Virtual Vehicle Trajectory Control for Proactive Hazard Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through complex transportation networks due to external objects, where existing systems either ignore potential hazards or make unnecessary maneuvers, leading to inefficiencies and discomfort for passengers.
Innovation Solution
The implementation of a proactive risk mitigation system that uses a virtual vehicle model to predict trajectories and adjust the vehicle's path and speed, incorporating lateral and speed constraints based on map data and sensor perceptions, to anticipate and avoid hazards before they become actual obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the vehicle uses sensor-based hazard detection to identify external objects, then the detection accuracy is improved, but the response time is delayed because hazards are detected only after they enter the sensor's perceptible area
Solution Approach 1:
The system performs preliminary action by predicting the trajectories of virtual vehicles before they become actual hazards. The trajectory prediction module anticipates where vehicles will be in the future based on current sensor data and map information, allowing the autonomous vehicle to prepare avoidance maneuvers in advance rather than reacting after a hazard is detected. This shifts the detection paradigm from reactive (sensor-based) to proactive (prediction-based).
Solution Approach 2:
The system applies preliminary anti-action by proactively mitigating potential hazards before they materialize into actual collision risks. The risk mitigation module generates adjusted trajectories that preemptively avoid predicted hazard zones, counteracting potential future hazards before they can affect the vehicle's safety. This prevents rather than merely responds to harmful events.
2Reliability
If the vehicle makes aggressive avoidance maneuvers when hazards are detected, then collision risk is reduced, but passenger comfort and vehicle efficiency deteriorate due to unnecessary speed and lateral changes
Solution Approach 1:
The system applies partial action by making only the necessary adjustments to the trajectory required to avoid predicted hazards, rather than executing full aggressive avoidance maneuvers. The trajectory adjustment module calculates minimal lateral and longitudinal modifications that suffice to maintain safety margins, avoiding excessive steering or braking that would compromise comfort. This provides just enough action to ensure safety without overreacting.
Solution Approach 2:
The system uses dynamics by continuously adapting the avoidance maneuver intensity based on the predicted risk level. When virtual vehicles are predicted to remain in their lanes, the system maintains smooth trajectories with minimal adjustments. When potential conflicts are predicted, the system dynamically increases avoidance intensity. This dynamic adjustment optimizes the balance between collision avoidance and passenger comfort based on real-time situational assessment.
3Ease of operation
If the vehicle ignores potential hazards to maintain smooth traversal, then passenger comfort is improved, but safety is compromised when hazards materialize into actual obstacles
Solution Approach 1:
The system introduces virtual vehicles as intermediary objects that represent potential hazards without requiring actual sensor detection. These virtual vehicles serve as mediators between the prediction module and the trajectory planning module, allowing the system to prepare for potential hazards in a computationally efficient manner. The virtual vehicles enable smooth traversal by only triggering avoidance maneuvers when they are predicted to become actual obstacles, rather than requiring aggressive responses to all detected objects.
Data Source
AI summary
Proactively mitigating risk to a vehicle traversing a vehicle transportation network includes identifying a location for a virtual vehicle. The virtual vehicle is added to a world object model maintained with respect to the vehicle. A trajectory is predicted for the virtual vehicle. The vehicle is autonomously controlled according to an adjusted trajectory that is based on the trajectory for the virtual vehicle. The adjusted trajectory includes at least one of a lateral constraint or a speed constraint. The location for the virtual vehicle is identified based on a lane in map data, a trajectory of a vehicle, and a perceptible area by sensors of the vehicle. The virtual vehicle is a hypothetical vehicle that is not observed by sensors of the vehicle.