Mobile Agent Path Planning with Dynamic Gates and Social Compliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigational planning systems for mobile programmable agents in crowded environments face challenges in balancing global and local optimality, often requiring excessive computational resources and neglecting social compliance and dynamic object interactions.
Innovation Solution
A system that divides the physical environment into plane figures with centroids, forming a network of segments from the origin to the destination, and determining gate states based on dynamic object movement to identify a safe and socially compliant pathway for the agent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If sampling based motion planners assume a static environment, then computation time and resources are reduced, but the planner cannot handle dynamic objects and time-varying environments
Solution Approach 1:
The patent segments the continuous environment into discrete grid cells and divides the planning problem into local navigation decisions at each cell. This segmentation allows the planner to process dynamic information incrementally rather than computing the entire path in advance, enabling real-time adaptation to moving objects while maintaining computational efficiency.
Solution Approach 2:
The patent implements dynamics by making the navigation plan adaptive and time-varying. Instead of assuming a static environment, the system continuously updates the cost function and re-plans based on current positions of dynamic objects. The plan evolves dynamically to accommodate moving obstacles while maintaining global optimality through iterative refinement.
2Reliability
If search-based and optimization-based planners account for dynamic objects, then navigation accuracy improves, but computational resources and time requirements increase exponentially
Solution Approach 1:
The patent applies local quality by focusing computational effort on locally relevant decisions rather than globally optimizing the entire path. The cost function evaluates local navigation choices based on current dynamic object positions, allowing high navigation accuracy in critical areas while avoiding exponential computational complexity across the entire environment.
Solution Approach 2:
The patent changes parameters dynamically by updating the cost function weights and constraints based on real-time positions of dynamic objects. Instead of re-computing the entire optimization problem, the system adjusts key parameters like collision risk weights and reuses previous computational results, maintaining navigation accuracy while reducing computational resource requirements.
3Reliability
If local planners focus on short-time collision-free paths, then agent dynamics are handled well, but global optimality is neglected
Solution Approach 1:
The patent applies preliminary action by pre-computing a global cost map that encodes efficient navigation paths through the environment. This preliminary structure guides local collision-free decisions, ensuring that short-term avoidance maneuvers still progress toward the global optimum. The pre-computed cost field provides a framework that maintains global optimality while allowing local adaptations for collision avoidance.
Data Source
AI summary
Embodiments, systems, and methods for navigational planning of a mobile programmable agent are provided. In some embodiments, the navigational planning may include identifying a plurality of dynamic objects in a physical environment having an origin and a destination. The physical environment is divided into a plurality of plane figures. The location of a centroid of each plane figure can then be calculated. A network of segments is formed from the origin to the destination intersecting the centroids. At least one channel is determined from the origin to the destination using a set of segments. A set of gates is identified along the at least one channel. The state of the gates is selectively determined based on movement of the dynamic objects. A pathway can then be identified within the channel for the mobile programmable agent to traverse from the origin to the destination based on the state of the gates.