A control method of a park unmanned vehicle track generation system based on ROS is characterized in that a track generation module carries out comprehensive analysis and planning on the current external environment, and the method comprises the following specific steps:
step 1, a target issuing module provides planning information and position information of a target, a combined navigation module provides state information of a vehicle, and the step 2 is carried out;
step 2, the waypoint loading module provides map information of a road, the sensing module provides position information of an obstacle, and the step 3 is switched to;
step 3, a track generation module collects the information to carry out global planning and local planning, generates specific track planning information and then goes to step 4;
and 4, the bottom layer control module controls the vehicle through the generated track planning information.
Compared with the prior art, the invention has the remarkable advantages that:
(1) The module based on ROS design has the advantages of distributed communication, and is convenient for the expansion and optimization of various modules.
(2) The algorithm of system integration can achieve the effect of real-time planning after being optimized.
(3) The integrated accurate rectangular obstacle detection method has higher accuracy than circular detection.
Drawings
FIG. 1 is a basic block diagram of the ROS-based park unmanned vehicle trajectory generation system of the present invention.
Fig. 2 is a global planning flow chart of the ROS-based park unmanned vehicle trajectory generation system control method of the present invention.
Fig. 3 is a partial planning flowchart of the ROS-based park unmanned vehicle trajectory generation system control method of the present invention.
Detailed Description
The present invention is described in further detail below with reference to the attached drawing figures.
With reference to fig. 1, the system for generating a park unmanned vehicle trajectory based on ROS in the present invention includes a target issuing module, a combined navigation module, a waypoint loading module, a sensing module, a trajectory generating module and a bottom layer control module; the system comprises a target issuing module, an integrated navigation module, a waypoint loading module, a sensing module, a track generation module and a bottom layer control module, wherein the target issuing module provides planning information and position information (such as absolute position of a target) of the target, the integrated navigation module provides state information (such as current pose information, speed information and acceleration information) of a vehicle, the waypoint loading module provides map information (such as waypoint positions of a driving area sampled in advance) of a road, the sensing module provides position information (such as positions of obstacles relative to a vehicle body coordinate system) of obstacles, the track generation module collects the information provided by the above modules to carry out global planning and local planning to generate specific track planning information, and the bottom layer control module controls the vehicle through the generated track planning information. The track generation module is respectively connected with the target release module, the integrated navigation module, the waypoint loading module, the sensing module and the bottom layer control module, and the track generation module carrying the ROS carries out comprehensive analysis on the current external environment for planning.
With reference to fig. 2, a control method of a ROS-based track generation module for a park unmanned vehicle, where the track generation module performs a comprehensive analysis on a current external environment to plan, includes the following specific steps:
step 1, a target issuing module provides planning information and position information of a target, a combined navigation module provides state information of a vehicle, and the step 2 is carried out;
step 2, the waypoint loading module provides map information of the road, the sensing module provides position information of the barrier, and the step 3 is switched to;
step 3, a track generation module collects the information to carry out global planning and local planning, generates specific track planning information and shifts to step 4;
and 4, the bottom layer control module controls the vehicle through the generated track planning information.
Further, the track generation module performs global planning first and then performs local planning, wherein the global planning comprises the following steps:
step 3-1), starting global planning by a track generation module, importing road map information provided by a waypoint loading module, and turning to the step 3-2);
step 3-2), predicting the track of the navigation point by using a KD tree according to the position information of the obstacle and the target provided by the perception module and the target release module, and turning to the step 3-3);
3-3), calling a Dubins curve to generate an initial waypoint according to the initial course angle information of the automobile provided by the integrated navigation module, and turning to the step 3-4);
step 3-4), connecting two parts of the waypoints by applying cubic spline interpolation to generate a global route, and turning to the step 3-5);
and 3-5) finishing the global planning.
With reference to fig. 3, a control method of a park unmanned vehicle trajectory generation system based on ROS performs local planning after global planning is completed, and the local planning method includes the following steps:
step 3-a >, the track generation module starts local planning, planning time, a transverse position and a longitudinal speed are sampled in a Frenet coordinate, and the step 3-b > is carried out;
step 3-b >, a trajectory set is generated by using a polynomial according to the planning information and the position information of the target provided by the target release module, and the step 3-c > is carried out;
step 3-c >, vehicle dynamics constraint and obstacle collision of each track are checked through intersection of the rotation matrixes, and the step 3-d > is carried out;
step 3-d >, selecting a track with the lowest cost, thinning the optimal track of the bottom control module, and turning to step 3-e >;
and 3-e >, finishing the local planning.
