Search

CN-121979070-A - Intelligent paying-off robot regulation and control system and method based on perception obstacle avoidance

CN121979070ACN 121979070 ACN121979070 ACN 121979070ACN-121979070-A

Abstract

The invention discloses an intelligent paying-off robot regulation and control system and method based on perceived obstacle avoidance, and relates to the technical field of intelligent robot control, wherein the method comprises the steps of collecting historical operation data of a robot in a plurality of operation periods and constructing an environment optimization model; the method comprises the steps of pre-generating a plurality of alternative paths with different risk characteristics by combining current working time and environment risk patterns before a task starts, calculating comprehensive scores of the alternative paths, distributing calculation and storage resources of a perception system, collecting operation data of a robot in real time and comparing the operation data with prediction data of an environment optimization model in real time in the task execution process, triggering dynamic path rescheduling when deviation exceeds a preset threshold value, triggering a grading early warning mechanism when the deviation exceeds the risk threshold value in a health early warning matrix, updating the environment risk patterns and the health early warning matrix after the task ends, and dynamically adjusting path confidence degree weights and resource configuration strategies of all areas.

Inventors

  • GUO FANLI

Assignees

  • 宿迁学院
  • 江苏冠城投资发展有限公司

Dates

Publication Date
20260505
Application Date
20260205

Claims (10)

