Robot Motion Planning With Dynamic Graph Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robot motion planning systems face challenges in efficiently planning paths at low costs and fast speeds, especially when the robot's characteristics change, such as when holding objects of varying sizes or switching end effectors, due to limitations in storing and processing motion planning information.
Innovation Solution
The system generates and stores multiple planning graphs associated with different sets of physical dimensions of the robot, allowing for dynamic switching between them based on current configurations, using processor-readable storage to provide edge information for collision checking and optimization, enabling efficient collision-free path planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple planning graphs are stored for different robot configurations, then motion planning adaptability improves, but memory storage requirements increase
Solution Approach 1:
The planning system is segmented into multiple discrete planning graphs, each corresponding to a specific robot configuration. This allows the system to divide the overall planning problem into manageable segments that can be stored and processed separately, enabling adaptability without requiring all configurations to be active simultaneously in memory.
Solution Approach 2:
Multiple planning graphs are pre-computed and stored for different robot configurations before actual motion planning is needed. This preliminary action allows the system to have pre-prepared plans for various configurations, reducing real-time computational requirements while maintaining adaptability.
2Speed
If planning graphs are stored in processor memory, then motion planning speed improves, but the amount of storable planning information is limited
Solution Approach 1:
The system extracts only the essential planning graph data structures and edge information needed for motion planning, storing them in processor memory for fast access. Non-essential or redundant information is excluded, allowing the system to maximize the use of limited processor memory while maintaining planning speed.
Solution Approach 2:
The planning graphs are optimized for local processing requirements, with data structures and information tailored to the specific needs of motion planning operations. This local optimization allows efficient use of processor memory by storing only the quality and type of information necessary for fast planning execution.
3Adaptability or versatility
If the robot holds objects of various sizes or changes end effectors, then operational versatility improves, but the complexity of motion planning increases
Solution Approach 1:
The planning graph data structure is designed to be universal and configuration-agnostic, capable of representing multiple robot configurations including different end effectors and held objects. This universal structure reduces the complexity of managing multiple specialized planning systems for each possible configuration.
Solution Approach 2:
The system dynamically selects and switches between different pre-computed planning graphs based on the current robot configuration. This dynamic approach allows the system to adapt to changing operational conditions (different objects, end effectors) without requiring a single complex planning system that handles all possibilities simultaneously.
Data Source
AI summary
A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.