203 results about "Safe path" patented technology

The invention provides an autonomous navigation path planning method, device and equipment for a humanoid robot in a complex environment. A navigation task is determined by obtaining the current position and path requirement of the robot; constructing a constraint preposition map based on body size constraint, joint motion constraint and dynamic balance constraint, and calculating a feasible motion space of the robot in advance; acquiring environment sensing data for variation trend analysis, and predicting a future movement track of the dynamic obstacle to generate a dynamic environment prediction sequence; establishing a bidirectional planning mechanism, performing forward and reverse path search at the same time, and generating a plurality of candidate path hypotheses through meeting point detection and path fusion; analyzing a human behavior pattern to identify a potential passage conflict area, establishing a social negotiation strategy, and taking an intermediate meeting point as a social key node to adaptively adjust a candidate path; the optimal safety path is determined through multi-dimensional safety evaluation of the falling risk, the collision risk and the energy consumption risk, and intelligent autonomous navigation of the humanoid robot in a complex environment is achieved.

The invention discloses a multi-unmanned aerial vehicle formation efficient cooperative control method, and belongs to the field of unmanned aerial vehicles. According to the method, through cooperation of the generator and the discriminator, a multi-level reward function is designed and dynamically adjusted by using diversified scenes and fault model training strategies in the digital twin model, so that complex tasks and scenes can be better coped with, and the cooperation efficiency is comprehensively improved. When a complex search rescue task is executed, search areas and tasks can be distributed more reasonably, and the rescue efficiency is improved. The state of the unmanned aerial vehicle is simulated and predicted by means of digital twin dynamics, errors are corrected, a real-time closed-loop optimization mechanism can rapidly re-plan a path when flight is abnormal, and the difference between virtual data and reality data is reduced through a domain self-adaptive module. When a new obstacle is encountered, the technical scheme of the invention can re-plan a safe path, and at the same time, through collaborative planning and obstacle avoidance of multi-technology fusion, the safety and reliability of unmanned aerial vehicle formation collaborative flight are improved.

The invention relates to a dynamic planning method, device and equipment for a low-altitude route of an unmanned aerial vehicle and a medium. The method comprises the following steps: acquiring real-time dynamic environment change data and obstacle distribution information of a low-altitude flight area, constructing a preliminary data set, and generating an initial flight path; according to the initial flight path, predicting energy consumption data, and if the energy consumption data exceeds a threshold value, performing optimization to obtain an optimized path; performing risk assessment quantification, combining a safety margin adjustment mechanism to obtain a safety index, and if the safety index is lower than a threshold value, performing safety distance adjustment to generate a safety path; monitoring flight conditions, generating a condition monitoring update report, acquiring new obstacle position information, and generating a dynamic obstacle avoidance path; and generating an execution instruction set of the unmanned aerial vehicle according to the dynamic obstacle avoidance path. By adopting the method, the dynamic environment real-time adaptability of the unmanned aerial vehicle can be improved, and the route meeting the task requirement can be planned in time when the unmanned aerial vehicle faces sudden obstacles or environment changes.

The invention relates to the technical field of mechanical arm obstacle avoidance path planning, in particular to a multi-degree-of-freedom mechanical arm obstacle avoidance path planning method based on three-dimensional reconstruction, which comprises the following steps: step 1, three-dimensional environment perception and dynamic modeling; preferentially offsetting and expanding the near-obstacle nodes towards the concave area or the hole center to generate a candidate node set; and 4, three-dimensional grid collision verification and safe path correction are conducted, specifically, the working space of the mechanical arm is divided into three-dimensional voxel grids, and collision detection is achieved by judging whether path nodes fall into obstacle object elements or not. According to the method, the laser radar and the depth camera are adopted to synchronously collect data through hardware triggering, statistical filtering denoising and three-dimensional grid modeling are combined, geometrical characteristics of static obstacles and motion parameters of dynamic obstacles are restored, and the collision risk caused by environmental perception errors of the mechanical arm is effectively avoided.

