57 results about "Robot localization" patented technology

The present invention belongs to the technical field of visual SLAM localization. Disclosed is a robot localization method based on improved point-line feature and IMU fusion. The method in the present invention comprises: 1, extracting feature points from an image, performing tracking and matching, using an improved line segment detection (LSD) method to extract lines from the image, using a line segment merging algorithm to merge short line segments belonging to the same straight line, and then using an LBD to perform matching; 2, performing pre-integration on collected IMU data; 3, using the same initialization policy as VINS-Mono; and 4, using information added to a sliding window, so as optimize the pose of a camera. In the present invention, filtering processing is added, a large number of line segments are no longer extracted in a dense region, a line segment merging algorithm is used to remove some short line segments, and long line segments with more stable characteristics are obtained by means of merging, thereby reducing the matching complexity; and in an environment where there are more texture lines, a trajectory generated in the present invention can also effectively improve the precision of localization.

The invention relates to the technical field of robot positioning and mapping, and discloses a positioning and mapping method and device and a storage medium. The method comprises the following steps: performing motion distortion correction on point cloud data of a current frame collected by a laser radar to obtain corrected point cloud data of the current frame; constructing a local sub-map of the current frame, calculating a degradation probability of a unit direction vector of the local sub-map, correcting a Hessian matrix of an iterative nearest point algorithm according to the degradation probability, and determining a pose estimation result of the corrected point cloud data relative to the local sub-map according to the corrected Hessian matrix; and fusing the pose estimation result and an IMU predicted value through a Kalman filter, calculating to obtain optimal pose estimation, and inserting the corrected point cloud data into a global map based on the optimal pose estimation. The problems of point cloud distortion and scene degradation in a dynamic scene are solved, and high-precision and robust positioning and mapping are realized.

The invention discloses a positioning optimization method based on fusion of a wheel type odometer and a laser radar in the technical field of robot positioning. The method comprises the following steps: firstly, collecting and processing laser point cloud data; estimating and calculating the initial pose of the robot; carrying out optimization convergence on the pose of the robot; and after the pose optimization convergence of the robot, updating the local map by using the accurate pose at the current moment and the registered point cloud data. According to the method, the wheel type odometer and laser radar data are deeply fused, optimization is carried out in combination with kinematics constraints of the robot, drifting of the wheel type odometer can be effectively corrected, more accurate pose estimation is output, and the precision of the method is superior to that of a single sensor or a traditional fusion method.

Robot localization or mapping can be provided without requiring the expense or complexity an “at-a-distance” sensor, such as a camera, a LIDAR sensor, or the like. Adjacency-derived landmark features can be used and non-unique landmark features can be accommodated. Uncertainty in robot pose can be tracked and compared to an adaptive threshold, and non-dock and dock-based localization behavior can be controlled based on the uncertainty, the adaptive threshold, one or more other thresholds, and the accessibility of available differently oriented landmark features, such as perpendicularly oriented straight wall segments landmark features. Available features can be sorted according to a quality metric, and path planning and navigation techniques are also included for helping obtain successful wall-following and localization observations.

This application provides a robot localization method, a computer program product, and a storage medium. The robot localization method includes: acquiring image data and odometer data of a target cage during robot movement; acquiring coordinate information of feature structures on the target cage from the image data; and determining the robot's localization data based on the coordinate information and the odometer data. This eliminates the need for additional QR code tags, positioning base stations, etc., reducing costs and making the robot less susceptible to interference. Furthermore, by combining the coordinates of feature structures in the image with the odometer data, the robot's position can be comprehensively determined, improving the accuracy of robot localization.

