Virtual Stop Line Control for Autonomous Intersection Approach
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating complex transportation networks due to external objects, which can lead to unpredictable interactions and inefficient trajectory planning, especially at intersections, where external objects may behave unpredictably, necessitating proactive risk mitigation to ensure safe and comfortable travel.
Innovation Solution
The implementation generates virtual road users based on sensor ranges and predicts their behavior to determine a target speed for the host vehicle, using a proactive trajectory planning system that considers both actual and virtual hazards to optimize speed and path adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle reduces speed and minimizes lateral changes for safe intersection traversal, then safety is improved, but productivity decreases
Solution Approach 1:
The system performs preliminary actions by generating virtual road users at sensor range borders before the vehicle actually reaches those positions. This allows the trajectory planning system to proactively identify potential hazards and calculate safe trajectories in advance, enabling the vehicle to maintain smoother, more efficient motion while still ensuring safety through pre-computed risk-mitigated paths.
Solution Approach 2:
Virtual road users serve as intermediaries between the actual external objects and the trajectory planning system. These virtual entities represent potential hazards at the boundaries of sensor detection, allowing the system to plan conservative trajectories that account for unseen objects without requiring the vehicle to excessively slow down. The virtual road users mediate the interaction between limited sensor range and safety requirements.
2Productivity
If the autonomous vehicle maintains higher speed for efficient transportation, then productivity is improved, but the risk from external objects increases
Solution Approach 1:
The system calculates safe trajectories and identifies potential hazards in advance by generating virtual road users before the vehicle reaches their positions. This preliminary risk assessment allows the vehicle to maintain higher speeds while still having pre-computed escape routes and risk mitigation strategies ready, reducing the need for sudden braking or lateral maneuvers.
Solution Approach 2:
The system continuously monitors the positions of virtual road users and updates the trajectory plan based on their proximity to actual external objects. This feedback mechanism allows the vehicle to adjust its speed and trajectory dynamically, maintaining efficient motion when risks are low while automatically reducing speed when virtual road users indicate potential hazards near the vehicle's path.
3Reliability
If the autonomous vehicle uses a conservative trajectory planning approach with virtual road users, then reliability is improved, but device complexity increases
Solution Approach 1:
The system creates simplified copies of potential external objects as virtual road users at sensor range borders. These virtual copies serve as computational proxies that are easier to track and plan against than actual complex external objects. By working with these simplified virtual representations, the system achieves reliable safety without requiring complex real-time analysis of every potential hazard.
Solution Approach 2:
The system segments the complex problem of intersection safety into manageable components: generating virtual road users at specific sensor boundaries, determining which virtual road users are most relevant to the current trajectory, and calculating trajectories based on these segmented risk assessments. This segmentation makes the overall system more manageable and computationally efficient.
Data Source
AI summary
At least one virtual road user is generated, wherein a position of a respective virtual road user of the at least one virtual road user corresponds to a border of a range of a sensor of a host vehicle approaching an intersection of a vehicle transportation network. A most relevant virtual road user of the at least one virtual road user is determined, the most relevant virtual road user being associated with an earliest crossing lane of the intersection from a perspective of the host vehicle. A time to contact for the most relevant virtual road user is determined, wherein the time to contact is based on an acceleration of the host vehicle, a predicted trajectory of the most relevant virtual road user, and a relative distance between the host vehicle and the most relevant virtual road user. A target speed for the host vehicle is determined based on the time to contact and the relative distance. The host vehicle is operated using the target speed as input to a control system of the host vehicle.