The invention relates to the technical field of machine vision and perception, in particular to a ton bag lifting unmanned control system based on a binocular vision camera and a laser radar, which comprises an intelligent control unit, a lifting appliance executing mechanism, a sensing unit and a special ton bag, the sensing unit comprises a binocular vision camera and a laser radar and is used for collecting depth vision and three-dimensional point cloud information of an operation area; the intelligent control unit fuses multi-source data, locates a lifting lug by improving a weighted multi-feature fusion algorithm, plans a safety path and generates a staged instruction; the lifting appliance executing mechanism lifts and pulls a collapsed lifting lug through an electromagnetic adsorption module, a mechanical gripper module clamps the lifting lug, and reliable operation is achieved in cooperation with a verification mechanism; the special ton bag is matched with a sensing and executing module through a high-contrast color and a pre-embedded metal piece. The full-process unmanned operation is achieved, the robustness and operation safety of the complex environment are improved, and the ton bag hoisting requirements of multiple industries are met.

The invention relates to the technical field of path planning, and discloses a path planning method and system of an AGV (Automatic Guided Vehicle) for a silver electrolysis process workshop. The method comprises the following steps: carrying out environment characteristic acquisition and electronic map construction on a silver electrolysis process workshop to obtain a silver electrolysis process workshop electronic map; calculating an initial optimal path of the AGV from the current position to the target workstation; detecting the actual driving resistance in the execution process of the initial optimal path to obtain a path correction parameter; performing local adjustment to obtain an energy-saving safe path; and in the process that the AGV executes the energy-saving safe path, the front moving obstacle and the electrolyte leakage area are monitored in real time, and a temporary detour path is generated. According to the application, the path planning is more suitable for the actual environment characteristics of the silver electrolysis workshop, the emergency situation of the silver electrolysis workshop can be timely handled, the equipment safety and the production continuity are guaranteed, the no-load rate of the AGV is reduced, and the overall logistics efficiency of the silver electrolysis workshop is improved.

The invention discloses an automatic driving vehicle environment sensing system based on deep learning, relates to the technical field of artificial intelligence, and solves the problem that it is difficult to identify a driving scene and a road type where a current vehicle is located. The scene migration probability in the future 3 seconds is difficult to predict, and whether the driving state of the vehicle on the predicted driving scene migration path is safe or not is predicted; obstacles and lane lines in the road type where the current vehicle is located are difficult to analyze; a movement track of an obstacle is difficult to predict and a driving path is planned; and the risk coefficient of the current vehicle is difficult to comprehensively evaluate. According to the invention, real-time identification of a driving scene and migration prediction in the next three seconds are realized through a deep learning model, a safe path is generated by identifying and positioning an obstacle and a track and applying a path optimization algorithm, and a risk coefficient of a current vehicle is comprehensively evaluated.

The invention discloses an unmanned aerial vehicle adaptive path planning method and system based on double-layer search, and relates to the technical field of unmanned aerial vehicle inspection. At present, the unmanned aerial vehicle is poor in transformer substation inspection safety and autonomy and low in efficiency. The method comprises the steps that the position, type and safety distance data of electrical equipment in a transformer substation are collected in real time through a sensor carried by the unmanned aerial vehicle; dynamically calculating a three-dimensional safety distance between the unmanned aerial vehicle and the equipment according to the type and the position of the equipment in combination with the real-time state information and the environment data of the unmanned aerial vehicle; based on the edge computing nodes, generating an optimal security path by adopting a double-layer path planning algorithm; the planned path is sent to the unmanned aerial vehicle, the flight state is continuously monitored, and if a deviation path or a sudden obstacle is detected, a dynamic path adjustment or hovering instruction is triggered; after the task is completed, flight efficiency and safety indexes are evaluated, algorithm parameters are optimized, and system settings are updated. According to the technical scheme, accurate obstacle avoidance, efficient planning, real-time response and adaptive evolution are realized.

