Robot Motion Planning Using Multi-Resolution Graph Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion planning systems for robots face challenges in efficiently planning paths for various environments and tasks at low costs and high speeds, particularly in complex settings with obstacles and dynamic objects.
Innovation Solution
The system employs a robotic system with a motion planning processor and appendages equipped with sensors, capable of generating and executing motion plans to navigate through environments without collisions, using data from images and sensors to determine optimal paths for grasping and manipulating objects in diverse tasks such as assembly, inspection, and packaging.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional motion planning algorithms are used, then collision-free paths can be determined, but the computation time is excessive and speed is reduced
Solution Approach 1:
The motion planning problem is segmented into multiple sub-problems by dividing the configuration space into discrete cells or regions. This allows the planning algorithm to process smaller, manageable segments rather than the entire configuration space at once, significantly reducing computation time while maintaining collision-free path determination.
Solution Approach 2:
The motion planning system dynamically adapts its search strategy based on the current state and environment. By adjusting the planning approach in real-time according to obstacle positions and robot configuration, the system achieves faster computation without compromising the reliability of collision-free path generation.
2Reliability
If comprehensive environment modeling is performed, then accurate motion plans can be generated, but device complexity increases
Solution Approach 1:
The system extracts only the essential geometric and topological features of the environment necessary for motion planning, rather than processing complete 3D models or all environmental details. This extraction of critical information maintains motion plan accuracy while significantly reducing processing system complexity.
Solution Approach 2:
The patent uses simplified graphical representations or abstract models of the environment and robot configuration space, rather than processing actual complex physical models. These abstract copies retain the necessary spatial relationships for accurate motion planning while being computationally much simpler to handle.
3Measurement precision
If detailed configuration space representation is used, then precise collision detection is achieved, but computation cost increases
Solution Approach 1:
The system performs collision detection at critical configuration space boundaries and transition points rather than continuously throughout the entire motion path. This partial action approach maintains precise collision detection where it matters most while reducing overall computation cost.
Solution Approach 2:
The patent employs simplified geometric representations of the configuration space that preserve essential collision information. By using abstracted models that capture the critical spatial relationships without full geometric detail, the system achieves precise collision detection at lower computational cost.
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. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.