Roadmap Segmentation for Robotic Coordination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic navigation systems in environments with multiple robotic devices face challenges in efficiently coordinating routes and minimizing conflicts, particularly at intersections where robotic devices may overlap or collide, leading to delays and inefficiencies.
Innovation Solution
A computing device determines a roadmap representing the environment with edge interaction regions and non-interaction regions, allowing for the segmentation of edges into sub-edges based on these regions, enabling the use of different rule sets for single and multiple agent planning software to manage robotic device interactions and optimize route planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a single unified rule set is used for all route planning, then the system is simple to implement, but it cannot efficiently coordinate robotic devices at intersections where conflicts may occur
Solution Approach 1:
The patent segments the environment into interaction regions and non-interaction regions, and applies different rule sets to each segment. Interaction regions use multiple agent planning rules to coordinate robotic devices, while non-interaction regions use simpler single agent planning rules, thus resolving the contradiction between system simplicity and conflict coordination reliability.
Solution Approach 2:
The patent implements local quality by applying different planning rule sets to different spatial regions. The multiple agent planning rule set is applied locally in interaction regions where robotic devices may conflict, while the single agent planning rule set is applied in non-interaction regions, optimizing both simplicity and reliability in their respective contexts.
2Reliability
If multiple agent planning is used throughout the entire environment, then conflict coordination is improved, but the computational complexity and processing time increase significantly
Solution Approach 1:
The patent divides the environment into interaction regions requiring multiple agent planning and non-interaction regions using simpler single agent planning. This segmentation reduces the overall computational complexity by limiting complex planning only to necessary areas, while maintaining conflict coordination reliability where needed.
Solution Approach 2:
The patent applies multiple agent planning partially only in interaction regions rather than throughout the entire environment. This partial application maintains sufficient conflict coordination reliability while significantly reducing computational complexity and processing time in non-critical areas.
3Productivity
If route planning does not consider interaction regions, then processing speed is faster, but conflicts between robotic devices at intersections increase
Solution Approach 1:
The patent segments the environment to identify interaction regions where robotic devices may conflict. By applying multiple agent planning specifically in these segmented regions, the system maintains high route planning efficiency in non-interaction areas while ensuring conflict-free navigation in critical interaction zones.
Solution Approach 2:
The patent performs preliminary identification of interaction regions before route planning. This preliminary action allows the system to pre-determine which areas require complex coordination, enabling faster processing in non-interaction regions while maintaining high conflict-free navigation reliability through advance preparation in critical areas.
4Device complexity
If the roadmap is not segmented into sub-edges, then the data structure is simpler, but it cannot effectively manage different planning rules in different regions
Solution Approach 1:
The patent segments edges into sub-edges corresponding to interaction and non-interaction regions. This segmentation creates a more complex data structure that enables the system to apply different planning rule sets adaptively to different regions, thus trading some structural simplicity for significant gains in rule set adaptability and planning effectiveness.
Solution Approach 2:
The patent implements local quality by associating different planning rule sets with different sub-edge segments. This allows the data structure to maintain adaptability for applying appropriate rules in different regions while keeping the overall structure organized and manageable through consistent segmentation principles.
Data Source
AI summary
Systems and methods related to roadmaps for mobile robotic devices are provided. A computing device can determine a roadmap that includes a first intersection associated with first and second edges. The computing device can determine an edge interaction region (EIR) surrounding the first intersection that includes portions of the first and second edges, where a traversal region on the first edge portion can overlap a traversal region on the second edge portion. The computing device can determine first and second sub-edges of the first edge; the first sub-edge within the EIR and the second sub-edge outside the EIR. The computing device can receive a request to determine a route, determine the route specifying travel along the first sub-edge with a first rule set and along the second sub-edge with a second rule set, and provide the route.