The invention discloses a safety-enhanced trajectory planning method based on an Astar algorithm, and belongs to the technical field of intelligent robot navigation and path planning, and the method comprises the following steps: 1, constructing a grid map, and marking an obstacle region; 2, establishing a security evaluation mechanism, evaluating the surrounding environment of the path node, and quantifying a security index; 3, in a node expansion process, combining a heuristic item and a security index in a cost function to realize priority search for a security region during path selection; 4, key nodes of the obtained initial safety path are extracted based on a Douglas-Peucker algorithm to generate a rectangular safety corridor, and smoothing processing of the initial path is achieved based on a segmented Bezier curve. On the basis of guaranteeing path optimality, safety is used as an auxiliary guiding basis in the path searching process, and the path searching efficiency is improved. Therefore, consideration of the path length and the environmental risk is realized, and the navigation path with higher execution safety is generated.

The invention discloses an end-side safe path planning method based on a small language model, which comprises the following steps: generating a task prompt by fusing the small language model SLM with an A * algorithm and a structured map token, storing the task prompt in a vector database, retrieving historical map information similar to the current task from the database when the path planning task is executed, and performing path planning according to the historical map information. The method comprises the following steps: constructing a COT logic chain prompt, guiding a small language model to gradually generate path key nodes and weights thereof in combination with the constructed COT logic chain prompt, then executing greedy path search by an A * algorithm by taking the key nodes as local targets, and finally generating a safe and efficient path. The method provided by the invention has end-side deployment capability, can be operated in scenes without network, resource limitation and the like, greatly reduces node traversal and improves planning efficiency compared with the existing A * algorithm, is particularly suitable for path planning tasks in a large-scale or high-density obstacle environment, gives consideration to intelligent reasoning and planning safety, and has wide application prospects. The method has good interpretability and expansibility, and has a wide application prospect.

The invention relates to an unmanned aerial vehicle cluster safety path planning reinforcement learning method and device. The method comprises the following steps: inputting unmanned aerial vehicle group states, task targets and environment observation information into a deep reinforcement learning strategy of a continuous action space, and generating a global guidance quantity; an explicit security constraint set between the unmanned aerial vehicles and between the unmanned aerial vehicles and obstacles is constructed, through graph structure modeling and a GNN adaptive mechanism, the unmanned aerial vehicles / obstacles are represented by dynamic graphs, and neighborhood and relative position speed information is utilized to predict CBF parameters; and performing safety projection correction on the guide quantity based on the constraint and the CBF parameter to obtain an actual control instruction corresponding to the safety path. After the instruction is executed, feedback information such as state deviation and constraint tensity is collected and used for adjusting a reinforcement learning strategy, loop iteration is carried out to continuously output an optimization path, and whole-course collision-free planning of the cluster is achieved. By adopting the method, stable and reliable safety protection in a complex dynamic environment can be realized.

The invention relates to the technical field of automatic driving and artificial intelligence, in particular to a driving track planning method based on a visual language model and an intelligent driving system. The trajectory planning method comprises the steps of multi-modal data acquisition and preprocessing, visual language model reasoning, execution control and the like. The intelligent driving system comprises a multi-modal data acquisition and preprocessing module, a visual language model reasoning module and an execution control module. The visual language model reasoning module is integrated with a Patch selection module, a token compression module and a speculation decoding module; according to the invention, an end-to-end driving planning reasoning framework is constructed based on the visual language model, the vehicle trajectory planning is directly generated from the original multi-view perception data and the high-level driving intention by a single model, the architecture of an automatic driving planning system is simplified, and the response speed and robustness are improved. The method can effectively meet the requirement of the automatic driving vehicle for generating the safe path in real time in a vehicle-mounted embedded environment, and has important practical value.