This invention discloses a robot indoor localization method based on acoustic-optical data fusion. The method includes: acquiring a predicted coordinate sequence; obtaining a training dataset and a test dataset based on the predicted coordinate sequence and the true coordinate sequence; constructing a neural network model; training the neural network model using the training dataset to obtain a trained neural network model; inputting newly acquired light source localization data and sound source localization data into the trained neural network model to obtain coordinate prediction values ​​after acoustic-optical data fusion; and performing Kalman filtering on the coordinate prediction values ​​after acoustic-optical data fusion to obtain the final coordinate prediction values. This invention considers the situation where indoor lighting is obstructed, using a sound source localization method based on arrival delay difference as compensation, and utilizing a BP neural network model to achieve the fusion of acoustic and optical methods, thus achieving high-precision indoor power inspection robot localization while ensuring real-time positioning.

This invention belongs to the field of robot localization and relates to an adaptive hierarchical robot localization method and apparatus for degraded scenarios. The method includes: real-time monitoring of the data quality acquired by heterogeneous sensors, mapping the states of the heterogeneous sensors to a unified quantization space, and outputting unique degradation level identifiers D1 to D4; for the D1 environment, uncertainty quantification is performed on feature matching, and the most contributing feature subset is selected; for the D2 environment, the degraded subspace is located through singular value decomposition; for the D3 environment, the expected error of the heterogeneous sensor engine is estimated through a performance prediction network, and continuous confidence weighting is used instead of hard switching; for the D4 environment, a cross-platform generalized pure inertial odometry is provided through a three-level architecture of pre-training-fine-tuning-online adaptation; and historical events are stored as empirical data. This achieves refined differentiation and directional processing of degraded scenarios and constructs an experience-driven closed-loop optimization mechanism.

The invention relates to a robot positioning method and device, a medium, electronic equipment and a program product, and the method comprises the steps: obtaining a first visual image collected by a camera disposed on a robot in response to the repositioning operation of the robot, and determining the visual pose of the robot in a world coordinate system based on the first visual image; the visual pose is verified; and transmitting the visual pose passing the verification to a laser radar positioning system of the robot, and performing repositioning on the robot by taking the visual pose passing the verification as a prior pose through the laser radar positioning system. According to the method, the visual pose determined based on vision is verified, the visual pose passing verification is transmitted to the laser radar positioning system, an initial value is provided for the laser radar positioning system, repositioning of the robot is carried out, and therefore the repositioning accuracy of the robot is improved.

The embodiment of the application provides a kind of indoor-oriented robot positioning method, electronic equipment, positioning system and medium, belong to robot control technical field.The method comprises: obtaining target line drawing track, and its pose data planning is carried out, obtains the target pose data of multiple time steps.Then the distance data between laser range finder and line laying robot and the laser point coordinate matrix of laser point are acquired, and pose data calculation is carried out according to laser point coordinate matrix and distance data, obtains the initial pose data of line laying robot relative to laser range finder at target time step, then according to initial pose data and target pose data of target time step, error calculation is carried out, and motion error data is obtained.Then the control signal generation is carried out to motion error data by preset prediction motion model, and the expected offset signal is obtained.Finally, according to the expected offset signal, line laying robot is moved.The embodiment of the application can realize the accurate line laying in room.

The invention relates to the technical field of computer vision, and provides a synchronous positioning and mapping method for a robot under a corn field canopy, and the method comprises the steps: obtaining and preprocessing an environment image, IMU data and encoder data, and obtaining visual data, inter-frame motion increment and motion data; updating a world coordinate system state value based on the inter-frame motion increment; performing visual SFM processing on the basis of the visual data to obtain an image acquisition posture and a road sign point position; performing visual inertia combination to obtain an InEKF initial state; performing InEKF fusion based on the state value of the world coordinate system, the motion data and the initial state of the InEKF to construct a self-sensing odometer; and performing nonlinear optimization processing based on the visual data, the inter-frame motion increment, the motion data and the self-sensing speedometer to obtain a pose estimation result and a map point cloud. According to the method, feature matching, edge feature supplementation and IMU-encoder sensor fusion technologies are utilized, and high-robustness and high-precision robot positioning and map construction adaptive to the whole corn growth cycle are achieved.

