Autonomous Inspection Platform Real-Time Flight Path Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional UAV inspection methods fail to capture all targets-of-interest due to imperfect knowledge of industrial asset configurations and unexpected defects, as they follow predetermined flight plans that cannot be altered in real-time based on collected data.
Innovation Solution
An autonomously-operated inspection platform that dynamically modifies its flight plan in real-time using sensory data analysis, incorporating predefined metrics and pretrained models to adaptively collect additional data and ensure comprehensive inspection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a predetermined flight plan is used for UAV inspection, then the flight path is simple to plan and execute, but the inspection cannot capture all targets-of-interest when asset configuration changes or unexpected defects occur
Solution Approach 1:
The flight plan transitions from a static predetermined path to a dynamic adaptive path that changes in real-time based on sensor data. The system continuously monitors captured images and sensor readings during flight, automatically generating new waypoints and adjusting the flight path to capture unexpected defects or configuration changes, thereby improving inspection completeness without requiring overly complex pre-planning
Solution Approach 2:
The system implements a feedback loop where sensor data collected during flight is continuously analyzed and fed back into the motion planning system. This feedback mechanism allows the UAV to detect missed targets or unexpected features and automatically adjust its flight path accordingly, ensuring reliable capture of all targets-of-interest while maintaining manageable system complexity through automated decision-making
2Adaptability or versatility
If a deliberative pre-flight planning process is deployed to optimize the UAV's flight path, then the flight path can be predetermined to achieve all waypoints, but the flight plan cannot be altered during execution to adapt to real-world conditions
Solution Approach 1:
The system performs preliminary deliberative planning to establish an initial optimized flight path and waypoint sequence before flight execution. This pre-computed path provides a efficient baseline route that minimizes inspection time. During flight, the system then applies real-time adaptations to this predetermined path when necessary, combining the time-efficiency of pre-planning with the adaptability of real-time modifications
Solution Approach 2:
The flight plan maintains a dynamic structure that allows transition from static pre-computed waypoints to adaptive real-time path generation. When sensor data indicates the need for adaptation, the system dynamically modifies the flight path by inserting new waypoints or altering existing ones, enabling versatility without requiring complete re-planning that would consume excessive time
3Extent of automation
If the UAV follows a conventionally predetermined flight plan with fixed viewing angles, then the flight execution is simple and efficient, but the system cannot autonomously alter its path based on real-time captured pictures and sensor data
Solution Approach 1:
The UAV system performs self-service by autonomously analyzing its own sensor data and independently deciding when and how to modify its flight path. The system uses onboard processing to evaluate captured images and sensor readings against inspection objectives, automatically generating path adjustments without external intervention. This self-service capability achieves high automation while managing control system complexity through integrated decision-making algorithms
Data Source
AI summary
Modifying a motion plan for an autonomously-operated inspection platform (AIP) includes obtaining sensor data for an industrial asset area of interest, analyzing the obtained sensor data during execution of an initial motion plan to determine if modification of the initial motion plan is required. If modification is required then performing a pose estimation on a first group of potential targets and a second group of potential targets, optimizing the results of the pose estimation to determine a modification to the initial motion plan, performing reactive planning to the initial motion plan to include the modification, the reactive planning providing a modified motion plan that includes a series of waypoints defining a modified path, and autonomously controlling motion of the AIP along the modified path. The analysis, pose estimation, optimization, and reactive planning occurring during movement of the AIP along a motion plan. A system and computer-readable medium are disclosed.