The invention relates to the technical field of unmanned aerial vehicle path planning, in particular to an unmanned aerial vehicle path planning method and system based on laser scanning. The method comprises the following steps: scanning a roadway environment in real time by using a laser scanner to obtain original radial section point cloud data; analyzing a structural stability index and a dangerous rock potential energy threat value based on the original radial section point cloud data to determine a risk attribution area of the current flight path of the unmanned aerial vehicle; judging whether a high-risk detour area exists or not according to the risk attribution area, and if yes, dynamically planning a risk detour path so as to adjust a single pre-scanning voyage and generate an intelligent safety execution route; and instructing the unmanned aerial vehicle to fly to the terminal point along the intelligent safety execution route, and taking the terminal point as the starting point of the next round of path planning until the iterative exploration of the target underground mine space is completed. According to the method, the structural stability and potential energy threat of the surrounding rock are quantified in real time to realize safe path planning for actively avoiding surrounding rock instability.

The invention discloses an intelligent robot navigation system with a body based on a multi-modal large model, and the system comprises an RGB-D camera module which captures a color image and a depth image of an environment in real time, and carries out the preprocessing of the color image and the depth image, and outputs the preprocessed image; the laser radar SLAM module provides a basis for subsequent coordinate calculation and navigation path planning; the multi-modal VLM module is used for calculating the three-dimensional coordinates of the target location in the map; and the navigation control module controls the robot to move. The beneficial effects of the invention lie in that the system realizes efficient environmental perception and natural language understanding through multi-modal fusion, and can accurately identify a target location, calculate a three-dimensional coordinate and plan a safe path, thereby improving the autonomous navigation precision and reliability of the robot, and being suitable for intelligent movement control in a complex scene.

The invention provides a robot safe path planning method and system based on an expansion distance, relates to the technical field of robot path planning, and solves the problem of engineering application limitation caused by too large or too small expansion distance in path planning when a starting point and an ending point are close to an obstacle. According to the method, a new starting point and a new ending point are set near an original starting point and an original ending point respectively, and it is ensured that the new points meet the specific large expansion distance requirement; path planning is carried out based on the newly set starting points and ending points and a large expansion distance constraint condition, so that a collision-free path is obtained; and then, seamlessly connecting paths from the original starting point to the new starting point and from the new starting point to the original ending point through the new ending point to form a collision-free path scheme. According to the method, a feasible path planning solution can be solved when the starting point and the ending point are close to the obstacle, and a relatively large expansion distance can be kept in the middle path section, so that the obtained path is safer.

Data is the “fuel” that powers the machine learning “engine” for Artificial Intelligence. However, identifying high quality data that can catalyze smarter AI, AGI, and SuperIntelligent systems is becoming an increasingly challenging bottleneck for machine learning. This invention not only describes novel methods for identifying the most valuable data, but it also presents an entirely new framework for understanding the information content of AI-relevant datasets. The methods can be used by intelligent systems autonomously or in collaboration with humans. Novel methods for accelerating AI learning, and for updating the knowledge of AI systems in real-time, are also disclosed. Consistent with the view that human survival may depend on the fastest path to AGI also being the safest path, the invention describes catalysts which help maximize alignment between the values of AGI and humans. These innovative catalysts increase not only the intelligence, but also the safety, of AI systems.

The invention relates to the technical field of scheme design of an unmanned aerial vehicle automatic fly-around no-fly zone, in particular to a method and system for an unmanned aerial vehicle to automatically fly around a no-fly zone. The method comprises the following steps: identifying a mountainous area environment based on topographic features (roughness, elevation standard deviation and a continuous climbing section), and constructing a safe path skeleton; generating an initial path by adopting an A * algorithm fused with an energy consumption factor, and optimizing a climbing rate through a dynamic gradient control model (in combination with a real-time pitch angle, a roll angle and a terrain gradient); a Bezier curve is used for achieving track smoothing; and responding to the no-fly zone change based on the local re-planning strategy. By means of terrain feature recognition and dynamic constraint cooperative control, mountain area low-climbing-rate path optimization is achieved. According to the method, the problems of insufficient path physical feasibility, dynamic environment response lag and the like under complex terrains are solved, and the safety and energy efficiency of the unmanned aerial vehicle flying in a no-fly zone and a mountainous area are remarkably improved.