This invention relates to the fields of computer vision and robot localization technology, and provides a method, system, device, and medium for loop closure detection based on a panoramic semantic topology map. The method includes: first, inputting a panoramic image into a semantic segmentation and depth estimation network to obtain a semantic map and a depth map, respectively; removing dynamic objects; and then extracting the centroid coordinates of each static object. The depth value corresponding to each centroid coordinate is calculated based on the depth map, and the three-dimensional spatial coordinates of each static object are obtained through coordinate transformation. When the spatial distance between static objects is less than a threshold, edge connections are established to generate a panoramic semantic topology map. By calculating the similarity between semantic topology maps, it is determined whether the user has returned to a previously visited location, thus completing the loop closure detection task. This method integrates high-level image information such as semantics, depth, and spatial position relationships, reducing perceptual ambiguity and mitigating the impact of changes in viewpoint, lighting, and dynamic objects on loop closure detection.

This invention relates to a robot performance testing method, apparatus, electronic device, and storage medium, belonging to the field of performance testing technology. A robot performance testing method includes: controlling a robot to travel along a reference path based on signal tags; executing a localization algorithm to obtain an estimated pose on a map when the robot reaches a first position, wherein the first position is located on the reference path; mapping the first position to the map to determine the robot's actual pose on the map at the first position; and evaluating the robot's localization performance based on the actual pose and the estimated pose. The robot performance testing method of this invention can be performed on a set reference path, thus controlling the testing process within a reasonable range and improving the efficiency of robot localization performance testing.

This application applies to the field of robotics technology, providing a robot localization method, a robot, and a program product. The method includes: obtaining real-time scene information of the robot based on real-time sensor data currently collected by the robot, wherein the real-time scene information includes real-time visual features and real-time spatial features, and the real-time visual features are semantic embedding vectors aligned to image and text; in the event of robot localization loss, determining multiple similar scene information from historical scene information based on the real-time visual features, each of the historical scene information having a corresponding historical pose; determining multiple candidate poses based on the real-time spatial features and the multiple similar scene information; and obtaining the robot's real-time pose based on the candidate poses and the real-time sensor data. This method enables robot localization recovery and improves robot localization performance.

This invention discloses a visual localization method based on pose space texture continuity mapping, belonging to the fields of robotics and computer vision. In the mapping stage, image intrinsic parameters, pose, and sparse point cloud are first obtained through sparse reconstruction. Image features are extracted using a pre-trained model, and pose encoding and decoding models are trained to ensure consistency between pose encoding and image features in spatial metrics. Simultaneously, the decoding model outputs a multi-peak distribution to model pose ambiguity. Subsequently, a mapping model from image features to pose encoding is trained and optimized end-to-end to construct a scene map. In the localization stage, features of the image to be localized are extracted, pose encoding is obtained through the mapping model, and the pose distribution is output by the decoding model. A unique location or multiple candidate poses are determined based on the number of peaks in the distribution. This invention effectively improves the robustness and accuracy of robot localization in repetitive texture scenes by maintaining the continuity alignment between the pose space and texture space.

This application relates to the field of robot localization technology, and in particular to a multi-sensor fusion method for locating drilling and anchoring robots. The method includes: acquiring point cloud data of an underground roadway within a target time period in a radar coordinate system; acquiring visual images of the underground roadway within the target time period in a camera coordinate system and extracting feature points from the visual images; fusing the feature points at the same time point within the target time period with the point cloud data to obtain target point cloud data; constructing a roadway model based on the target point cloud data; establishing a fuselage observation model based on the feature points; acquiring inertial navigation data of the underground roadway within the target time period in an inertial navigation coordinate system; establishing a fuselage prediction model based on the inertial navigation data; fusing the fuselage observation model and the fuselage prediction model to obtain a target model; and outputting the target pose of the drilling and anchoring robot at each time point within the target time period. This application improves the localization accuracy of drilling and anchoring robots in underground roadways.

