CN114543814A - Robot autonomous positioning and navigation method applied to three-dimensional environment - Google Patents
Robot autonomous positioning and navigation method applied to three-dimensional environment Download PDFInfo
- Publication number
- CN114543814A CN114543814A CN202210174162.1A CN202210174162A CN114543814A CN 114543814 A CN114543814 A CN 114543814A CN 202210174162 A CN202210174162 A CN 202210174162A CN 114543814 A CN114543814 A CN 114543814A
- Authority
- CN
- China
- Prior art keywords
- slope
- navigation
- algorithm
- map
- robot
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Abstract
The invention discloses a robot autonomous positioning and navigation method applied to a three-dimensional environment, and a Ubuntu system and a ring ROS environment required by using the method are configured. And configuring a function package of a compiled Cartogrer algorithm and a Navigation package. And (4) establishing a ground map and a slope top map by using a Cartogrrapher algorithm. And selecting and configuring a positioning algorithm to realize autonomous positioning and navigation. And (4) setting a multi-point navigation task, and after the robot moves to the upper part of the slope, replacing the original ground map with a slope top map, repositioning to perform navigation of a slope top plane, thereby completing autonomous positioning and navigation in a three-dimensional environment. The method enables the robot mobile platform to realize autonomous positioning and navigation of a three-dimensional environment according to the point cloud data of the three-dimensional laser radar under the reference of the two-dimensional map.
Description
Technical Field
The invention relates to the field of autonomous positioning and navigation of a mobile robot, in particular to autonomous positioning and path planning in a complex three-dimensional terrain environment under the condition that the mobile robot has a two-dimensional map.
Background
In recent years, almost all intelligent robots, except industrial robots, cannot walk without leaving, so robot navigation technology is one of the core technologies of intelligent robots. Research on navigation techniques is continually being iteratively updated. Autonomous positioning and navigation are core technologies in the research field of intelligent robots, and map construction, autonomous positioning, path planning and the like are key problems to be solved, namely 3 problems of 'where does i' the robot, 'where does i' go 'and how to reach' the robot. The robot needs to sense the information of the environment through the sensor, acquire the environment data and combine the state of the robot, and finally make a decision suitable for the environment and the target.
The robot autonomous positioning navigation technology comprises the following steps: location and map creation (SLAM) and path planning and motion control. In a traditional autonomous positioning navigation system, a two-dimensional map is constructed by using an SLAM (mapping algorithm or Cartogrier algorithm) first, robot position and posture information is provided by using a positioning algorithm (AMCL algorithm or Cartogrier algorithm), and a route is planned by using a path planning algorithm (A-x algorithm or Dijskstra algorithm, DWA algorithm or TEB algorithm, or the like) so as to control the robot to move to reach a specified target position and posture.
The traditional navigation system only converts a pgm map and laser point cloud fed back in real time into an occupation grid map, loses three-dimensional environment information, and is generally classified into obstacles when facing a passable three-dimensional environment such as a slope (such as a slope, a bridge floor, a stair and the like), so that a passing path cannot be planned, avoidance actions occur, and the problem is that the traditional navigation system cannot be well applied to a complex environment.
Therefore, how to solve the above problems is a key problem in solving the application of the mobile robot in the environment with complex terrain.
Disclosure of Invention
The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not intended to detail all of the contemplated aspects, but is provided for the sole purpose of presenting some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
The invention aims to solve the problems and provide an all-weather and all-time-domain flexible navigation capability for a ground unmanned vehicle under complex environments such as satellite rejection, physical space change and the like. The early preparation of the method is to establish a ground map in the global scope of the ground under the ramp and establish a slope top map in the local scope of the top of the ramp. And then, carrying out slope detection according to the geometric characteristics of the slope reflection point cloud fitting straight line by using the laser point cloud information, feeding back the slope pose to a navigation layer, carrying out grid value processing, and carrying out path planning by using the updated occupancy grid map to finish the uphill action. After the uphill action is finished, the mobile robot is located at the top of the slope, the slope top map replaces the ground map to repeatedly position the robot, and the navigation task on the slope top plane is continuously finished.