According to the motion planning method and device for the multi-mechanical-arm cooperative task, a large number of potential conflicts are actively avoided in the early stage of task allocation through division of a virtual wall and a safety area and a danger area, the difficulty and the calculated amount of follow-up track collaboration are remarkably reduced, and the success rate and the efficiency of planning are improved. Cost and load balance are considered in the task allocation stage; in the path point sorting stage, minimizing the total movement distance and the total completion time is taken as a target; and track generation adopts a time optimal algorithm. The layered decoupling design avoids the huge calculation overhead of centralized planning, and meanwhile, the quality of a final solution is ensured through the optimization strategy of each stage. The innovative cost function takes collision distance into consideration, and guides the planner to select a safer path. Through layered and ordered collision solution strategies, such as deceleration, local re-planning and optimal waiting, it is ensured that a collision-free solution can be always found in a complex dynamic environment, and robustness is high.

The invention discloses a multi-degree-of-freedom mechanical arm obstacle avoidance path planning method based on industrial vision, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: collecting and preprocessing an initial environment image of a current working scene of a mechanical arm, obtaining a standardized working scene image data set, carrying out dynamic object detection, and obtaining an environment perception evaluation report; identifying an unobserved area of the working scene based on the environment perception evaluation report, performing collision path calculation, and generating a visual angle adjustment action instruction; the safety path sequence is issued to a mechanical arm joint and executed, images in front of the mechanical arm are continuously collected during execution, and if an unpredicted sudden obstacle is detected, the four-dimensional risk map is dynamically updated, and path re-planning is conducted; and when the tail end of the mechanical arm successfully completes the task, obstacle avoidance path planning data of the mechanical arm are recorded and stored persistently, and an obstacle avoidance path planning record is generated. According to the method, the real-time problem of path planning of the mechanical arm is solved through construction of the four-dimensional dynamic risk map.

The invention discloses a breast surgery puncture positioning system, which relates to the technical field of image positioning, and is characterized in that a preoperative medical image and an intraoperative ultrasonic image of a patient are acquired to generate a three-dimensional model, an optimal puncture path is planned by receiving a needle insertion point of a user, and the spatial pose of a puncture needle is tracked; the optimal puncture path and the position and posture of the puncture needle are displayed on the real-time ultrasonic image in an overlapped mode, real-time deviation is calculated, the puncture needle is guided and adjusted to the target focus, and real-time compensation is carried out based on the respiratory signal and / or the displacement of the reference datum. Through the multi-modal image fusion and real-time dynamic tracking technology, the puncture precision and hit rate are remarkably improved, meanwhile, the system intelligently plans a safe path and provides an AR navigation interface, the operation difficulty and dependence on doctor experience are greatly reduced, physiological displacement interference is overcome through respiratory gating and a motion compensation mechanism, and the system has the advantages of being high in accuracy and high in reliability. Accuracy and reliability in the whole operation process are guaranteed, and finally standardized and safe mammary gland puncture diagnosis and treatment operation is achieved.

The invention relates to the technical field of mobile robot autonomous navigation path planning, and discloses a complex orchard scene-oriented hybrid sampling global path planning method, which comprises the steps of adopting a Gaussian hybrid sampling strategy, switching between global uniform sampling and Gaussian offset sampling through a probability threshold, and considering global exploration and key area guidance; a dynamic node expansion strategy is adopted, the expansion step length is adaptively adjusted according to the distance between the expansion step length and a target point, and the expansion direction is optimized by fusing vectors facing a sampling point and the target point and introducing an obstacle influence factor; a layered collision detection strategy is adopted, and step-by-step filtering is carried out through rough detection based on a quadtree, secondary screening based on an axis alignment bounding box and accurate geometric judgment in sequence so as to improve the efficiency; and a dynamic iteration termination mechanism is adopted, and the minimum number of iterations and the path quality convergence state are combined as composite termination conditions. The method can quickly generate a smooth and safe path, and is especially suitable for structured scenes such as orchards.