  1. 1. The intelligent paying-off robot regulation and control method based on perception obstacle avoidance is characterized by comprising the following steps of: S100, acquiring historical operation data of a robot in a plurality of working periods, and constructing an environment optimization model based on the historical operation data, wherein the environment optimization model comprises an environment risk map reflecting space-time distribution characteristics of obstacles and a health early warning matrix of association relations among the operation data, energy consumption data and fault data; S200, pre-generating a plurality of alternative paths with different risk characteristics by combining the current working time and an environment risk map before the task starts, and calculating the comprehensive score of each alternative path; s300, in the task execution process, operation data of the robot are collected in real time and compared with predicted data of an environment optimization model in real time; s400, triggering a dynamic path re-planning and recording an abnormal event when the deviation between the operation data and the prediction data exceeds a preset threshold value, triggering a hierarchical early warning mechanism when the operation data reaches a risk threshold value in the health early warning matrix, and outputting operation adjustment or maintenance advice; and S500, updating an environment risk map and a health early warning matrix based on operation data acquired by the task after the task is finished, and dynamically adjusting the path confidence degree weight and the resource allocation strategy of each area according to the consistency evaluation result of path execution.
  2. 2. The intelligent paying-off robot regulating and controlling method based on perceived obstacle avoidance as set forth in claim 1, wherein the step S100 includes: s110, collecting historical operation data of the robot in a plurality of operation periods, wherein the historical operation data comprise obstacle avoidance event data, path deviation data, energy consumption data and fault data, the obstacle avoidance event data comprise obstacle occurrence time, geographic coordinates, obstacle types and robot coping behaviors, the path deviation data comprise deviation quantification data of an actual operation path of the robot and a preset planning path, the energy consumption data comprise real-time energy consumption data of each execution subsystem of the robot, and the fault data comprise fault occurrence time, associated execution components and fault types; S120, generating the environment risk map based on analysis of the obstacle avoidance event data, wherein the analysis comprises statistical processing of time distribution, geographic distribution and type distribution of obstacle occurrence; S130, constructing the health early warning matrix based on association relation analysis among the obstacle avoidance event data, the path deviation data, the energy consumption data and the fault data in the historical operation data.
  3. 3. The intelligent paying-off robot regulating and controlling method based on perceived obstacle avoidance as set forth in claim 1, wherein the step S200 includes: S210, extracting regional risk information of a corresponding period from the environment risk map according to the current operation time, and generating at least two alternative paths with differential risk characteristics based on the regional risk information; s220, calculating comprehensive scores of the alternative paths, wherein the comprehensive scores are calculated in a weighting mode based on the path length of each alternative path, the risk level of the area and the area environment stability; s230, dynamically configuring the sensing data acquisition frequency and the processing resource allocation priority of the corresponding region in the sensing system according to the risk level of each region through which the selected alternative path passes.
  4. 4. The intelligent paying-off robot regulating and controlling method based on perceived obstacle avoidance as set forth in claim 1, wherein the step S300 includes: S310, acquiring operation data of the robot in real time in the task execution process, wherein the operation data comprises real-time obstacle avoidance event data, real-time path deviation data, real-time energy consumption data and real-time fault state data; S320, based on the current operation position and the current operation time of the robot, obtaining prediction data of a corresponding operation period and operation area from an environment optimization model, wherein the prediction data comprises prediction obstacle information, a prediction path deviation range, a prediction energy consumption interval and a prediction fault risk state; s330, performing dimension-by-dimension corresponding comparison on the operation data and the prediction data, and generating a real-time deviation analysis result.
  5. 5. The intelligent paying-off robot regulating and controlling method based on perceived obstacle avoidance as set forth in claim 1, wherein the step S400 includes: S410, acquiring a real-time deviation analysis result, judging the real-time deviation analysis result and a corresponding first preset threshold value, and judging an abnormal operation event if the deviation of at least one dimension exceeds the first preset threshold value; S420, triggering dynamic path re-planning based on current environment information when the abnormal operation event is judged to occur, and recording related data of the abnormal operation event to an abnormal event database; s430, inputting the operation data acquired in real time into the health early warning matrix to evaluate the risk state, and triggering a hierarchical early warning mechanism when the evaluation result reaches a second preset threshold; s440, generating and outputting targeted robot operation parameter adjustment instructions or system component maintenance suggestions according to the early warning levels corresponding to the hierarchical early warning mechanisms.
  6. 6. The intelligent paying-off robot regulating and controlling method based on perceived obstacle avoidance as set forth in claim 1, wherein the step S500 includes: s510, after the task is finished, extracting all operation data acquired in the task execution process; s520, updating obstacle risk level information of corresponding space-time areas in the environment risk map based on the current obstacle avoidance event data in the operation data; S530, updating association relations among behavior data, energy consumption data and fault data in the health early warning matrix based on all running data of the task; S540, calculating a consistency evaluation result of an actual execution path and a planned path of the task, and dynamically adjusting path confidence weight of each region in the environment risk map according to the consistency evaluation result; s550, updating the perceived system resource allocation strategy of the corresponding region according to the updated environment risk map and combining the path confidence weight.
  7. 7. The intelligent paying-off robot regulation and control system based on perceived obstacle avoidance is characterized by comprising a model construction module, a dynamic planning module, a real-time comparison module, an event response module and an updating and optimizing module: The model construction module is used for collecting historical operation data of the robot and constructing an environment optimization model based on the historical operation data, wherein the environment optimization model comprises an environment risk map and a health early warning matrix, the model construction module comprises a data collection unit, a map construction unit and a matrix construction unit, the data collection unit is used for collecting the historical operation data and real-time operation data of the robot in a plurality of working periods, the operation data comprise obstacle avoidance event data, path deviation data, energy consumption data and fault data, the map construction unit is used for carrying out space-time distribution analysis on the obstacle avoidance event data and generating and updating the environment risk map, and the matrix construction unit is used for carrying out association relation analysis on the obstacle avoidance event data, the path deviation data, the energy consumption data and the fault data in the operation data and constructing the health early warning matrix; The dynamic planning module is used for generating and evaluating a plurality of alternative paths based on the environment risk map and the current operation time before the task starts, and dynamically distributing the calculation and storage resources of the perception system according to the risk level of the selected path; The real-time comparison module is used for collecting operation data in real time and comparing the operation data with the prediction data provided by the environment optimization model in the task execution process to generate a real-time deviation analysis result; The event response module is used for triggering dynamic path re-planning and abnormal recording according to the real-time deviation analysis result, and triggering grading early warning and maintenance suggestion output according to the risk assessment result of the operation data in the health early warning matrix; and the updating and optimizing module is used for updating the environment risk map and the health early warning matrix based on the task operation data after the task is finished, and adjusting the path confidence degree weight and the resource allocation strategy according to the path execution consistency evaluation result.
  8. 8. The intelligent paying-off robot regulation and control system based on perceived obstacle avoidance as claimed in claim 7, wherein: the dynamic planning module comprises a path planning unit, a path evaluation unit and a resource allocation unit; The path planning unit is used for extracting regional risk information from the environment risk map according to the current operation time and generating at least two alternative paths with differential risk characteristics; The path evaluation unit is used for carrying out weighted scoring on each alternative path based on the path length, the risk level of the passed area and the environmental stability of the area; The resource allocation unit is used for dynamically configuring the sensing data acquisition frequency and the processing resource allocation priority of the corresponding region in the sensing system according to the risk level of each region through which the selected path passes.
  9. 9. The intelligent paying-off robot regulation and control system based on perceived obstacle avoidance as claimed in claim 7, wherein: the event response module comprises an exception processing unit, a health early warning unit and an instruction output unit; The abnormal processing unit is used for judging an abnormal operation event when the real-time deviation analysis result exceeds a first preset threshold value, triggering dynamic path re-planning and recording event data to an abnormal event database; The health early warning unit is used for inputting operation data acquired in real time into the health early warning matrix to perform risk assessment, and triggering a grading early warning mechanism when an assessment result reaches a second preset threshold value; The instruction output unit is used for generating and outputting corresponding robot operation parameter adjustment instructions or system component maintenance suggestions according to the triggered early warning level.
  10. 10. The intelligent paying-off robot regulation and control system based on perceived obstacle avoidance as claimed in claim 7, wherein: The updating and optimizing module comprises a model updating unit, a confidence level adjusting unit and a strategy optimizing unit; the model updating unit is used for updating the association relationship between the obstacle risk grade information in the environment risk map and the health early warning matrix based on the operation data acquired by the task; the confidence coefficient adjusting unit is used for dynamically adjusting the path confidence coefficient weight of each region in the environment risk map according to the consistency evaluation result of the actual execution path and the planning path of the task; The strategy optimization unit is used for updating the perceived system resource allocation strategy of the corresponding area according to the updated environment risk map and the path confidence weight.