The invention discloses a fruit and vegetable picking robot positioning detection device based on a boundary attention mechanism, and relates to the technical field of picking robot detection, the fruit and vegetable picking robot positioning detection device comprises a base, a direction detection mechanism, an angle detection mechanism and a displacement detection mechanism; the robot has the advantages of being reasonable and simple in structure, low in production cost and convenient to install, the direction detection mechanism can accurately detect direction changes caused by movement of the robot, all the components work cooperatively, the rotating base rotates flexibly, and the movement direction of the robot each time can be determined; the angle detection mechanism can detect the angle change caused by the movement of the robot, and the detection effects under different conditions can be met by loosening or tightening a locking screw; the displacement detection mechanism can detect the distance change caused by the movement of the robot, the universal clamped head can rotate, it is guaranteed that the movement change of the robot does not affect the device, and the clamping block and the spring structure guarantee that the clamping block does not move freely after the robot is loosened.

The invention relates to the technical field of map data, and discloses a degradation compensation-based multi-robot positioning mapping method and system, a terminal and a storage medium, and the method comprises the steps: carrying out the feature extraction of a tunnel environment through employing a main robot and a beacon robot through employing a leapfrog strategy, and if the feature collected by the main robot is judged to have a degradation condition, carrying out the positioning mapping of the main robot; and if not, performing fusion processing by using the highly locatable points acquired by the beacon robot to restrain error accumulation of the main robot so as to optimize the degraded tunnel map. According to the method, the positioning accuracy of the longitudinal translation dimension of the tunnel is improved, decimeter-level accurate positioning is realized, and the mapping robustness and the accuracy of the generated image are improved.

The invention provides an indoor robot positioning method based on multi-description coding-decoding, and the technical key points are as follows: the method comprises the following steps: building a kinematic model of an indoor robot and a measurement model of a sensor, and building a mathematical model; constructing a state estimator of the indoor robot; and solving the upper bound of the covariance of the positioning error, and optimally designing parameters of an estimator to minimize the upper bound of the covariance of the positioning error, thereby realizing accurate positioning of the indoor robot. According to the method, the transmission opportunity of sensor data is actively adjusted through a token bucket communication protocol, burst flow is effectively inhibited, instantaneous overload of a channel is avoided, and efficient and smooth utilization of communication resources is realized; measurement information of each time is divided into two independent descriptions by adopting a multi-description coding-decoding scheme, and the two independent descriptions are transmitted in parallel through two independent communication links, so that even if partial descriptions are lost due to insufficient tokens or poor channels, a decoder can still perform effective reconstruction based on a single description, and the fault tolerance of an indoor robot positioning system is improved.

This invention relates to the field of robotics, disclosing a robot localization method, a robot path planning method, an apparatus, and a robot. The localization method includes: acquiring first localization data of the robot in physical space; determining second localization data of the robot in a virtual space constructed in real time based on the surrounding environment (3D panoramic imaging); and correcting the first localization data based on the second localization data to obtain target localization data of the robot in physical space. This application introduces second localization data in a 3D panoramic imaging virtual space constructed in real time based on the surrounding environment. The 3D panoramic imaging virtual space can reflect environmental changes in real time, and the second localization data can capture these dynamic information in a timely manner, correcting the first localization data, enabling the robot to accurately adapt to environmental changes and improving the accuracy and stability of localization.

This invention discloses a robust and interference-resistant 3D point cloud localization method and system, belonging to the field of robot navigation technology. The method includes: projecting the original point cloud of a 3D LiDAR onto a virtual horizontal coordinate system using attitude data from an inertial measurement unit (IMU) to eliminate the influence of uneven road surfaces; adaptively selecting and fusing the results of the LiDAR and wheel speed measurement units based on the data quality of the pose estimation units such as wheel speedometers to generate reliable pose priors; and performing high-precision pose optimization using the geometric information contained in the local normal vectors during point cloud matching. This invention also includes a fast relocalization mechanism. This invention can significantly improve the robustness and accuracy of robot localization in complex environments, ensuring continuous and safe operation, and is mainly used in autonomous mobile platforms such as wheeled inspection robots.

