22 results about "Planetary surface" patented technology

The invention discloses a cross-scale planet impact crater detection method and system, and belongs to the technical field of remote sensing image intelligent identification. The method comprises the following steps: collecting and preprocessing a planet surface remote sensing image, and constructing an impact crater detection data set; a Transform-based detection model is constructed, the model comprises a multi-scale attention gating fusion feature extraction backbone module, a small target feature enhancement pyramid module and a target detection module, and the detection capability of the small-size impact crater is improved through multi-scale feature fusion and detail enhancement; pre-training the model by using the universal target detection data, and performing fine tuning optimization on the impact crater data; and finally deploying the model to an edge computing device or a remote sensing terminal to realize real-time detection. The method solves the problem of insufficient precision in cross-scale and weak texture impact crater detection of a traditional method, has the advantages of end-to-end and no need of post-processing, and is suitable for automatic image analysis of planet surfaces such as the moon and the Mars.

1. Name of the product in this design: Robot (Wide-area closed-chain five-link double-wheel leg). 2. Purpose of this design: As a space exploration device, it is used for the transportation and delivery of materials on the planetary surface, as well as for cleaning solar panels and equipment maintenance. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.

This invention relates to the field of anchoring technology and discloses a rope-driven, plant root sheath-inspired anchoring mechanism, comprising: a hollow anchoring drill bit; and a root sheath anchoring assembly disposed inside the anchoring drill bit. The root sheath anchoring assembly includes two flexible drill rods, one end of which extends to the outside of the anchoring drill bit for reinforcing the anchoring drill bit's anchoring to the planetary surface. This rope-driven, plant root sheath-inspired anchoring mechanism, by drawing inspiration from the structural characteristics of plant root sheaths, uses flexible drill rods as anchoring components. When extended, these rods can penetrate deep into the planetary surface like plant roots. Furthermore, the barbs on the drill rod surface pop out and unfold after extension, further enhancing the anchoring force. The biomimetic design allows it to better adapt to the complex terrain and geological conditions of the asteroid surface, improving the stability and reliability of the anchoring and effectively solving the problem of weak anchoring that often occurs with traditional anchoring devices on asteroid surfaces.

The invention discloses a planetary surface typical target high-precision positioning identification system and method, and the method comprises the steps: a data enhancement module receives hyperspectral data, carries out the data enhancement of the hyperspectral data, and builds a contrast learning frame based on an enhanced sample; extracting a background sample and a prior sample in the hyperspectral data, enhancing the sample and extracting a space-spectrum combined feature, combining the space-spectrum combined feature with a contrast learning framework to calculate a contrast loss, and performing sample reconstruction on the background sample; the weight reconstruction module calculates a reconstruction error of an original hyperspectrum and a prior sample, calculates a deviation vector according to the reconstruction error, converts the deviation vector into a reconstruction weight, and dynamically adjusts the comparison loss by using the reconstruction weight; the system trained by the modules performs feature extraction and calculates feature similarity to generate a target detection image; according to the method, high-precision and robust typical target positioning and recognition can be realized in a planetary surface environment which is lack of labeled samples and has spectral change.

The invention relates to the field of deep space exploration and planet surface scientific research, in particular to a planet surface scientific interest target intelligent sampling method and system. The method comprises the following steps: step 1, acquiring a visible light image of a planet surface by an inspector end, autonomously identifying a potential scientific interest target through a target detection model, determining a spatial position, acquiring spectral data of a target area, and inputting the spectral data into a spectral classification model for identification; if the confidence coefficient is lower than a preset threshold value, executing the step 2, otherwise, outputting a category label and executing the step 3; 2, marking a low-confidence target as a potential new category target, transmitting the image, spectrum and spatial position information of the target to a ground center, obtaining a classification result through manual marking, carrying out incremental learning training on a spectrum classification model, realizing adaptive optimization and new and old category compatible identification, and redeploying the target to a patroller end after updating; and step 3, according to the target classification result and the spatial position information, controlling an inspector to complete scientific interest target sampling operation.