Claims (2)
1. A control method of a park unmanned vehicle track generation system based on ROS is characterized in that the park unmanned vehicle track generation system based on ROS comprises
The target issuing module is used for providing planning information and position information of a target;
the integrated navigation module provides state information of the vehicle;
the navigation point loading module is used for providing map information of roads;
the sensing module is used for providing position information of the obstacle;
the track generation module is respectively connected with the integrated navigation module, the waypoint loading module, the sensing module and the target issuing module, collects all the information, performs global planning and local planning and generates specific track planning information;
the bottom layer control module is connected with the track generation module and used for controlling the vehicle through the generated track planning information;
the track generation module plans by comprehensively analyzing the current external environment, and comprises the following specific steps:
step 1, a target publishing module provides planning information and position information of a target, an integrated navigation module provides state information of a vehicle, and the step 2 is switched;
step 2, the waypoint loading module provides map information of a road, the sensing module provides position information of an obstacle, and the step 3 is switched to;
step 3, the track generation module collects the information to carry out global planning and local planning and generates specific track planning information, and the global planning step is as follows:
step 3-1), starting global planning by a track generation module, importing road map information provided by a waypoint loading module, and turning to the step 3-2);
step 3-2), predicting the track of the navigation point by using a KD tree according to the position information of the obstacle and the target provided by the perception module and the target release module, and turning to the step 3-3);
step 3-3), calling a Dubins curve to generate an initial waypoint according to the state information of the vehicle provided by the integrated navigation module, and turning to the step 3-4);
step 3-4), connecting two parts of the route points by applying cubic spline interpolation to generate a global route, and turning to the step 3-5);
step 3-5), completing global planning;
turning to step 4;
and 4, the bottom layer control module controls the vehicle through the generated track planning information.
2. The control method of the ROS-based park unmanned aerial vehicle trajectory generation system according to claim 1, wherein the local planning comprises the following specific steps:
step 3-a), a track generation module starts local planning, planning time, a transverse position and a longitudinal speed are sampled in Frenet coordinates, and the step 3-b) is switched;
step 3-b), generating a track set by using a polynomial according to the planning information and the position information of the target provided by the target release module, and turning to step 3-c);
step 3-c), checking the vehicle dynamic constraint and the obstacle collision of each track through the intersection of the rotation matrixes, and turning to the step 3-d);
step 3-d), selecting a track with the lowest cost, thinning the optimal track of the bottom control module, and turning to step 3-e);
and 3-e) finishing the local planning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910911263.0A CN110687908B (en) | 2019-09-25 | 2019-09-25 | Park unmanned vehicle track generation system based on ROS and control method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910911263.0A CN110687908B (en) | 2019-09-25 | 2019-09-25 | Park unmanned vehicle track generation system based on ROS and control method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110687908A CN110687908A (en) | 2020-01-14 |
CN110687908B true CN110687908B (en) | 2023-01-13 |
Family
ID=69110143
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910911263.0A Active CN110687908B (en) | 2019-09-25 | 2019-09-25 | Park unmanned vehicle track generation system based on ROS and control method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110687908B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111240187B (en) * | 2020-01-16 | 2023-01-13 | 南京理工大学 | Vehicle track tracking control algorithm based on vehicle error model |
CN111753694B (en) * | 2020-06-16 | 2024-02-09 | 西安电子科技大学 | Unmanned vehicle target searching system and method |
CN111845774B (en) * | 2020-07-20 | 2021-12-03 | 上海大学 | Automatic driving automobile dynamic trajectory planning and tracking method based on transverse and longitudinal coordination |
CN112833898B (en) * | 2020-12-30 | 2023-03-21 | 清华大学 | ROS-oriented unmanned vehicle backing method |
