Autonomous Driving Topological Planning With Constraint Bounds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face computational inefficiencies when navigating roadways due to the need to evaluate vast numbers of potential lane changes and in-lane maneuvers, often resulting in suboptimal or unfeasible trajectory planning, especially in dense traffic conditions.
Innovation Solution
A computer-implemented method that expands a topological tree by adding nodes to represent actions associated with constraints, generates bounds for navigating the vehicle relative to these constraints, and uses pruning techniques like feasibility, strict redundancy, and fuzzy redundancy pruning to reduce the number of candidate constraint sets and optimize trajectory planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the AV evaluates all possible candidate trajectories to ensure optimal path planning, then the quality of trajectory selection is improved, but the computational cost becomes infinitely expensive and computationally infeasible
Solution Approach 1:
The patent segments the continuous trajectory space into discrete topological elements (nodes and edges) forming a graph structure. This segmentation allows the system to evaluate only relevant path segments rather than all possible continuous trajectories, making the problem computationally tractable while maintaining planning quality.
Solution Approach 2:
The patent performs preliminary actions by pre-processing map data to extract topological relationships, road networks, and navigable paths before actual trajectory planning. This pre-computation of the topological graph structure enables faster online planning by eliminating the need to evaluate all possible trajectories from scratch during real-time operation.
2Productivity
If the AV samples a finite number of candidate trajectories to reduce computational load, then the computational cost is reduced, but the system may fail to find feasible or optimal trajectories when they exist
Solution Approach 1:
The patent creates a universal topological graph structure that represents all possible navigational paths through the environment. This graph serves multiple functions: it enables feasibility checking, supports optimization queries, and allows retrieval of valid trajectories. By making the topological representation multi-functional, the system ensures reliable trajectory finding while maintaining computational efficiency.
Solution Approach 2:
The patent incorporates feedback mechanisms where the cost function evaluation provides information about trajectory quality, which then guides the selection and refinement of candidate trajectories. This feedback loop ensures that the system continues to search for feasible and optimal paths rather than settling for arbitrary sampled trajectories.
Data Source
AI summary
Provided are autonomous vehicles and methods of controlling autonomous vehicles through topological planning with bounds, including receiving map data and sensor data, expanding a topological tree by adding a plurality of nodes to represent a plurality of actions associated with the plurality of constraints, generating a bound based on a constraint in the geographic area, the bound associated with an action for navigating the autonomous vehicle relative to the at least one constraint, storing the bound in a central bound storage, linking a set of bounds of a tree node to the bound via a bound identifier, wherein the first bound is initially linked as an active bound, or alternatively, as an inactive bound after determining it is not the most restrictive bound at any sample index, and control the autonomous vehicle based on the topological tree, to navigate the plurality of constraints.