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 at low costs and high speeds, particularly in dynamic and cluttered spaces with obstacles like humans and static objects, while ensuring collision avoidance.
Innovation Solution
A robotic system equipped with a motion planning processor and appendages with sensors, capable of generating and executing motion plans that navigate through complex environments by processing data on obstacle positions and orientations, using sensors like image, contact, and proximity sensors to determine safe trajectories and avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional motion planning algorithms are used to ensure collision avoidance in complex environments, then safety is improved, but computation time and system cost increase significantly
Solution Approach 1:
The motion planning problem is divided into multiple sub-problems by segmenting the configuration space into discrete cells. Each cell represents a specific robot state, and the planning algorithm navigates through these segmented cells to find a collision-free path, reducing the computational complexity compared to continuous space planning.
Solution Approach 2:
The system dynamically adapts the motion planning approach based on environmental complexity. For simple environments, faster but less comprehensive algorithms are used, while for complex environments with many obstacles, more thorough planning algorithms are employed. This dynamic adaptation optimizes computation time while maintaining safety.
2Adaptability or versatility
If comprehensive motion planning is performed for various environments and tasks, then adaptability is improved, but system complexity increases
Solution Approach 1:
A universal motion planning framework is implemented that can handle multiple task types (manipulation, locomotion, navigation) and various environment configurations through a single integrated system. The framework uses common data structures and algorithms that can be applied across different robot types and tasks, reducing overall system complexity while maintaining high adaptability.
Solution Approach 2:
The system achieves adaptability to different environments and tasks by dynamically adjusting planning parameters such as cell size, search depth, and algorithm selection based on environmental characteristics and task requirements, rather than requiring completely different systems for each scenario.
3Productivity
If fast motion planning is implemented to improve productivity, then operation speed is improved, but planning thoroughness and collision safety may be compromised
Solution Approach 1:
The motion planning system performs periodic re-planning and verification at key points during robot execution. Rather than performing one comprehensive plan that takes too long, the system generates initial fast plans and then periodically checks and refines them, ensuring thoroughness while maintaining operational speed.
Solution Approach 2:
The system performs preliminary motion planning in advance when time is not critical, preparing collision-free paths before actual execution. This preliminary action allows the robot to operate at high speeds during execution while safety has already been verified in advance.
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.