The invention provides a method for realizing autonomous positioning and navigation of a mobile robot based on laser point cloud in a three-dimensional environment facing complex terrain, which comprises the following technical scheme:
the method comprises the following steps: the Ubuntu system and the ring ROS environment required by the method are configured. And establishing a three-dimensional simulation model for debugging, and configuring a real mobile robot platform and the multi-line laser radar.
Step two: and configuring a function package compiled with a Cartogrrapher algorithm and a Navigation package.
Step three: and (4) establishing a ground map and a slope top map by using a Cartogrrapher algorithm.
Step four: selecting and configuring a positioning algorithm, selecting and configuring a global path planning algorithm and a local path planning algorithm, configuring a Cartographer algorithm parameter file to provide a positioning function, selecting an A-x algorithm (global path planning) and a TEB algorithm (local path planning) by the path planning algorithm, and adjusting a cost map and the path planning parameter file.
Step five: and setting a multi-point navigation task, wherein a target point is arranged in front of the slope so as to detect the slope, when the robot moves in front of the slope, the slope is detected, slope pose information is fed back, the cost map updates the cost value according to the slope pose information, the cost value at the slope is set to be 0, and the path planning considers that the slope is a passable route so that the robot can move to the slope.
Step six: and after the robot moves to the upper part of the slope, the original ground map is replaced to the top map of the slope, and the relocation is carried out so as to carry out the navigation of the top plane of the slope, thereby completing the autonomous positioning and navigation in the three-dimensional environment.
According to the method for realizing the autonomous positioning and navigation of the mobile robot based on the laser point cloud in the three-dimensional environment facing the complex terrain, in the first step, the following steps are included:
step 1: ubuntu18.04 and ROS release Melodic versions were configured.
Step 2: a three-dimensional simulation world model is built by utilizing Gazebo software, so that a mobile robot platform can be simulated, simulation data of the multi-line laser radar can be collected, and an actual mobile robot platform and the multi-line laser radar are built for experiment use.
According to the method for realizing the autonomous positioning and navigation of the mobile robot based on the laser point cloud in the three-dimensional environment facing the complex terrain, in the second step, the following steps are included:
step 1: because the mapping algorithm of Gmapping has no loop and depends on a milemeter, the experimental effect is not as good as that of the mapping algorithm of Cartogrer. Installing protobuf, installing ceres-solvent, manually compiling and installing a Cartographer and establishing a complete working environment, processing the measured point cloud data by the Cartographer, comparing the point cloud data with the sub-graph obtained by the last scanning, inserting the point cloud data into the last sub-graph for updating and optimizing if the point cloud data is successfully matched with the sub-graph obtained by the last scanning, and generating the next sub-graph. When no new sub-graph is inserted, the construction of the complete sub-graph is completed. And after the construction of a plurality of sub-images is finished, the back end starts loop detection, and each sub-image is matched with all the point cloud frames subjected to motion filtering after the construction is finished, so that loop optimization is carried out, and accumulated errors are eliminated.
Step 2: and manually installing and compiling the navigation package, establishing a complete working environment, and configuring related parameters to complete the construction of the navigation system.
According to the method for realizing the autonomous positioning and navigation of the mobile robot based on the laser point cloud in the three-dimensional environment facing the complex terrain, the method comprises the following steps:
step 1: and installing and compiling a pointclosed _ to _ laser package, operating a multi-line laser radar driving program and converting a laser point cloud three-dimensional wire harness into a two-dimensional wire harness program so as to more fully extract the characteristics of the surrounding environment, configuring topic names and function package parameters, operating a mobile robot chassis driving program, making a pose conversion relation between a chassis and a radar, operating a cartographer program and driving the chassis to carry out two-dimensional mapping.
Step 2: and in the two-dimensional map building process, a ground map is built under a slope, and a slope top map is built after the slope is uphill.
