Dual-Planner Vehicle Trajectory Planning for Safety and Driving Quality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-driving vehicles face challenges in navigating complex environments due to varying driving requirements, safety considerations, and cultural expectations, which complicate decision-making processes.
Innovation Solution
A signal processing system that generates and dynamically adjusts trajectories for autonomous vehicles based on component data, such as sensor data and time data, to ensure compliance with safety constraints and optimize navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single planner is used for trajectory planning, then the system is simpler, but it cannot simultaneously optimize for safety constraints and driving behavior quality
Solution Approach 1:
The trajectory planning system is divided into two separate planners: a stateless planner focused on safety constraints and a stateful planner focused on driving behavior quality. Each planner handles specific aspects independently, allowing optimization for their respective goals without compromising the other.
Solution Approach 2:
A trajectory generator acts as an intermediary component that receives inputs from both the stateless planner and stateful planner, processes their outputs, and generates the final trajectory. This mediator coordinates the outputs of both planners to produce a unified trajectory that satisfies both safety requirements and driving behavior expectations.
2Ease of operation
If comprehensive trajectory evaluation is performed, then driving behavior quality improves, but computation time increases
Solution Approach 1:
The evaluation process is segmented into two independent evaluation stages: safety constraint evaluation by the stateless planner and driving behavior evaluation by the stateful planner. This segmentation allows each evaluation to focus on specific criteria, improving overall evaluation efficiency while maintaining comprehensive assessment quality.
Solution Approach 2:
The stateless planner performs preliminary safety constraint evaluation before the stateful planner conducts driving behavior evaluation. By filtering trajectories based on safety constraints first, the system reduces the search space for the subsequent behavior evaluation, thereby reducing overall computation time.
3Productivity
If trajectories are generated without considering future planning steps, then generation speed is faster, but trajectory consistency deteriorates
Solution Approach 1:
The stateful planner maintains dynamic state information across multiple planning steps, allowing it to adapt trajectory generation based on the vehicle's current state and historical context. This dynamic approach ensures trajectory consistency while maintaining generation speed by only processing relevant state changes.
Solution Approach 2:
The stateful planner continuously updates and refines trajectories based on ongoing vehicle operation and changing conditions, ensuring consistent behavior across multiple planning steps. The planner maintains continuous state awareness, allowing it to generate coherent trajectories that align with long-term driving goals while operating at real-time speeds.
Data Source
AI summary
Provided are methods for trajectory generation using an adjusted plurality of trajectories, which can include generating a plurality of trajectories for a vehicle from a plurality of poses, combinations of trajectories of the plurality of trajectories representing a plurality of paths for the vehicle through an environment, adjusting the plurality of trajectories to obtain an adjusted plurality of trajectories based on component data associated with the vehicle, selecting a first trajectory from the adjusted plurality of trajectories, and determining a path for the vehicle to operate along based on the first trajectory. Systems and computer program products are also provided.