Systems and methods are described for instructing performance of a localization and an action by a mobile robot based on composite data. A system may obtain satellite-based position data and one or more of odometry data or point cloud data. The system may generate composite data by merging the satellite-based position data and the one or more of the odometry data or the point cloud data. The system may instruct performance of a localization by the mobile robot based on the composite data. Based on the localization by the mobile robot, the system may identify an action and instruct performance of the action by a mobile robot.

The invention relates to a robot positioning and mapping method based on an improved octree structure. The robot positioning and mapping method comprises the steps that residual errors of the posture, the speed and the pose of a robot are obtained through IMU pre-integration; performing loopback candidate frame retrieval by improving an octree structure; a transformation matrix between loopback frames is calculated through a registration method combining coarse registration based on a random sampling consensus algorithm and fine registration based on an iterative nearest point algorithm, and loopback detection factors are obtained; and introducing the odometer factor, the IMU pre-integration factor and the loopback detection factor into a factor graph optimization model to solve the pose. According to the invention, the decision-making speed and the operation precision of the system under complex working conditions can be greatly improved through the efficient data processing capability, and key technical support is provided for digital transformation of the power industry; and the processing efficiency and the modeling precision of the point cloud data in the synchronous positioning and mapping algorithm process of the robot in the complex electrified environment can be remarkably improved.

This application proposes a robot localization method, electronic device, and computer storage medium. The method includes: acquiring motion state data of the robot in its body coordinate system, wherein the motion state data includes inertial velocity parameters and encoder velocity parameters; acquiring the robot's attitude information based on the motion state data, and performing calculations based on the attitude information and the inertial velocity parameters to obtain first calculated data; calculating the encoder velocity parameters to obtain second calculated data; acquiring the robot's slippage condition based on the first and second calculated data; and acquiring the robot's localization result based on the slippage condition using the first and second calculated data. By using the first and second calculated data to localize the robot, the impact of robot slippage abnormalities on localization accuracy is reduced, improving the accuracy and robustness of robot navigation and localization.

This invention provides a SLAM construction method and system based on RGB-D semantic segmentation, belonging to the field of robot localization and navigation technology. The method includes: constructing an RGB-D-based SLAM system framework; training an RGB-D semantic segmentation model based on Transformer-based dual-branch multi-level attention fusion within the SLAM system framework to obtain an initial semantic segmentation model; and pre-training the initial semantic segmentation model using a depth noise decoder to obtain a SLAM semantic segmentation model. This invention combines RGB-D images and a depth completion algorithm in a visual SLAM system, and by introducing an RGB-D semantic segmentation model, ensures the robustness of the acquired semantic information under poor imaging conditions.

Robot localization or mapping can be provided without requiring the expense or complexity an “at-a-distance” sensor, such as a camera, a LIDAR sensor, or the like. Adjacency-derived landmark features can be used and non-unique landmark features can be accommodated. Uncertainty in robot pose can be tracked and compared to an adaptive threshold, and non-dock and dock-based localization behavior can be controlled based on the uncertainty, the adaptive threshold, one or more other thresholds, and the accessibility of available differently oriented landmark features, such as perpendicularly oriented straight wall segments landmark features. Available features can be sorted according to a quality metric, and path planning and navigation techniques are also included for helping obtain successful wall-following and localization observations.

The invention discloses a power distribution room multi-mode sensing inspection robot based on visual navigation. The robot comprises a mobile platform; the visual navigation module is arranged on the mobile platform and is used for collecting environmental vision and distance information of the power distribution room and realizing robot positioning and autonomous path planning; the multi-mode sensing module is arranged on the mobile platform and is used for synchronously acquiring the equipment state and environment multi-dimensional data of the power distribution room; and the control module is electrically connected with the mobile platform, the visual navigation module and the multi-mode sensing module, and is used for receiving the positioning path information and the sensing data and controlling the movement of the mobile platform. The method has the beneficial effects that a visual navigation scheme of fusing the binocular camera and the laser radar is adopted; the multi-modal sensing module integrates infrared, sound, gas, temperature and humidity sensing units and other multi-dimensional sensing units, so that the omnibearing detection of the equipment state and the environment is realized, and the fault missing detection caused by a single sensing mode is avoided; the crawler-type moving mechanism is matched with a damping assembly.