According to the method for realizing the autonomous positioning and navigation of the mobile robot based on the laser point cloud in the three-dimensional environment facing the complex terrain, in the fourth step, the following steps are included:
step 1: and configuring a Cartogrer algorithm parameter file to provide a positioning function, writing a configuration file by using a Cartogrer pure positioning interface, modifying a launch file and a lua file, and loading the previously constructed two-dimensional pbstream format map. The conventional navigation system uses the monte carlo (AMCL) positioning algorithm,
step 2: and configuring a global path planning configuration file, and selecting an A-algorithm as a global path planning algorithm (the default path planning algorithm is Dijkstra algorithm). The A-point algorithm with the heuristic function in the field of artificial intelligence has a memorability function, so that the optimal path can be autonomously selected in a road network, and the searching efficiency is higher along with the increase of the obstacle information and the geographic position information. The A-algorithm and the traditional Dijkstra algorithm are compared in a simulation mode through experiments, the search speed and the search efficiency are compared, and the result proves that the A-algorithm in the actual road network has a more obvious search effect.
And step 3: and installing a compiled TEB _ local _ planer function package, configuring a local path planning configuration file, and selecting a TEB algorithm as a local path planning algorithm. Compared with the traditional DWA algorithm, the TEB algorithm has strong prospective and can optimize a front section of track; the dynamic obstacle avoidance method can be used for dynamically avoiding obstacles, and has a good obstacle avoidance effect on the dynamic obstacles. Although the computational complexity is large, the complexity can be reduced by sacrificing the predicted distance and adjusting the computation frequency.
And 4, step 4: a cost map conversion plug-in (costmap _ converter plug-in) is installed to realize tracking and dynamic obstacle avoidance, an original cost map is composed of unit cells in a grid map and used for representing obstacles, but the unit cells occupy larger computing resources, so the plug-in is adopted to convert the unit cells into points, lines and polygons for representation. The obstacle in the costmap two-dimensional is converted to a geometric primitive (point, line, polygon) to represent using the costmap _ converter plug-in. Each obstacle is considered to be point if not actively activated. When the map resolution is high, only point is used, which results in too large calculation amount in calculating discrete topologies. Of course, costmap _ coverter also consumes computational resources, but it can be computed in parallel.
According to the method for realizing the autonomous positioning and navigation of the mobile robot based on the laser point cloud in the three-dimensional environment facing the complex terrain, in the fifth step, the method comprises the following steps:
step 1: installing a navi _ multi _ targets _ pub _ rviz _ plugin, configuring rviz so as to complete a multipoint navigation task, setting a plurality of target points, and setting one of the target points in front of a slope.
Step 2: the robot feeds back the detected slope pose information to the cost map code packet, the cost value is updated according to the slope pose information, the cost value at the slope is set to be 0, the path planning considers that the slope is a passable route, and the robot can move to the slope.
According to the method for realizing the autonomous positioning and navigation of the mobile robot based on the laser point cloud in the three-dimensional environment facing the complex terrain, in the sixth step, the following steps are included:
step 1: and after the robot moves to the upper part of the slope, the original ground map is replaced to the top map of the slope.
Step 2: the robot relocates to perform navigation of the top plane of the slope, thereby completing autonomous positioning and navigation in a three-dimensional environment.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
Fig. 1 is an overall system framework diagram applied by the method.
Fig. 2 is an overall schematic diagram of a simulation experiment platform.
FIG. 3 is a simulated ramp environment.
Fig. 4 is a two-dimensional ground map (overall).
Fig. 5 is a two-dimensional hill top map (partial).
FIG. 6 is a schematic view of navigation process node communication.
Fig. 7 is a schematic diagram of a navigation process target point and a path planning.
Fig. 8 is a laser spot cloud before treatment.
Fig. 9 is a laser spot cloud after processing by the slope detection program.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is noted that the aspects described below in connection with the figures and the specific embodiments are only exemplary and should not be construed as imposing any limitation on the scope of the present invention.
Step 1: the two-dimensional map plane of the robot driving in the experimental scene is shown in fig. 4.
Step 2: and setting a plurality of target points so as to move the platform for remote navigation.
And step 3: one of the target points is set in front of the ramp for detection by the ramp detection algorithm.
