Robot Motion Planning Graph Switching for Changing Swept Volumes
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 and edge information sets based on different physical dimensions of the robot, allowing for dynamic selection and use of appropriate graphs during runtime to account for changes in the robot's configuration and environment, using voxels or rectangular prisms to represent swept volumes and perform collision checks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple planning graphs are stored for different robot configurations, then adaptability to changing robot characteristics is improved, 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 store pre-computed motion plans for different configurations separately, enabling quick selection without storing all possible variations in a single large structure.
Solution Approach 2:
Motion plans are pre-computed and stored in planning graphs before runtime. When the robot configuration changes, the system can directly retrieve the pre-computed plan from the corresponding planning graph without performing real-time computation, significantly improving response speed.
2Manufacturing precision
If motion planning information is stored in detail, then planning accuracy is improved, but processing speed decreases
Solution Approach 1:
The system performs detailed motion planning computations in advance and stores the results in planning graphs. During runtime, it only needs to retrieve and execute pre-computed plans, achieving both high accuracy and fast processing speed.
Solution Approach 2:
The planning space is segmented into discrete configurations, each with its own planning graph. This segmentation allows the system to store detailed information only for necessary configurations rather than all possible configurations, balancing detail with processing efficiency.
3Adaptability or versatility
If the robot holds objects of various sizes, then operational versatility is improved, but the volume occupied by the robot increases
Solution Approach 1:
The system dynamically selects the appropriate planning graph based on the current robot configuration, including the size of held objects. This allows the robot to adapt its motion plan to the current volume requirements without being constrained by a fixed, conservative volume estimate.
Solution Approach 2:
Different planning graphs are created for different local configurations of the robot, including different object sizes. Each planning graph contains motion plans optimized for its specific configuration, allowing the system to use the minimal necessary volume for each task rather than a uniform conservative estimate.
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.