Mobile Robot Path Planning With Confidence-Based Obstacle Buffers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile automation apparatuses face increased computational loads and reduced efficiency due to errors in localization within complex environments, such as retail facilities, leading to inefficient path generation and navigation.
Innovation Solution
A method and apparatus for navigational path planning that involves obtaining localization and confidence levels, detecting obstacle boundaries, generating dynamic and static perimeter regions, and identifying unobstructed space to generate efficient navigational paths, thereby reducing errors and improving system efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional path generation methods are used in complex environments, then the mobile automation apparatus can navigate the environment, but localization errors increase computational load and reduce system efficiency
Solution Approach 1:
The patent segments the environment into discrete grid cells and divides the path generation into multiple stages: generating candidate paths, evaluating them against constraints, and selecting the optimal path. This segmentation reduces computational complexity by breaking down the large-scale path planning problem into smaller, manageable sub-problems that can be processed more efficiently
Solution Approach 2:
The patent performs preliminary actions by pre-generating candidate paths and pre-evaluating them against environmental constraints before final path selection. The system pre-processes localization data and environmental information to identify feasible path options in advance, reducing the computational burden during real-time navigation and improving overall system efficiency
2Measurement precision
If localization confidence is not considered, then path generation is simpler, but navigation accuracy decreases in complex environments
Solution Approach 1:
The patent applies dynamics by making the path generation process adaptive to localization confidence levels. The system dynamically adjusts path evaluation criteria and candidate path selection based on the confidence associated with localization data. When localization confidence is high, the system can use more aggressive path planning; when confidence is low, it incorporates additional safety margins and re-evaluates candidate paths, thereby maintaining navigation accuracy without requiring a completely complex system architecture
Solution Approach 2:
The patent changes parameters by incorporating localization confidence as an additional parameter in the path evaluation process. Instead of treating all paths equally, the system weights path candidates based on localization confidence levels, adjusting the effective cost function and selection criteria. This parameter change allows the system to account for uncertainty without fundamentally redesigning the entire path generation architecture
3Reliability
If obstacle handling is simplified, then computational load is reduced, but navigation safety and accuracy deteriorate in complex environments
Solution Approach 1:
The patent performs preliminary obstacle analysis by pre-identifying and cataloging obstacles in the environment before path generation. The system pre-processes sensor data to create an updated environmental model that includes obstacle locations, types, and potential hazards. This preliminary obstacle handling reduces computational load during actual path planning while maintaining navigation safety, as the obstacle information is already structured and ready for rapid evaluation
Solution Approach 2:
The system performs self-service by continuously updating its own environmental model using sensor data from the mobile automation apparatus. The apparatus autonomously detects obstacles, updates localization confidence, and re-evaluates candidate paths without external intervention. This self-service capability ensures navigation safety through continuous monitoring while reducing computational overhead by using the apparatus's own data rather than requiring extensive external processing
Data Source
AI summary
A method of navigational path planning for a mobile automation apparatus includes: obtaining an apparatus localization in a common frame of reference and a localization confidence level; detecting an obstacle boundary by one or more apparatus sensors; obtaining an obstacle map indicating the obstacle boundary in the frame of reference; generating a dynamic perimeter region of the obstacle boundary defining obstruction probabilities for respective distances from the obstacle boundary according to the localization confidence level; obtaining an environmental map indicating a predefined obstacle boundary; generating, for the predefined obstacle boundary, a static perimeter region defining obstructed space; identifying an obstructed portion of the dynamic perimeter region based on the obstruction probabilities and the apparatus localization; generating a navigational path traversing unobstructed space, that excludes the obstructed portion of the dynamic perimeter region, and the static perimeter region; and controlling the apparatus to traverse the generated navigational path.