And 4, step 4: the slope detection principle mainly applies slope single-frame point cloud data fed back by a radar. Firstly, filtering and ground segmentation are carried out by utilizing a PCL (personal computer) library, laser point clouds belonging to the ground part are removed, and only the laser point clouds in the range of 30 degrees at the left and right in front of a vehicle head are reserved; clustering the processed laser point cloud by utilizing a PCL (personal computer) library, and performing ground projection on the clustered point cloud; and then, fitting straight lines on the projection point clouds, clustering according to the similarity of the slopes of the fitting straight lines of the slope projection point clouds, screening point cloud clusters with similar slopes, and obtaining the final slope point cloud pose.
And 5: after a slope is detected according to the laser point cloud, the pose of the slope point cloud is fed back to a costmap _ two-dimensional code packet, the costmap _ two-dimensional code packet utilizes input sensor data to construct a data two-dimensional cost map, and the cost of the two-dimensional cost map is calculated according to an occupied grid and an expansion radius defined by a user. In addition, the package also supports initialization of a cost map by using a map _ server, supports a cost map of a rolling window, and supports configuration of parameterized subscriptions and sensor themes.
Step 6: after the pose of the slope point cloud is fed back to the costmap _ two-dimensional code packet, the navigation layer carries out path planning according to the cost value of the cost map. costmap consists of multiple layers, one for each function map. StaticLayer is the first layer, obstaclerlayer is the second layer, InflationLayer is the third layer. These three layers are combined into a mastermap (final costmap) for use by the route planning module. And obtaining pose information of the slope point cloud, customizing a slope layer in costmap, overlapping the slope layer with the original three layers, and setting the cost value of the slope to be 0.
And 7: after the cost value of the slope in the cost map costmap is set to be 0, the path planning considers that the slope is a passable route, the robot can move to the slope, and after the robot moves to the upper part of the slope, the original ground map is replaced to the top map of the slope, and secondary relocation is carried out to carry out navigation on the top plane of the slope.
Experiments prove that the method can be used for autonomous positioning and navigation of the mobile robot in a three-dimensional environment.
To simplify the explanation of the present invention, the above-described graphics and text have been described as a series of steps, and the processing of slope detection and navigation layers from laser point cloud data has been described, and the principle thereof will be understood by those skilled in the art.
Although illustrative embodiments of the present invention have been described above for the purpose of facilitating understanding by those skilled in the art, the present invention is not limited to the scope of the embodiments, and those skilled in the art can make various changes or modifications within the scope of the appended claims as long as they are within the spirit and scope of the present invention as defined and defined by the appended claims.
Claims (7)
1. A method for autonomous positioning and navigation of a robot in a three-dimensional environment, comprising:
the method comprises the following steps: a Ubuntu system and a ring ROS environment required by the method are configured; establishing a three-dimensional simulation model for debugging, and configuring a real mobile robot platform and a multi-line laser radar;
step two: configuring and compiling a Cartogrrapher algorithm function package and a Navigation package;
step three: establishing a ground map and a slope top map by using a Cartogrier algorithm;
step four: selecting and configuring a positioning algorithm, selecting and configuring a global path planning algorithm and a local path planning algorithm, configuring a Cartographer algorithm parameter file to provide a positioning function, selecting an A-x algorithm and a TEB algorithm by the path planning algorithm, adjusting a cost map and the path planning parameter file, and realizing autonomous positioning and navigation;
step five: setting a multi-point navigation task, wherein a target point is arranged in front of a slope so as to detect the slope, when the robot moves to the front of the slope, the slope is detected, slope pose information is fed back, a cost map updates the cost value according to the slope pose information, the cost value at the slope is set to be 0, and the path planning considers that the slope is a passable route and enables the robot to move to the slope;
step six: and after the robot moves to the upper part of the slope, the original ground map is replaced to the top map of the slope, and the relocation is carried out so as to carry out the navigation of the top plane of the slope, thereby completing the autonomous positioning and navigation in the three-dimensional environment.
