Autonomous Vehicle Fleet Coverage Using Multi-Precision Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for operating autonomous vehicles to accomplish coverage tasks are limited by the use of a single type of vehicle, which can restrict operational parameters such as coverage rate, precision, speed, and cost, leading to increased resources and time required for task completion.
Innovation Solution
A method and system that iteratively select and operate multiple types of autonomous vehicles (ground, aerial, and naval) based on their unique operational parameters to optimize coverage, analyzing sensory data to identify uncovered segments and adjust vehicle selection and operation paths to achieve optimal coverage with minimal resources and time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single type of autonomous vehicle is used to accomplish coverage tasks, then the operational system is simple to manage, but the coverage rate, precision, and speed are limited, leading to increased time and resource requirements
Solution Approach 1:
The patent combines multiple types of autonomous vehicles (aerial, ground, and naval vehicles) into a unified fleet to accomplish coverage tasks. Each vehicle type contributes its unique operational capabilities, with aerial vehicles providing high-speed overview coverage, ground vehicles delivering detailed ground-level data, and naval vehicles covering water bodies. This merging of different vehicle types resolves the contradiction by achieving high productivity through diversified capabilities while maintaining manageable system complexity through centralized coordination.
Solution Approach 2:
The autonomous vehicle fleet is designed with multi-functionality, where different vehicle types can perform various coverage tasks depending on the environment and requirements. The system can dynamically assign aerial vehicles for rapid area scanning, ground vehicles for detailed inspection, and naval vehicles for water body coverage, making the fleet universally applicable to diverse coverage scenarios and resolving the productivity limitation of single-vehicle-type systems.
2Measurement precision
If high coverage precision is achieved using a single vehicle type, then measurement accuracy is improved, but the coverage rate decreases and more time is required to complete the task
Solution Approach 1:
The patent segments the coverage task into different levels: aerial vehicles perform initial broad-area coverage to identify regions requiring detailed inspection, while ground vehicles are deployed to specific segments for high-precision data collection. This segmentation allows the system to achieve both high coverage rate through aerial overview and high measurement precision through targeted ground vehicle deployment, resolving the contradiction between precision and productivity.
Solution Approach 2:
The system transitions from two-dimensional ground-level coverage to three-dimensional multi-layer coverage by incorporating aerial vehicles operating at altitude. This dimensional change enables simultaneous high-speed area coverage from above while ground vehicles provide detailed ground-level data, achieving both high coverage rate and high precision without the trade-off present in single-vehicle-type systems.
3Productivity
If multiple types of autonomous vehicles are deployed to optimize coverage, then coverage precision and rate are improved, but the system complexity and resource requirements increase
Solution Approach 1:
The patent implements a feedback mechanism where aerial vehicles first conduct broad-area coverage and identify regions requiring detailed inspection. Based on this feedback, ground vehicles are dynamically deployed to specific segments needing high-precision coverage. This feedback-driven coordination optimizes resource allocation and reduces unnecessary vehicle deployments, resolving the contradiction by achieving high productivity while managing system complexity through intelligent task assignment.
Solution Approach 2:
The system performs preliminary action by deploying aerial vehicles to conduct initial broad-area coverage and identify critical regions before deploying ground vehicles for detailed inspection. This preliminary action by aerial vehicles provides valuable information that guides subsequent ground vehicle deployment, reducing the overall system complexity by avoiding random or redundant vehicle assignments and optimizing resource utilization.
Data Source
AI summary
Described herein are methods and systems for automatically operating autonomous vehicles to accomplish a coverage task by receiving a plurality of task parameters defining a coverage task in a certain geographical area, calculating and outputting instructions for operating first autonomous vehicle(s) to cover the certain geographical area according to a first movement path computed according to operational parameters of the first autonomous vehicle with respect to the task parameters, identifying uncovered segment(s) in the certain geographical area by analyzing coverage of the certain geographical, and calculating and outputting instructions for operating second autonomous vehicle(s) to cover the uncovered segment(s) according to a second movement path computed according to operational parameters of the second autonomous vehicle. The first autonomous vehicle(s) and the second autonomous vehicle(s) are selected to optimally accomplish the coverage task. The second autonomous vehicle having increased coverage precision and reduced coverage rate compared to the first autonomous vehicle.