CN114371712B (en) * | 2022-01-11 | 2024-06-25 | 湖南大学 | Parking track re-planning method with non-stop obstacle detouring function |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107145153A (en) * | 2017-07-03 | 2017-09-08 | 北京海风智能科技有限责任公司 | A kind of service robot and its indoor navigation method based on ROS |
CN108279679A (en) * | 2018-03-05 | 2018-07-13 | 华南理工大学 | A kind of Intelligent meal delivery robot system and its food delivery method based on wechat small routine and ROS |
CN108897328A (en) * | 2018-08-27 | 2018-11-27 | 桂林电子科技大学 | Wheel chair robot and its indoor autonomous navigation method |
CN109333540A (en) * | 2018-12-05 | 2019-02-15 | 河海大学常州校区 | A kind of guest-meeting robot and its application method based on raspberry pie |
CN109343541A (en) * | 2018-12-05 | 2019-02-15 | 河海大学常州校区 | A kind of AGV and its application method based on ROS |
CN109976355A (en) * | 2019-04-26 | 2019-07-05 | 腾讯科技(深圳)有限公司 | Method for planning track, system, equipment and storage medium |
CN109978272A (en) * | 2019-03-30 | 2019-07-05 | 华南理工大学 | A kind of path planning system and method based on multiple omni-directional mobile robots |
-
2019
- 2019-09-25 CN CN201910911263.0A patent/CN110687908B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107145153A (en) * | 2017-07-03 | 2017-09-08 | 北京海风智能科技有限责任公司 | A kind of service robot and its indoor navigation method based on ROS |
CN108279679A (en) * | 2018-03-05 | 2018-07-13 | 华南理工大学 | A kind of Intelligent meal delivery robot system and its food delivery method based on wechat small routine and ROS |
CN108897328A (en) * | 2018-08-27 | 2018-11-27 | 桂林电子科技大学 | Wheel chair robot and its indoor autonomous navigation method |
CN109333540A (en) * | 2018-12-05 | 2019-02-15 | 河海大学常州校区 | A kind of guest-meeting robot and its application method based on raspberry pie |
CN109343541A (en) * | 2018-12-05 | 2019-02-15 | 河海大学常州校区 | A kind of AGV and its application method based on ROS |
CN109978272A (en) * | 2019-03-30 | 2019-07-05 | 华南理工大学 | A kind of path planning system and method based on multiple omni-directional mobile robots |
CN109976355A (en) * | 2019-04-26 | 2019-07-05 | 腾讯科技(深圳)有限公司 | Method for planning track, system, equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110687908A (en) | 2020-01-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110687908B (en) | Park unmanned vehicle track generation system based on ROS and control method thereof | |
Li et al. | An optimization-based path planning approach for autonomous vehicles using the DynEFWA-artificial potential field | |
CN111845774B (en) | Automatic driving automobile dynamic trajectory planning and tracking method based on transverse and longitudinal coordination | |
CN109375632B (en) | Real-time trajectory planning method for automatic driving vehicle | |
CN110244735B (en) | Heuristic dynamic programming control method for tracking preset track by mobile robot | |
CN102393744B (en) | Navigation method of pilotless automobile | |
Ritschel et al. | Nonlinear model predictive path-following control for highly automated driving | |
Kang et al. | On-road path generation and control for waypoints tracking | |
CN111123947A (en) | Robot traveling control method and device, electronic device, medium, and robot | |
Li et al. | Multiple vehicle formation control based on robust adaptive control algorithm | |
Sharma et al. | A survey on smooth path generation techniques for nonholonomic autonomous vehicle systems | |
Wang et al. | Research on logistics autonomous mobile robot system | |
Jiang et al. | A dynamic motion planning framework for autonomous driving in urban environments | |
CN114200926B (en) | Local path planning method and system for unmanned vehicle | |
Cheng et al. | Planning and control for a fully-automatic parallel parking assist system in narrow parking spaces | |
Signifredi et al. | A general purpose approach for global and local path planning combination | |
CN112799384A (en) | Vehicle and driving track planning method and planning device thereof | |
Bae et al. | Steering rate controller based on curvature of trajectory for autonomous driving vehicles | |
Kong et al. | Real-time motion planning based on layered cost map for AGV navigation | |
Chen et al. | Nonlinear model predictive control of autonomous vehicles considering dynamic stability constraints | |
Nietzschmann et al. | Trajectory optimization for car-like vehicles in structured and semi-structured environments | |
Vilca et al. | An overall control strategy based on target reaching for the navigation of an urban electric vehicle | |
Hu et al. | Decision-making system based on finite state machine for low-speed autonomous vehicles in the park | |
Hegedüs et al. | Real-time optimal motion planning for automated road vehicles | |
Hafner et al. | Dynamic trajectory planning for trailer backup |
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 |