Description

Intelligent paying-off robot regulation and control system and method based on perception obstacle avoidance Technical Field The invention relates to the technical field of intelligent robot control, in particular to an intelligent paying-off robot regulation and control system and method based on sensing obstacle avoidance. Background In the fields of traffic engineering, building construction and the like, automatic paying-off operation is important to improving efficiency and precision. Traditional paying-off robots either rely on a preset fixed path to execute tasks or only have basic real-time obstacle avoidance functions. The former cannot adapt to the dynamically changing working environment, while the latter usually adopts a 'perception-reaction' type simple control logic, and lacks knowledge and utilization of environmental laws. In the prior art, path planning is mostly based on static maps or instant perception, depth mining and learning of historical operation data are lacked, environmental risk change trend cannot be predicted, path selection is lacked prospective, perception and calculation resources are generally distributed by adopting uniform or fixed strategies, resource waste or insufficient key information capture is easily caused in complex and changeable environments, association between the health state of a robot and operation behaviors and environmental loads is not systematically modeled and analyzed, so that maintenance is mostly post passive response, operation continuity and equipment reliability are affected, and in the prior art, most systems lack a closed-loop mechanism for continuously learning from execution results and optimizing self-decision models, and intelligence level is difficult to evolve with time. Disclosure of Invention The invention aims to provide an intelligent paying-off robot regulation and control system and method based on sensing obstacle avoidance, so as to solve the problems in the prior art. In order to achieve the purpose, the invention provides the following technical scheme that the intelligent paying-off robot regulation and control method based on perceived obstacle avoidance comprises the following steps: S100, acquiring historical operation data of a robot in a plurality of working periods, constructing an environment optimization model based on the historical operation data, wherein the environment optimization model comprises an environment risk map reflecting space-time distribution characteristics of obstacles and a health early warning matrix of association relations among the operation data, the energy consumption data and the fault data; S200, pre-generating a plurality of alternative paths with different risk characteristics by combining the current working time and an environment risk map before the task starts, and calculating the comprehensive score of each alternative path; s300, in the task execution process, operation data of the robot are collected in real time and compared with predicted data of an environment optimization model in real time; S400, triggering dynamic path re-planning and recording abnormal events when the deviation between the running data and the predicted data exceeds a preset threshold value, triggering a hierarchical early warning mechanism and outputting running adjustment or maintenance suggestions when the running data reaches a risk threshold value in a health early warning matrix, wherein the dynamic path re-planning is local path adjustment based on latest instant environment perception information, and the hierarchical early warning mechanism is used for outputting gradient suggestions from running parameter fine adjustment to preventive maintenance according to different reached risk level threshold values; and S500, updating an environment risk map and a health early warning matrix based on operation data acquired by the task, wherein the updating is to incorporate a new obstacle event observed in the task into the map to correct risk probability, feed back the association of the operation state and the health state in the task to the matrix to optimize an evaluation rule, dynamically adjust path confidence degree weight and resource configuration strategy of each region according to a consistency evaluation result of path execution, and the path confidence degree is based on quantitative evaluation of the prediction reliability of the model in the region by the matching degree of a historical actual path and a planning path. According to the above scheme, step S100 includes: S110, collecting historical operation data of the robot in a plurality of working periods, wherein the historical operation data comprises obstacle avoidance event data, path deviation data, energy consumption data and fault data, the obstacle avoidance event data comprises obstacle occurrence time, geographic coordinates, obstacle types and robot coping behaviors, the path deviation data comprises deviation quantification data