Vehicle Trajectory Planning With Time-Based Rule Violation Costs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing rule-based trajectory planning systems face challenges in defining valid cost functions that account for rule violations, particularly in determining appropriate violation costs for permissible and impermissible system states and transitions.
Innovation Solution
A cost function is developed that distinguishes between time-dependent and fixed violation costs for state and transition rule violations, respectively, allowing for the optimization of movement trajectories by incorporating these costs into the planning process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a cost function is defined to account for rule violations in trajectory planning, then the trajectory optimization can consider rule compliance, but it becomes challenging to parameterize the violation costs appropriately
Solution Approach 1:
The patent applies parameter changes by transforming the abstract concept of rule violation costs into concrete, quantifiable parameters. Specifically, it introduces a violation cost parameter C_violation that can be adjusted to reflect different rule priorities, and a time-dependent parameter t that captures the duration of rule violations. This allows the cost function to dynamically adapt to different rule compliance requirements without increasing structural complexity.
Solution Approach 2:
The patent applies local quality by making the cost function sensitive to local rule violations rather than treating all violations uniformly. The cost function J(x(τ), u(τ)) is designed to accumulate costs only when and where rules are violated, allowing different trajectory sections to have different compliance requirements. This localized approach enables fine-grained control over rule adherence in specific spatial or temporal regions.
2Productivity
If trajectory planning minimizes total costs including violation costs, then optimal trajectories can be determined, but the planning complexity increases due to iterative optimization requirements
Solution Approach 1:
The patent applies preliminary action by pre-defining the cost function structure and violation cost parameters before trajectory optimization begins. The cost function J(x(τ), u(τ)) is formulated in advance with clear rules for calculating violation costs, allowing the iterative optimization process to focus solely on minimizing the pre-specified cost metric rather than also determining the cost structure itself. This separation reduces computational complexity during the optimization iterations.
3Measurement precision
If violation costs are made time-dependent to account for duration of rule violations, then more accurate rule compliance assessment is achieved, but the cost calculation complexity increases
Solution Approach 1:
The patent applies dynamics by making the violation cost time-dependent rather than static. The cost function incorporates the duration t of rule violations, allowing the penalty to scale with how long a rule is violated. This dynamic approach captures the intuitive notion that longer violations should incur higher costs, while the calculation remains straightforward by simply accumulating the time duration of violated rules.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The invention relates to a method for determining a motion trajectory for a moving object, in particular a vehicle, in a rule-based trajectory planning system, wherein trajectory planning is carried out based on a minimization of total costs according to a cost function, the cost function taking into account violation costs that result for each trajectory segment of the motion trajectory from any respective violation of one or more violateable rules with respect to the trajectory segment, wherein the rule violation comprises a state rule violation and/or a transition rule violation, wherein the state rule violation indicates a violation of a state rule that specifies an impermissible state of the moving object, and the transition rule violation indicates a violation of a transition rule that specifies an impermissible state transition.where a time-dependent cost amount of the violation costs is assigned to the state rule violation and a fixed, in particular time-independent, cost amount of the violation costs is assigned to the transition rule violation, so that the total cost for a movement trajectory for each trajectory segment that violates a violateable rule depends on the time-dependent or fixed cost amount assigned to the violated rule.