A deep neural network(s) (DNN) may be used to perform panoptic segmentation by performing pixel-level class and instance segmentation of a scene using a single pass of the DNN. Generally, one or more images and / or other sensor data may be stitched together, stacked, and / or combined, and fed into a DNN that includes a common trunk and several heads that predict different outputs. The DNN may include a class confidence head that predicts a confidence map representing pixels that belong to particular classes, an instance regression head that predicts object instance data for detected objects, an instance clustering head that predicts a confidence map of pixels that belong to particular instances, and / or a depth head that predicts range values. These outputs may be decoded to identify bounding shapes, class labels, instance labels, and / or range values for detected objects, and used to enable safe path planning and control of an autonomous vehicle.

The invention belongs to the field of navigation of an unmanned vehicle in a field unstructured scene, and particularly relates to an unmanned vehicle field scene passable area segmentation and navigation method based on air-ground cooperation, and the method comprises the steps: respectively generating a global point cloud map and a local point cloud map through employing a double-SLAM algorithm; according to the global point cloud map and the local point cloud map, using a CHSM-based passable pavement segmentation method to construct a global passable point cloud map; taking the global passable point cloud map as the input of UGV navigation, and generating a global safe path by adopting a PLA-RRT algorithm; in combination with real-time environment data, using an NMPC algorithm to locally optimize the global security path so as to realize real-time obstacle avoidance and path smoothing, and obtaining a final planning path; and then the motion instruction is transmitted to the controller to guide the UGV to complete navigation. According to the invention, the application limitation of the existing UGV navigation framework in a field unstructured environment is overcome.

The invention discloses an intelligent unmanned aerial vehicle path planning system based on a reverse hyperbolic artificial bee colony algorithm, and aims to solve the problem of unmanned aerial vehicle path planning through an innovative algorithm. According to the system, a terrain environment model is established, and unmanned aerial vehicle path planning is carried out between two demand points needing to be planned. And efficient and safe path planning is realized while the generated path is ensured to comply with the flight limitation of the unmanned aerial vehicle. A preliminary test is carried out on a plurality of terrain models, and a result shows that the system can plan a smoother path with lower flight cost. Under the background of global economic acceleration and unmanned aerial vehicle application rapid growth, unmanned aerial vehicle path planning becomes a key link. The system comprehensively considers the terrain environment, fully searches the feasible space, improves the convergence and diversity of the algorithm, and finally generates a reliable path. Through the intelligent unmanned aerial vehicle path planning system based on the reverse hyperbolic artificial bee colony algorithm, the unmanned aerial vehicle can complete tasks more quickly and efficiently, fuel oil is saved, and overall benefit maximization is achieved.

The invention discloses a multi-AUV safe path planning method based on deep reinforcement learning. According to the method, a deep reinforcement learning algorithm model based on an MATD3 method is adopted, a policy network and a value network are updated by adopting security constraints, the security of policy learning is improved, the expected reward revenue is maximized under the condition that the expected security cost constraints are met, a frequent minimum and maximum optimization process is avoided by adopting first-order penalty optimization, and the security of policy learning is improved. Meanwhile, safety correction based on a safety layer is added in the training process to guarantee safety in the early stage of training, and exploratory and safety balance is brought to strategy optimization of reinforcement learning through safety constraint and safety correction. According to the multi-AUV path planning method, the time cooperation constraint and the space cooperation constraint of multi-AUV path planning are comprehensively considered, the centralized training and decentralized decision-making architecture is applied to multi-AUV path planning, the path planning method capable of ensuring cooperation safety is provided for a multi-AUV system, and the safety and the reliability of path planning are improved.

The invention discloses a fire unmanned aerial vehicle emergency processing path optimization method, and belongs to the field of unmanned aerial vehicle channel control, and the method comprises the steps: building a three-dimensional map, setting a starting point and an ending point of an unmanned aerial vehicle, and obtaining a reference datum line through the starting point and the ending point; adding a fire intensity function formed by the wind speed, the temperature and the smoke concentration on the reference datum line; constructing a constraint function on the reference datum line added with the fire intensity function; key parameter optimization is carried out by using a multi-objective optimization method; and the optimized parameters are substituted into the improved fast random tree model for solving, and a Bezier curve is used for performing path smoothing optimization operation. According to the invention, factors such as the environment when the unmanned aerial vehicle flies are considered when a fire occurs, and the dynamic adaptability and the flight safety of the flight path of the unmanned aerial vehicle are improved; through the improved fast random tree model, efficient, smooth and safe path planning in a complex terrain environment during a fire disaster is realized, and powerful support is provided for an intelligent navigation technology.