2. The method for robot autonomous positioning and navigation in three-dimensional environment according to claim 1, wherein in step one, a system platform required by the method is configured, an Ubuntu18.04 system and a ROS release Melodic version are configured, and Gazebo software is used for building a three-dimensional simulated world model and a simulated mobile platform with a sensor.
3. The method for the autonomous positioning and navigation of the robot in the three-dimensional environment as recited in claim 1, wherein in the second step, the environment required for drawing and navigation is configured and built, and each node is configured, so as to ensure successful topic communication between the nodes.
4. The method for autonomous positioning and navigation of a robot in a three-dimensional environment as claimed in claim 1, wherein in step three, Cartographer algorithm is used to perform mapping in the simulated world, a ground map is built on the ground, and a top map is built on the top of a slope.
5. The method as claimed in claim 1, wherein in step four, the Cartographer algorithm parameter file is configured to provide a positioning function, the path planning algorithm selects the a-x algorithm and the TEB algorithm, and the cost map and the path planning parameter file are adjusted to achieve autonomous positioning and navigation.
6. The method for autonomous positioning and navigation of a robot in a three-dimensional environment according to claim 1, wherein in step five, a slope layer is configured in a costmap _2d code packet, a slope detection algorithm is included, the detection slope pose is fed back to the calculation of the cost map, and is overlapped with other cost map layers to adjust the total cost value to zero.
7. The method as claimed in claim 1, wherein in step six, the target point is set within a certain range in front of the slope, and after the mobile platform of the robot detects the slope and moves above the slope, the referenced two-dimensional map is changed from a ground map to a top map, and the robot is repositioned and the multi-point navigation action is continued.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210174162.1A CN114543814A (en) | 2022-02-24 | 2022-02-24 | Robot autonomous positioning and navigation method applied to three-dimensional environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210174162.1A CN114543814A (en) | 2022-02-24 | 2022-02-24 | Robot autonomous positioning and navigation method applied to three-dimensional environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114543814A true CN114543814A (en) | 2022-05-27 |
Family
ID=81678082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210174162.1A Pending CN114543814A (en) | 2022-02-24 | 2022-02-24 | Robot autonomous positioning and navigation method applied to three-dimensional environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114543814A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573140A (en) * | 2013-10-09 | 2015-04-29 | 北京军区军事训练模拟仿真研发服务中心 | Layered dynamic path planning method applied to virtual simulation |
| CN105487535A (en) * | 2014-10-09 | 2016-04-13 | 东北大学 | Mobile robot indoor environment exploration system and control method based on ROS |
| CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
| CN111813117A (en) * | 2020-07-09 | 2020-10-23 | 北京布科思科技有限公司 | Robot line patrol priority navigation method, device and equipment |
| CN112650255A (en) * | 2020-12-29 | 2021-04-13 | 杭州电子科技大学 | Robot indoor and outdoor positioning navigation system method based on vision and laser radar information fusion |
| US20210154835A1 (en) * | 2019-11-21 | 2021-05-27 | Ubtech Robotics Corp Ltd | Robot path planning method and apparatus and robot using the same |
| CN112987763A (en) * | 2021-05-11 | 2021-06-18 | 南京理工大学紫金学院 | ROS-based intelligent trolley of autonomous navigation robot control system |
| CN113485346A (en) * | 2021-07-15 | 2021-10-08 | 上海交通大学 | Autonomous navigation method of mobile robot in nuclear accident complex environment |
| US11175664B1 (en) * | 2019-01-15 | 2021-11-16 | Amazon Technologies, Inc. | Navigation directly from perception data without pre-mapping |
| CN113884574A (en) * | 2021-11-03 | 2022-01-04 | 河南理工大学 | SLAM-based intelligent pavement longitudinal section flatness measuring instrument |
-
2022
