Robot Path Planning With Resolution-Independent Free-Space Seeding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional free-space based path planning techniques face challenges with inefficient seed selection, particularly in cluttered environments, where random-walk based seeding increases run-time and deterministic seeding depends on grid resolution, leading to incomplete exploration and redundancy.
Innovation Solution
The proposed method employs resolution-independent seeding, where seeds are generated sequentially using Iterative Regional Inflation by Semidefinite Programming (IRIS), creating contiguous navigable convex free-spaces without depending on environment grid resolution, and uses an undirected graph for local path planning with a heuristic function based on Euclidean distance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If random-walk based seeding is used, then free-space coverage is improved, but run-time increases
Solution Approach 1:
The patent pre-computes convex regions of safe space using IRIS before performing path planning. By preparing the free-space map in advance with proper seeding strategies, the system avoids runtime computation overhead while maintaining comprehensive free-space coverage for efficient real-time planning
Solution Approach 2:
The patent changes the seeding parameters from random-walk based approaches to a deterministic seeding strategy that selects seeds based on environment geometry. This parameter change reduces the number of seeds required and eliminates the runtime penalty associated with random-walk exploration while maintaining or improving free-space coverage
2Loss of time
If deterministic seeding is used, then run-time is reduced, but free-space exploration becomes incomplete and redundant
Solution Approach 1:
The patent modifies the seeding parameters by using geometry-based seed selection that considers environmental features such as narrow corridors, broken windows, and partially closed doors. This ensures complete and non-redundant free-space exploration while maintaining low run-time through deterministic computation
Solution Approach 2:
The patent incorporates feedback mechanisms where the seeding process adapts based on the generated free-space map. By evaluating the coverage and connectivity of convex regions, the system refines seed selection to ensure complete exploration without redundancy, resolving the contradiction between speed and completeness
3Productivity
If conventional seeding is used, then path planning can proceed, but navigable free-space coverage is insufficient in cluttered environments
Solution Approach 1:
The patent performs preliminary computation of convex free-space regions using IRIS with optimized seeding before path planning. This pre-processing step ensures comprehensive coverage of navigable spaces in cluttered environments, providing a complete map of safe regions that enables efficient subsequent path planning without re-computation
Solution Approach 2:
The patent segments the environment into convex free-space regions separated by obstacle surfaces. By decomposing the complex cluttered environment into manageable convex polytopes, the system achieves complete navigable space coverage while maintaining computational efficiency for path planning operations
Data Source
Figure 1~2
Figure 3~4A
Figure 4B~5
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.