Autonomous Excavator Hierarchical Planning for Multi-Task Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current research on autonomous excavators lacks a comprehensive planning architecture that effectively connects high-level task planners, sub-task planners, and motion planning, particularly for a wide range of real-world tasks such as material loading and trench digging, with most focus on individual components rather than a unified system.
Innovation Solution
A hierarchical planning architecture is developed for autonomous machinery, comprising a high-level task planner that divides tasks into sub-task planners and motion primitives, with sub-task planners handling material removal and base move tasks, and motion primitives generating trajectories for controllers, validated through real-world experiments and simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a comprehensive planning architecture connecting high-level task planner, sub-task planners, and motion planning is implemented, then the ability to execute diverse real-world tasks is improved, but the device complexity increases
Solution Approach 1:
The planning architecture is divided into three distinct hierarchical levels: high-level task planner, sub-task planners, and motion planning. Each level handles specific aspects of task execution, allowing the system to manage complexity through modular organization while maintaining the ability to execute diverse excavation tasks.
2Productivity
If hierarchical planning architecture with multiple planners is implemented, then task execution efficiency is improved, but the control system complexity increases
Solution Approach 1:
The control system is segmented into specialized planners: high-level task planner for overall task management, sub-task planners for specific operations like material removal and base movement, and motion planning for execution. This segmentation improves task execution efficiency by assigning specific functions to dedicated components while managing complexity through clear separation of concerns.
Solution Approach 2:
The high-level task planner acts as an intermediary that receives high-level task descriptions and decomposes them into sub-tasks that are then processed by specialized sub-task planners. This intermediary layer simplifies the control system by providing a clear interface between high-level task specification and detailed execution planning.
Data Source
AI summary
Autonomous excavator has developed rapidly in recent years because of a shortage of labor and hazardous working environments for operating excavators. Presented herein are embodiments of a novel hierarchical planning system for autonomous machines, such as excavators. In one or more embodiments, the overall planning system comprises a high-level task planner for task division and base movement planning, and general sub-task planners with motion primitives, which include both arm and base movement in the case of an excavator. Using embodiments of the system architecture, experiments were performed for the trench and pile removal tasks in the real world and for the large-scale material loading tasks in a simulation environment. The results show that the system architecture embodiments and planner method embodiments generate effective task and motion plans that perform well in autonomous excavation.