Forward Graph Search for Reduced Vehicle Trajectory Trees
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for vehicle navigation in the presence of obstacles require computationally expensive and inefficient consideration of numerous maneuver combinations, leading to slow decision-making in complex environments.
Innovation Solution
Implementing a graph exploration forward search method that generates a reduced decision tree by excluding irrelevant or unreachable maneuver combinations, allowing for faster and more efficient selection of optimal vehicle trajectories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional systems consider all possible combinations of maneuvers to handle obstacles, then the system can find optimal trajectories, but the computational cost and time consumption increase significantly
Solution Approach 1:
The patent extracts and removes invalid or redundant maneuver combinations from the decision tree before evaluation. By identifying and eliminating trajectories that cannot lead to valid solutions (e.g., maneuvers that would cause collisions or violate constraints), the system reduces the computational search space while preserving all potentially optimal trajectories.
Solution Approach 2:
The patent segments the maneuver selection process into distinct phases: generating all possible maneuver combinations, validating each combination against constraints, and then evaluating only valid combinations for optimality. This segmentation allows the system to filter out invalid options early, reducing the computational burden of the optimization phase.
2Reliability
If conventional systems consider all possible combinations of maneuvers to handle obstacles, then the system can find optimal trajectories, but the computational complexity increases
Solution Approach 1:
The patent extracts and removes invalid or redundant maneuver combinations from the decision tree before evaluation. By identifying and eliminating trajectories that cannot lead to valid solutions (e.g., maneuvers that would cause collisions or violate constraints), the system reduces the computational search space while preserving all potentially optimal trajectories.
Solution Approach 2:
The patent segments the maneuver selection process into distinct phases: generating all possible maneuver combinations, validating each combination against constraints, and then evaluating only valid combinations for optimality. This segmentation allows the system to filter out invalid options early, reducing the computational burden of the optimization phase.
3Productivity
If the system reduces the decision tree by excluding certain trajectories, then computational efficiency improves, but the risk of excluding optimal trajectories increases
Solution Approach 1:
The patent extracts and removes only invalid trajectories from the decision tree, not potentially optimal ones. A trajectory is removed only if it violates hard constraints (e.g., would cause collision, exceeds vehicle capabilities). This ensures that all remaining trajectories are feasible candidates for optimality evaluation.
Solution Approach 2:
The patent implements a validation feedback mechanism where each generated trajectory is checked against predefined constraints and environmental conditions. Trajectories that fail validation are removed, while those that pass are retained for further evaluation. This feedback loop ensures that the reduced decision tree contains only valid trajectories without prematurely eliminating potentially optimal solutions.
Data Source
AI summary
Provided are methods for graph forward search exploration, which can include detecting a plurality of obstacles along a first trajectory of a vehicle. Some methods described also include determining a plurality of valid combinations of a plurality of trajectories to handle the plurality of obstacles. Some methods described also include generating a reduced decision tree based at least on the valid combinations of the plurality of trajectories by at least excluding a second trajectory of the plurality of trajectories associated with an obstacle of a plurality of obstacles based on a position of the obstacle being outside of a corridor defined by a spatial range and/or a temporal range. Some methods described also include selecting an optimal trajectory of the vehicle from the plurality of trajectories of the reduced decision tree. Systems and computer program products are also provided.