The application discloses a kind of planet laser spectroscopy acquisition device and method combined with remote ultraviolet Raman-fluorescence technology, and it is related to deep space exploration spectral measurement technical field.The device includes ultraviolet laser emission unit, beam expander unit, dichroic beam splitter, cassegrain telescope unit, signal separation and acquisition unit, Raman spectrometer, fluorescence spectrometer and computer control unit.Laser is projected to remote target by cassegrain telescope after beam expansion and dichroic beam splitter, and the Raman and fluorescence signals excited are received by the same telescope, then after filtering out Rayleigh scattering light, they are collected by optical fiber into corresponding spectrometer.The application can realize the integrated collection of ultraviolet Raman and fluorescence spectrum of remote, non-contact planetary surface material, and provide efficient optical detection means for mineral composition identification, organic matter and potential life marker detection.

The application relates to a kind of asteroid surface escape velocity calculation method considering rotation and terrain influence, comprising: obtaining the three-dimensional shape model of target asteroid and carrying out discrete, reading the vertex set and triangular facet set of polyhedron, carrying out gravity field modeling, establishing standard polyhedral gravity model;Define the logarithmic kernel function of each edge of each triangular facet, to determine the gravitational potential of target asteroid on any field point;Establish star-fixed coordinate system in standard polyhedral gravity model, determine the rotation speed of any point on the surface of target asteroid, thereby define the effective potential upper bound and the inertial system speed of the release instant of the particle on the surface of target asteroid;Based on the minimum escape condition that the kinetic energy of the particle on the surface of target asteroid is equal to the corresponding effective potential upper bound, determine the minimum normal escape velocity of the particle. Compared with the prior art, the application can quickly obtain accurate minimum escape velocity and corresponding escape direction at any surface point.

This invention discloses an unsupervised method for detecting planetary changes, belonging to the field of remote sensing image processing technology, and includes the following steps: S1, acquiring two planetary remote sensing images at different time phases, namely, planetary surface image X at time T1. i Planetary surface image at time T2 Y i The images are preprocessed to obtain preprocessed images. A pre-trained VGG-19 network and a Convolutional Block Attention (CBAM) module are used to extract deep features from the preprocessed images. Global max pooling is then used to obtain patch-level features of the two-phase planetary images. Further analysis of the differences in deep features between the two-phase images is then performed to determine whether changes have occurred. The planetary change detection method provided by this invention not only has high accuracy but also requires few parameters and has low computational complexity. It has high practical application value on different planetary datasets and can be further studied using unsupervised learning on different datasets in the future.

The disclosed embodiments describe an integrated aerial exploration system for deployment on a planetary surface, the system including: a rotorcraft configured for flight in a low-density atmosphere and adapted to carry a scientific payload; an enclosure housing the rotorcraft during launch, transit, and landing, the enclosure including a mounting interface for attachment to a host vehicle and a cover movable to provide an opening for deployment of the rotorcraft; and a deployment mechanism configured, upon activation, to move the rotorcraft from within the enclosure to a position outside the enclosure through said opening; where activation of the deployment mechanism automatically releases the rotorcraft from the enclosure and deploys one or more stowed components of the rotorcraft into a flight-ready configuration for aerial operation.

The application relates to the field of deep space exploration and planetary surface scientific research, in particular to a planetary surface scientific interest target intelligent sampling method and system. The method comprises the following steps: step 1: a rover end acquires a planetary surface visible light image, autonomously identifies a potential scientific interest target through a target detection model and determines a spatial position, inputs spectral data of a target region into a spectral classification model for identification, executes step 2 when a confidence degree is lower than a preset threshold, otherwise, outputs a category label and executes step 3; step 2: a low-confidence-degree target is marked as a potential new category target, image, spectral and spatial position information of the target are transmitted to a ground center, a classification result is obtained through manual marking, an incremental learning training is conducted on the spectral classification model, adaptive optimization and new and old category compatible identification are realized, and the updated model is redeployed to the rover end; and step 3: according to the target classification result and the spatial position information, the rover is controlled to complete scientific interest target sampling operation.

The application discloses a three-dimensional point cloud terrain segmentation method for unstructured planetary surface, and belongs to the technical field of deep space exploration and mobile robot autonomous navigation. The method comprises the following steps: performing abnormal point and negative obstacle sensitive preprocessing on the obtained original point cloud; performing grid division on the effective point cloud, decoupling the slope and roughness features of the terrain based on principal component analysis; processing sparse data through adaptive density checking, and performing initial classification on the grid according to geometric features; performing double-mode elevation updating, performing time sequence probability fusion on the candidate ground area, and introducing a forced downward correction strategy for the candidate obstacle area to correct under-segmentation; performing space-time joint interpolation on the hollow area and the sparse area to generate a complete terrain, and outputting a semantic segmentation result in combination with multi-dimensional features. The application is especially suitable for the environment perception of a planetary surface exploration vehicle on the moon, Mars and other planets, and effectively improves the precision of environment perception and the safety of navigation under rugged terrain.

