Real-Time Robot Path Planning Using Convex Free-Space Seeding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional path planning methods face inefficiencies in obstacle avoidance and free-space exploration, particularly with increased obstacle clutteredness, leading to high computational burdens and incomplete exploration of environments.
Innovation Solution
A method for free-space based real-time path planning that uses resolution-independent seeding, where seeds are generated sequentially and expanded to form contiguous navigable convex spaces, allowing for efficient local path planning within an undirected graph based on Euclidean distance metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional sampling-based motion planning (SMP) or probabilistic roadmap method (PRM) is used for path planning, then the planner can dodge obstacles, but additional run-time is required for obstacle avoidance during planning
Solution Approach 1:
The patent pre-computes a visibility graph containing all visible edges and nodes before path planning. This preliminary action stores the environmental geometry information in advance, eliminating the need for runtime obstacle detection and computation during actual path planning, thus resolving the contradiction between reliable obstacle avoidance and planning time
Solution Approach 2:
The patent pre-generates an A* distance map from the goal position before querying paths. This preliminary computation of distance metrics allows for instant pathfinding decisions during planning without requiring additional runtime calculations for distance metrics, reducing planning run-time while maintaining reliable navigation
2Reliability
If conventional path planning methods are used in cluttered environments, then obstacle avoidance is achieved, but computational burden increases and free-space coverage becomes incomplete
Solution Approach 1:
The patent segments the continuous environment into discrete visible edges and nodes that form a visibility graph. By dividing the complex environment into manageable graph components, the computational burden is reduced while maintaining complete free-space coverage and reliable obstacle avoidance capabilities
Solution Approach 2:
The patent creates a simplified graph representation (visibility graph) that copies the essential geometric relationships of the environment. This abstracted copy contains all necessary information for path planning without the computational complexity of the full continuous environment, reducing device complexity while preserving obstacle avoidance reliability
Data Source
AI summary
This disclosure relates generally to real-time path planning. Planning amidst obstacles in a cluttered indoor environment is a difficult task for a robotic agent. The disclosed method provides semidefinite programming induced free-space based path planning. Free-space is generated by an efficient environment grid resolution independent seeding technique. In the proposed resolution independent seeding technique, initial position of the robotic agent is considered as the first seed. For subsequent seeding, information of the expanded earlier seeds are employed intelligently. This process is followed unto a finite sequence, which naturally results in a contiguous navigable convex free-space. This contiguous navigable convex free-space is employed to create an undirected graph, which is then used for path planning. Path planning is done locally by evaluating the subgoal with respect to a final goal. Local planning cumulatively assists the planner to attain the final goal.