Lane Graph Construction for Autonomous Vehicle Trajectory Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently planning lane changes while navigating through complex road environments, as existing technologies lack effective methods to optimize lane changes based on real-time factors like road blocks, lane dividers, and driving conditions.
Innovation Solution
A computer-based method that generates a lane graph from a geographic map, allowing autonomous vehicles to select optimal paths for lane changes by considering factors such as pose, road blocks, and lane dividers, and assigning weights to trajectories based on viability and cost, enabling the vehicle to commit to an initial path segment (stem) and adjust accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle considers multiple real-time factors (road blocks, lane dividers, driving conditions) for lane change planning, then the safety and optimality of lane changes is improved, but the computational complexity and processing time increases
Solution Approach 1:
The planning circuit segments the complex lane change planning problem into distinct components: generating multiple candidate trajectories, evaluating each trajectory against real-time factors (road blocks, lane dividers, driving conditions), assigning weights based on viability and cost, and selecting the optimal trajectory. This segmentation allows systematic handling of multiple factors without overwhelming computational burden.
Solution Approach 2:
The system performs preliminary actions by pre-generating multiple candidate trajectories before final selection. Each trajectory is pre-evaluated against current driving conditions, and weights are pre-assigned based on viability and cost metrics. This preliminary processing enables efficient real-time decision-making when lane changes are needed.
2Productivity
If the vehicle generates and evaluates multiple trajectories with weights, then the optimality of path selection is improved, but the processing time and computational resources increase
Solution Approach 1:
The planning circuit generates multiple trajectories (excessive action) to ensure optimal selection, but applies efficient weighting and evaluation methods to process them within acceptable timeframes. The system considers more trajectories than strictly necessary but uses streamlined evaluation to maintain efficiency.
Solution Approach 2:
The system changes parameters by assigning dynamic weights to trajectories based on real-time factors such as viability and cost. These weight parameters are continuously updated according to current driving conditions, allowing the system to efficiently prioritize more suitable trajectories without exhaustive evaluation of all possibilities.
3Stability of the object's composition
If the vehicle commits to an initial path segment (stem) of the trajectory, then the stability and predictability of navigation is improved, but the adaptability to changing conditions decreases
Solution Approach 1:
The trajectory is segmented into a committed stem portion and a flexible remaining portion. The vehicle commits to following the stem segment which provides stable, predictable navigation for the immediate future. Beyond the stem, the trajectory remains flexible and can be re-evaluated and adjusted in response to changing driving conditions, maintaining adaptability.
4Use of energy by moving object
If the system optimizes resource consumption for lane changes, then the efficiency of vehicle operation is improved, but the complexity of trajectory evaluation increases
Solution Approach 1:
The planning circuit uses parameter changes by assigning weight values to trajectories based on resource consumption metrics such as energy efficiency and travel time. These weight parameters allow the system to optimize for resource-efficient paths while maintaining a manageable evaluation framework that compares trajectories using standardized criteria.
Data Source
AI summary
Using a planning circuit of a vehicle, a map is accessed that includes information identifying at least one lane on which vehicles can travel. Using the planning circuit and from the map, a graph representing a driving environment of the vehicle is generated. The graph includes multiple trajectories. At least one trajectory includes a lane change. Each trajectory is a path for the vehicle to move from a first spatiotemporal location to a second spatiotemporal location. The trajectory includes at least one lane alone which the vehicle can move. Using the planning circuit, a trajectory of the multiple trajectories for the vehicle to travel is selected based on an initial vehicle trajectory of the vehicle. The selected trajectory includes a stem. The stem is a portion of the selected trajectory to which the vehicle is configured to adhere. Using the control circuit, the vehicle is moved along the selected trajectory.