This invention discloses a system and method for spectral recognition of targets of interest on planetary surfaces, specifically including: data preprocessing, acquiring hyperspectral images, and performing meta-task partitioning on the hyperspectral images to obtain a multi-category sample set; receiving the sample set, extracting kernel attention features and kernel dispersion features through bi-branch feature extraction, respectively, and applying consistency constraints to obtain sample features; using the sample features to obtain prototype vectors for each category, constructing a graph structure with prototype vectors as nodes and sample features as associated nodes, and aggregating semantic and geometric information; using a gradient-aware metric function to calculate the gradient information between each sample feature and the corresponding category prototype vector, constructing a gradient force field, and adaptively adjusting the distance relationship between the sample and the prototype based on the gradient information; this invention can achieve highly accurate spectral intelligent recognition of targets of interest on planetary surfaces in environments lacking a large number of labeled samples and in harsh planetary surface environments.

A planetary surface rover is provided with a variable speed transmission dedicated to each wheel drive such that it can switch its gear reduction ratio either manually or automatically using a gear selection mechanism that may switch between different strain-wave gearing sets, epicyclic gearing sets, cycloidal gearing sets, standard gear train sets, or between each of the different gear sets described. A cable deployment system for a planetary surface rover is also provided which can load a cable spool and then replace a cable spool once the cable has been fully deployed, as well as feed the cable into its own dedicated deployment system which can ultimately then feed the cable along the surface of the celestial body that the rover has been deployed to as it traverses various terrains. These cables may be used for power infrastructure on the Moon or Mars to connect solar panel arrays with charging stations and other applications such as fixed building structures.

The invention discloses a spectrum identification system and method for a target of interest on a planet surface, and the method specifically comprises the steps: preprocessing data, collecting a hyperspectral image, carrying out the meta-task division of the hyperspectral image, and obtaining a multi-class sample set; receiving the sample set, respectively extracting kernel attention class features and kernel dispersion features through double-branch feature extraction to carry out consistency constraint, and obtaining sample features; obtaining a prototype vector of each category by using the sample features, constructing a graph structure by taking the prototype vectors as nodes and the sample features as associated nodes, and aggregating semantic information and geometric information; calculating gradient information between each sample feature and the prototype vector of the corresponding category according to a gradient perception measurement function, constructing a gradient force field, and adaptively adjusting a distance relationship between the sample and the prototype according to the gradient information; according to the method, high-accuracy intelligent spectrum identification of the target of interest on the planetary surface can be realized in the environment of lack of a large number of labeled samples and a severe planetary surface.

The invention discloses a planetary polar region air cushion patrol robot based on in-situ solid gas sublimation driving, belongs to the technical field of deep space exploration and specialized robots, and is suitable for low-energy-consumption and long-period patrol of the surfaces of solid volatile substances such as Mars polar crowns and Mu ice satellites. The robot comprises a sublimation heating chassis used for heating solid volatile substances to generate sublimation gas; the flexible sealing skirt edge on the periphery of the chassis and the planet surface are enclosed to form a semi-closed gas collection cavity for accumulating gas; a flow guide channel, an air injection nozzle array and a valve control assembly are arranged on the periphery of the air collection cavity, so that accurate regulation and control of air flow and injection are achieved; the posture and propulsion control module is used for jointly adjusting the heating power and the valve control opening degree, dynamically balancing the pressure of a gas collection cavity and controlling the thrust; and the energy and heat management system directionally conducts heat of the heat source to the heating chassis. Controllable suspension gas film pressure is formed through in-situ sublimation gas, thrust is generated through a nozzle, and suspension movement and posture control of the robot on the target surface are achieved.

The application relates to a fixed time guidance method of a tethered lander powered descent phase, and a processing and storage device, which first establishes a dynamics model of the tethered lander powered descent phase; on the basis, a non-singular terminal sliding mode surface is designed; in order to eliminate the influence of unknown interference, an adaptive law is designed, and accurate guidance under external interference is realized; in addition, in order to avoid the collision between the lander and the planet surface, i.e. realize soft landing, a synchronous time convergence method is adopted. The application combines the sliding mode control, the adaptive technology and the synchronous time convergence method, not only guarantees the accurate guidance under interference, but also avoids the collision of the lander, and realizes the fixed time soft landing effect on the planet surface.