The invention discloses a quadruped robot positioning and mapping method and device in a complex terrain environment, a terminal and a medium, and the method comprises the steps: obtaining a laser radar point cloud, inertial measurement data and leg motor data of a quadruped robot, constructing a state estimation observation model of the quadruped robot, and achieving the estimation of the motion state of the quadruped robot, obtaining a state estimation result; performing point cloud motion compensation based on a state estimation result, realizing point cloud registration and point cloud state estimation based on the state estimation result, the compensated laser radar point cloud and a global map of an adaptive voxel structure, and outputting a three-dimensional voxel map; and on the basis of a plane constraint foot end updating mechanism of confidence perception, a three-dimensional voxel map is used as a constraint to update a foot end elevation so as to optimize a subsequent state estimation process of the quadruped robot. According to the method, the problems of positioning drift, matching loss, fuzzy mapping, registration failure and the like caused by the flexible motion state of the quadruped robot under the complex terrain can be effectively solved.

This application discloses a dynamic feature discrimination method and system based on graph neural networks, belonging to the field of robot localization and mapping algorithms. The method includes: acquiring image sequences and motion data; detecting feature points and extracting multi-dimensional feature information; constructing standardized multimodal feature vectors for the feature points; calculating the comprehensive similarity between feature points and constructing an adjacency matrix through adaptive threshold filtering; using the multimodal feature vectors as node feature matrices and the adjacency matrix as edge relationship descriptions, inputting them into a trained graph autoencoder to obtain latent embedding representations; performing cluster analysis on the latent embedding representations, and completing the discrimination of feature points by calculating the comprehensive score of each cluster; outputting the discrimination results as dynamic / static labels, which are integrated with a SLAM system via a standard interface; significantly improving the accuracy and efficiency of dynamic feature recognition, and also possessing good generalization, adaptability, and system compatibility.

This invention discloses a high-precision localization path planning system for a road cone robot based on deep learning, comprising: a visual acquisition and preprocessing module for acquiring and preprocessing road scene data; a visual semantic recognition module for generating a set of scene semantic information; a multi-source localization fusion module for obtaining a sequence of robot localization results; a semantic map construction module for generating a road semantic map; a spatiotemporal energy constraint construction module for constructing a spatiotemporal energy constraint field based on the road semantic map; an energy-optimized path planning module for generating path planning results; a dynamic path correction module for correcting the path planning results; and a trajectory tracking control module for driving the road cone robot to run along a dynamic path. This invention employs deep learning and spatiotemporal energy optimization methods to achieve dynamic path planning for the road cone robot, possessing advantages such as high localization accuracy, intelligent obstacle avoidance, and strong adaptability.

This invention relates to a fire source localization method for a warehouse fire inspection robot, belonging to the field of fire robot localization technology. It includes the following steps: the warehouse fire inspection robot collects temperature field data and infrared light source signals to locate the fire source area; it activates the GNSS navigation module to obtain the robot's three-dimensional geographic coordinates; it controls a laser rangefinder to align with the center of the fire source and calculates the robot's horizontal rotation and elevation angles; it measures the straight-line distance between the robot and the fire source using the laser rangefinder; it establishes a three-dimensional Cartesian GNSS rectangular coordinate system and a three-dimensional Cartesian laser rectangular coordinate system; it converts the relative coordinates of the fire source in the laser rectangular coordinate system to absolute coordinates in the GNSS rectangular coordinate system; it optimizes the absolute coordinates of the fire source using Kalman filtering to obtain the final absolute coordinates of the fire source; and it feeds back the final absolute coordinates of the fire source to a cloud server, triggering an alarm device and outputting the localization result. This invention can improve the stability and accuracy of fire source localization.