The invention provides a robot safety interaction path planning method based on a dynamic danger criterion and bidirectional search, and the method comprises the steps: introducing the dynamic danger criterion in a planning stage, carrying out the quantification of a potential collision risk between a robot and a person, and comprehensively considering the inertia and rigidity of the robot, and the influence of the relative distance between the robot and the person; in combination with forward global search and reverse local search, a safe path is quickly generated in a complex environment. The forward search preferentially reduces danger indexes, the reverse search reversely avoids obstacles from a target position, the path continuity is ensured through an attitude potential energy function, and the local convergence problem of a traditional planning algorithm in an obstacle dense area is solved; the system also combines a real-time monitoring and safety control module, fuses a danger criterion, an obstacle potential field and a target potential field, and supports online path optimization in a dynamic environment so as to ensure that the robot can be always in a safe state in a final interaction process.

The invention discloses a well repair robot control algorithm fusion method, and relates to the field of oil and gas field well repair. Comprising the following steps: collecting a video stream through a high-resolution camera, carrying out target detection and multi-dimensional feature extraction by using an improved YOLOv7 and Res-Net-50 network, and generating an interactive three-dimensional model in combination with a classifier result; fusing the point cloud density and the image texture features, and training a lightweight semantic segmentation model to realize a target object category; selecting an optimal grabbing point and strategy according to categories and features, constructing a working environment map by combining an A * algorithm and multi-sensor data, and planning a safe path; dynamic track adjustment and pose control are realized through coordinate system alignment and real-time pose feedback; and finally, according to the grabbing strategy, all finger joints of the mechanical arm are controlled to grab the target object, the comprehensive index influence score is calculated, whether grabbing needs to be conducted again or not is judged, accurate grabbing of the robot is controlled, and the stability and reliability of the system are improved.

An orchard picking robot path planning algorithm comprises the following steps: (1) constructing a two-dimensional grid map according to an orchard top view or a planning map; (2) classifying obstacle areas and customizing a picking sequence; (3) acquiring a peripheral angular point coordinate set of the picking area; (4) determining a connection point set of adjacent regions; (5) performing regional path planning by using an improved A * algorithm and integrating a preliminary path; (6) optimizing the path through an arc fitting smoothing method; and (7) drawing a final path. According to the method, a complex orchard environment can be effectively modeled and analyzed, regional planning and integration are carried out by means of the improved A * algorithm, and complex conditions of numerous obstacles, irregular layout and the like in an orchard can be handled. And an arc fitting smoothing method in path optimization processing further improves the performability and smoothness of the path in a complex environment. The method can adapt to a complex orchard environment, and provides efficient and safe path planning for the picking robot.

The invention relates to the technical field of intelligent control of fire-fighting robots, and discloses a fire-fighting robot capable of autonomously moving and automatically detecting and extinguishing fire and a control method. The method comprises the following steps: acquiring original detection data including a visible light image, a thermal infrared image, a laser point cloud and a sound signal; after feature extraction is carried out on the data sources, mapping the data sources to a unified environment three-dimensional coordinate system according to a preset space alignment rule, and generating fusion environment data; a fire source is identified and positioned based on the data, and the three-dimensional coordinate, the combustion intensity and the expansion rate of the fire source are obtained; in combination with fire source information and obstacle contours, performing global path planning by adopting an improved fast exploration random tree algorithm fused with a fire scene safety evaluation index; and finally, according to the planned path, the safety index and the state of the robot, a task execution instruction sequence containing a moving and fire extinguishing strategy is generated. According to the invention, the precision and consistency of multi-modal sensing are improved, and safe path planning under the dynamic fire scene risk is realized.