Robot Movement Planning with Symbolic-Motion Executability Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automatic movement planning methods for robot devices are inefficient, as they either generate plans quickly but with high memory load or require manual effort and time, and do not ensure executability in real environments, especially for complex tasks.
Innovation Solution
A movement planning device that uses a combination of symbolic and motion planners to generate abstract and physical action sequences, ensuring executability by discarding inexecutable plans and iteratively refining the planning process, while incorporating a cost estimation model for optimized planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If classical planning is used to generate abstract action sequences, then planning speed is improved and memory load is reduced, but executability in real environment cannot be ensured
Solution Approach 1:
The planning process is divided into two independent stages: classical planning for generating abstract action sequences (high speed, low memory) and motion planning for verifying physical executability (realism check). This segmentation allows each stage to optimize for its specific purpose without compromising the other.
Solution Approach 2:
Abstract action sequences serve as an intermediary representation between the simplified classical planning domain and the detailed motion planning domain. They capture essential task logic while remaining abstract enough for fast planning and detailed enough to guide realistic motion generation.
2Reliability
If Moveit Task Constructor is used to generate executable movement instructions, then executability in real environment is ensured, but user burden increases due to manual action definition
Solution Approach 1:
The system performs preliminary classical planning to automatically generate abstract action sequences that capture the essential task logic, eliminating the need for users to manually define detailed action sequences. Users only need to specify high-level task goals, not implementation details.
3Reliability
If all movements are held in memory during planning, then complete movement plans can be generated, but memory load increases
Solution Approach 1:
The planning process is segmented into stages that process and verify movements sequentially rather than loading all movements into memory simultaneously. Classical planning generates abstract sequences with low memory requirements, and motion planning verifies executability in a subsequent stage.
Solution Approach 2:
The system performs preliminary classical planning to generate abstract action sequences that capture essential task logic without storing detailed motion data. This preliminary structuring allows subsequent motion planning to proceed with reduced memory requirements.
Data Source
AI summary
Provided is a technique for generating a movement plan rapidly and at a relatively light memory load, even for a complicated task, while guaranteeing executability in a real environment. A movement planning device according to one aspect of the present invention uses a symbolic planner to generate an abstract action sequence including one or more abstract actions that are arranged in the order of execution. The movement planning device: uses a motion planner to generate, from each abstract action and in the order of execution, a sequence of movements; and determines whether the generated sequence of movements can be physically executed by a robot device in the real environment.