Robot Motion Planning Using Voxel Maps and Runtime 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, particularly in environments with dynamic obstacles and the need for fast and cost-effective operations across diverse settings such as kitting, inspections, and human-inhabited spaces.
Innovation Solution
A robotic system equipped with a motion planning processor and appendages that use sensors and logic circuits to determine and execute motion plans, processing data on object positions and orientations to navigate through environments without collisions, and adapt to dynamic conditions by generating and updating motion plans in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional motion planning algorithms are used, then motion planning can be achieved, but the computational cost is high and speed is slow
Solution Approach 1:
The patent segments the configuration space into discrete cells and pre-computes navigation graphs for each cell type. This segmentation allows the system to avoid complex continuous optimization during runtime, instead using pre-computed path segments that can be rapidly assembled, thereby improving motion planning speed while reducing computational time.
Solution Approach 2:
The system performs preliminary actions by pre-computing navigation graphs, collision-free paths, and motion primitives for different cell types before actual motion planning is needed. This pre-computation stores frequently used path segments and motion strategies, enabling the robot to quickly assemble complete paths during runtime without performing expensive real-time calculations, thus resolving the contradiction between planning speed and computation time.
2Adaptability or versatility
If complex motion planning algorithms are used to handle various environments and tasks, then adaptability improves, but device complexity increases
Solution Approach 1:
The patent implements a universal motion planning framework where a single navigation graph data structure and path assembly algorithm can handle multiple environment types (static obstacles, dynamic obstacles, confined spaces) and various tasks (point-to-point navigation, avoidance maneuvers). By using unified cell types, motion primitives, and path assembly rules that work across different scenarios, the system achieves high adaptability without requiring separate complex algorithms for each environment, thus maintaining relatively simple system architecture.
Solution Approach 2:
The system uses dynamic motion primitives and adjustable path assembly strategies that can adapt to different environment conditions. The navigation graph cells and motion primitives are designed to be configurable and modifiable based on environmental characteristics, allowing the same underlying system to handle diverse scenarios dynamically without increasing structural complexity. The path assembly process dynamically selects and combines motion primitives based on real-time conditions.
Data Source
Figure 1
Figure 2
Figure 3
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.