This invention discloses a multi-spacecraft spherical path planning method based on an improved Sequoia algorithm, belonging to the field of spacecraft intelligent control and trajectory planning. Based on the Sequoia ecological algorithm, this invention introduces three enhancement mechanisms: an adaptive multi-parameter self-adjustment mechanism, an elite fire response strategy, and a directional local search with orthogonal exploration, to construct an improved Sequoia algorithm. The method establishes a spherical multi-spacecraft path planning model, comprehensively considering multi-objective fitness functions such as static no-fly zone avoidance, dynamic obstacle avoidance, safe distance between spacecraft, and spherical constraints. The improved Sequoia algorithm iteratively optimizes the cooperative flight trajectory of multiple spacecraft, ultimately outputting smooth, collision-free spherical flight trajectories for multiple spacecraft. This invention demonstrates superior convergence accuracy and robustness in multi-scenario spherical path planning simulations, and is suitable for aerospace applications such as planetary surface exploration and satellite orbit optimization.

The application discloses a kind of deep learning three-dimensional sparse reconstruction method and system suitable for planetary exploration vehicle image, comprising: step one, import preprocessed planetary exploration vehicle image and other auxiliary data;Step two, the key point extraction and description of each image imported are carried out, obtain the key point set containing the two-dimensional image coordinates of key point on each image and corresponding descriptor;Step three, the key point is matched, and the same name point is extracted in the image with each other overlapping, and the same name point of error is eliminated while more correct same name point is matched;Step four, using the coordinates of key point and the corresponding relationship of same name point obtained by matching, the accurate object side three-dimensional point coordinates and the position and posture of camera are solved, and then the three-dimensional structure of terrain is recovered.The application combines deep neural network technology to carry out accurate and reliable same name point extraction for sparse three-dimensional reconstruction, which can significantly improve the stability of planetary surface three-dimensional reconstruction.

The application discloses a visual guidance detection method for a planetary surface rover, and solves the problem of low detection efficiency caused by the fact that the aiming of a target to be detected is realized through manual point selection and instruction interaction when an extraterrestrial object is landed and patrolled. The application realizes a complete closed-loop automatic process from target identification, evaluation, coarse adjustment to fine adjustment through visual guidance, replaces the traditional manual point selection and instruction interaction mode, greatly reduces ground intervention, and significantly improves the real-time performance and efficiency of planetary patrol detection.

The invention provides a dynamic modeling method for a multistage energy absorption buffer system of a spacecraft, relates to interstellar detection or multiplex take-off of the spacecraft landing on a planet surface, and belongs to the technical field of spacecraft rod piece framework type landing buffer. According to the method, a spacecraft rod piece framework type landing buffer system is taken as a research object, and the efficiency of a dynamic model is effectively improved on the premise of ensuring the precision of an analysis result by performing fitting equivalent processing on a multi-stage buffer energy absorption system based on a series-parallel connection structure by combining a test and a mathematical model. The method can be widely applied to dynamic modeling analysis and parameter evaluation of the spacecraft rod piece framework type multi-stage buffering energy absorption system, and design and development of the rod piece framework type multi-stage buffering energy absorption system are effectively guided.

The disclosed embodiments describe an integrated aerial exploration system for deployment on a planetary surface, the system including: a rotorcraft (110) configured for flight in a low-density atmosphere and adapted to carry a scientific payload (119); an enclosure (150) housing the rotorcraft during launch, transit, and landing, the enclosure including a mounting interface (154) for attachment to a host vehicle and a cover (152) movable to provide an opening for deployment of the rotorcraft; and a deployment mechanism (160) configured, upon activation, to move the rotorcraft from within the enclosure to a position outside the enclosure through said opening; where activation of the deployment mechanism automatically releases the rotorcraft from the enclosure and deploys one or more stowed components of the rotorcraft into a flight-ready configuration for aerial operation.

1. Name of the product in this design: Model (Planet Rover). 2. Purpose of this design: This design is intended to carry various scientific instruments to conduct planetary surface exploration and complete scientific exploration of planetary surfaces. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.