Vehicle Trajectory Planning Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Advanced Driver Assistance Systems (ADAS) face challenges in generating smooth, collision-free trajectories for autonomous vehicle maneuvers, particularly in general traffic situations, due to trade-offs between computational resources and formal stability analysis, which limits their applicability and safety in diverse traffic environments.
Innovation Solution
A method for trajectory planning using receding horizon control, sensor systems, prediction systems, and decision-making algorithms to determine lateral and longitudinal motion trajectories, safety critical zones, and control signals, allowing for efficient and safe maneuvers in both highway and urban traffic scenarios, such as lane changes and intersection crossings, by formulating the problem as a Quadratic Program optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If commonly used trajectory planning methods are applied, then the ability to generate smooth collision-free trajectories is improved, but the required computational resources increase
Solution Approach 1:
The trajectory planning problem is segmented into two independent sub-problems: lateral motion planning and longitudinal motion planning. The lateral planner generates candidate trajectories for lane changes using simplified dynamics, while the longitudinal planner independently computes safe speed profiles. This segmentation reduces computational complexity compared to solving the full coupled dynamics problem, while maintaining safety through systematic verification of each component.
Solution Approach 2:
The lateral motion planner generates candidate trajectories in advance before the longitudinal planning step. These pre-computed lateral paths serve as inputs for the longitudinal planner, allowing the system to evaluate safety and feasibility beforehand. This preliminary action enables more efficient computational resource usage by avoiding iterative refinement of both lateral and longitudinal motions simultaneously.
2Reliability
If extensive simulation and experimental testing are performed for validation, then the reliability of trajectory planning is improved, but the loss of time increases
Solution Approach 1:
The system incorporates formal stability analysis that provides mathematical guarantees of safety and correctness. This feedback mechanism allows the developers to verify trajectory planning correctness through rigorous mathematical proofs rather than relying solely on extensive simulation and experimental testing, significantly reducing validation time while maintaining high reliability.
3Device complexity
If the trajectory planning method is simplified to reduce computational complexity, then the ease of operation is improved, but the ability to handle general traffic situations deteriorates
Solution Approach 1:
The system uses dynamic adjustment of prediction horizons and planning frequencies based on traffic conditions. In complex urban environments with frequent maneuvers, the system increases planning frequency and extends prediction horizons. In simpler highway conditions, it reduces computational effort. This dynamic adaptation allows the simplified two-stage planner to handle diverse traffic situations effectively without requiring excessive computational resources in all scenarios.
Data Source
AI summary
The present disclosure relates to a method of trajectory planning for maneuvers for an ego vehicle (E) equipped with a sensor systems, a prediction systems, a control system, and a decision-making system. The method includes determining possible lateral motion trajectories of a requested maneuver, longitudinal safety critical zones which correspond to each of the determined possible lateral motion trajectories, a longitudinal motion trajectory of the requested maneuver, lateral safety critical zones which correspond to the determined longitudinal motion trajectory of the requested maneuver, and a lateral motion trajectory of the requested maneuver. The present disclosure also relates to a driver assistance system arranged to perform the method and a vehicle including such a system.