- 2022-02-24 CN CN202210174162.1A patent/CN114543814A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573140A (en) * | 2013-10-09 | 2015-04-29 | 北京军区军事训练模拟仿真研发服务中心 | Layered dynamic path planning method applied to virtual simulation |
| CN105487535A (en) * | 2014-10-09 | 2016-04-13 | 东北大学 | Mobile robot indoor environment exploration system and control method based on ROS |
| CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
| US11175664B1 (en) * | 2019-01-15 | 2021-11-16 | Amazon Technologies, Inc. | Navigation directly from perception data without pre-mapping |
| US20210154835A1 (en) * | 2019-11-21 | 2021-05-27 | Ubtech Robotics Corp Ltd | Robot path planning method and apparatus and robot using the same |
| CN111813117A (en) * | 2020-07-09 | 2020-10-23 | 北京布科思科技有限公司 | Robot line patrol priority navigation method, device and equipment |
| CN112650255A (en) * | 2020-12-29 | 2021-04-13 | 杭州电子科技大学 | Robot indoor and outdoor positioning navigation system method based on vision and laser radar information fusion |
| CN112987763A (en) * | 2021-05-11 | 2021-06-18 | 南京理工大学紫金学院 | ROS-based intelligent trolley of autonomous navigation robot control system |
| CN113485346A (en) * | 2021-07-15 | 2021-10-08 | 上海交通大学 | Autonomous navigation method of mobile robot in nuclear accident complex environment |
| CN113884574A (en) * | 2021-11-03 | 2022-01-04 | 河南理工大学 | SLAM-based intelligent pavement longitudinal section flatness measuring instrument |
Non-Patent Citations (2)
| Title |
|---|
| 程东锋: "基于ROS的新型全地形轮式移动机器人智能导航设计", 《中国优秀硕士学位论文全文数据库（电子期刊）》, pages 37 - 38 * |
| 程志: "自主导航的移动机器人动态路径规划算法研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》, pages 61 - 62 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Oh et al. | Complete coverage navigation of cleaning robots using triangular-cell-based map | |
| Azpúrua et al. | Multi-robot coverage path planning using hexagonal segmentation for geophysical surveys | |
| Bogdan Rusu et al. | Leaving Flatland: Efficient real‐time three‐dimensional perception and motion planning | |
| Kallmann et al. | Geometric and discrete path planning for interactive virtual worlds | |
| CN111968229A (en) | High-precision map making method and device | |
| CN110471426A (en) | Unmanned intelligent vehicle automatic Collision Avoidance method based on quantum wolf pack algorithm | |
| Morisset et al. | Leaving flatland: Toward real-time 3d navigation | |
| Huang et al. | A multi-robot coverage path planning algorithm for the environment with multiple land cover types | |
| CN114859375A (en) | Autonomous exploration mapping system and method based on multi-robot cooperation | |
| CN114577214B (en) | Wheeled robot path planning method applied to cross-heterogeneous multi-layer space | |
| CN114967701A (en) | Autonomous navigation method for mobile robot in dynamic environment | |
| CN109977455B (en) | Ant colony optimization path construction method suitable for three-dimensional space with terrain obstacles | |
| Xuexi et al. | Survey on key technology of robocup rescue robot | |
| CN116338729A (en) | Three-dimensional laser radar navigation method based on multilayer map | |
| CN114543814A (en) | Robot autonomous positioning and navigation method applied to three-dimensional environment | |
| Atas et al. | Elevation state-space: Surfel-based navigation in uneven environments for mobile robots | |
| CN116136417A (en) | Unmanned vehicle local path planning method facing off-road environment | |
| Thorpe | Outdoor visual navigation for autonomous robots | |
| Cupec et al. | Step sequence planning for a biped robot by means of a cylindrical shape model and a high-resolution 2.5 D map | |
| CN113485378B (en) | Mobile robot path planning method, system and storage medium based on traffic rules | |
| CN115328210A (en) | Path planning method and device, terminal equipment and storage medium | |
| CN111596668B (en) | Mobile robot anthropomorphic path planning method based on reverse reinforcement learning | |
| Yang et al. | An optimization-based selection approach of landing sites for swarm unmanned aerial vehicles in unknown environments | |
| CN114839975A (en) | Autonomous exploration type semantic map construction method and system | |
| Liu et al. | [Retracted] Collaboration and Management of Heterogeneous Robotic Systems for Road Network Construction, Management, and Maintenance under the Vision of “BIM+ GIS” Technology |
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 |