Multi-Vehicle Route Planning with Belief State Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional algorithms for determining vehicle routes are inadequate in planning multi-vehicle rendezvous, failing to account for localization uncertainty and often resulting in route failures.
Innovation Solution
A method using belief state planners to plan routes that account for localization uncertainty, involving a route determination process that constructs a graph within a joint state space of vehicles, identifies paths, and determines routes to ensure vehicles rendezvous without collisions, utilizing measurement systems like radar and GPS.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional algorithms are used for determining vehicle routes, then the route determination process is simple, but the reliability of multi-vehicle rendezvous is poor due to failure to account for localization uncertainty
Solution Approach 1:
The patent transitions from planning in physical space to planning in belief space, which is a higher-dimensional state space that incorporates localization uncertainty. The belief state planner constructs a graph where vertices represent belief states (probability distributions over possible vehicle positions) rather than simple physical coordinates, enabling routes to be planned that account for uncertainty while maintaining computational tractability through dimensionality reduction techniques.
2Reliability
If belief state planners are used to account for localization uncertainty, then the reliability of rendezvous is improved, but the computational complexity increases
Solution Approach 1:
The patent segments the complex belief state planning problem into discrete vertices and edges within a graph structure. The belief space is partitioned into manageable belief states, each representing a discrete uncertainty configuration. This segmentation allows the planner to process uncertainty in discrete steps rather than as a continuous, intractable problem, reducing computational power requirements while maintaining reliability.
Solution Approach 2:
The patent implements partial action by considering only the most probable belief states and their transitions, rather than exhaustively processing all possible uncertainty configurations. The graph construction focuses on relevant belief states that are likely to be encountered during vehicle operation, eliminating computation for highly improbable states and thereby reducing processing requirements while preserving rendezvous reliability.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A method and apparatus for determining routes vehicles (4, 6), the method comprising: measuring positions of a first vehicle and a second vehicle (6); providing a specification of a region (12) having a fixed position in relation to the first vehicle (4); using the measurements and the region specification, determining a first route for the first vehicle (4) and a second route for the second vehicle (6). Determining the routes comprises: constructing a graph (34) within a joint state space (X) of the vehicles (4, 6); identifying, within the graph (34), a path from a first vertex to a second vertex, the first vertex corresponding to the measured positions of the vehicles (4, 6), and the second vertex corresponding to the second vehicle (6) being at least partially located within the region (12); and, using the identified path, determining the first and second routes.