Autonomous Machine Deployment Using Geofenced Task Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous machines in construction applications face inefficiencies and safety issues when operating simultaneously on a work site, such as machines waiting for each other to complete tasks, potential collisions, and inefficient task allocation due to site characteristics and machine limitations.
Innovation Solution
A system and method for optimizing machine deployment across a work site by determining deployment events based on machine and site characteristics, segmenting the work area to prevent collisions, and using machine learning to predict optimal deployment times, ensuring continuous operation and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple autonomous machines operate simultaneously on a work site, then productivity increases, but collision risk and safety issues increase
Solution Approach 1:
The work site is divided into multiple geofenced zones or segments, with each autonomous machine assigned to specific segments. The system dynamically allocates work areas among machines based on their locations, task progress, and operational status, preventing overlap and potential collisions while maintaining high productivity through parallel operations in different zones.
2Stability of the object's composition
If autonomous machines wait for each other to complete tasks, then task completion order is maintained, but idle time increases
Solution Approach 1:
The system performs preliminary analysis of task dependencies, machine capabilities, and site characteristics before deployment. It pre-calculates optimal task allocation and sequencing, allowing machines to begin operations as soon as they are ready rather than waiting for predecessors to complete entire tasks. The system dynamically adjusts allocations based on real-time progress, minimizing idle time while maintaining required task completion sequences.
3Ease of operation
If machines are deployed based on simple scheduling, then deployment is straightforward, but task allocation efficiency decreases
Solution Approach 1:
The system continuously monitors machine locations, task progress, operational status, and site conditions, using this feedback to dynamically optimize task allocation. The cloud-based platform processes real-time data from all machines and adjusts task assignments, work area allocations, and deployment decisions to maximize productivity. This closed-loop control maintains deployment simplicity while achieving high task allocation efficiency through automated, data-driven decisions.
Data Source
AI summary
Systems and methods are disclosed for optimal utilization of machines for performing tasks across a predetermined area. A request may be received to initiate a job on a predetermined area, the job comprising a plurality of tasks associated with a plurality of machines. In response to the request, a first machine of the plurality of machines may be deployed to the predetermined area to execute a first task of the plurality of tasks autonomously. A deployment event may be determined based on characteristics of the first machine and a second machine, and based on characteristics of the predetermined area. The second machine to the predetermined area, upon detection of the deployment event, to execute a second task of the plurality of tasks autonomously.