Autonomous Vehicle Lane Changes Around Predicted Traffic Stacks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through intersections with predicted traffic stacks, where a line of stopped vehicles can prevent forward progress, and existing systems struggle to effectively encourage lane changes to avoid such stacks.
Innovation Solution
The autonomous vehicle's computing devices predict traffic stacks using behavior predictions and occlusion information, adjusting the costs of roadgraph edges to encourage lane changes, thereby generating routes that avoid traffic stacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous vehicle continues straight in the current lane, then it follows the simple routing logic, but it gets stopped by the traffic stack at the intersection
Solution Approach 1:
The system performs preliminary detection of traffic stacks at intersections before the vehicle reaches them. By identifying the traffic stack in advance and predicting that it will block forward progress, the system proactively adjusts routing costs to encourage lane changes before the vehicle encounters the obstruction, thereby maintaining productivity and avoiding time loss.
Solution Approach 2:
The system dynamically adjusts the costs of roadgraph edges based on real-time detection of traffic stacks. Instead of using static routing costs, the system modifies the costs of edges leading to the intersection where a traffic stack is detected, making lane change options more attractive dynamically. This allows the vehicle to adapt its route in response to changing traffic conditions.
2Productivity
If the autonomous vehicle changes lanes to avoid the traffic stack, then it avoids being stopped, but it increases the complexity of routing decisions
Solution Approach 1:
The system applies local quality by modifying costs only for specific roadgraph edges related to the detected traffic stack, rather than recalculating the entire routing problem. By locally adjusting the costs of edges leading to the intersection where the traffic stack is detected, the system introduces lane change encouragement in a targeted manner, minimizing the increase in routing decision complexity while maintaining the ability to avoid traffic stacks.
3Productivity
If the autonomous vehicle detects and responds to traffic stacks, then it navigates dense urban environments more effectively, but it requires more complex sensor processing and behavior prediction
Solution Approach 1:
The system performs preliminary detection and classification of traffic stacks using sensor data and behavior predictions before they become immediate obstacles. By identifying traffic stacks in advance at intersections and predicting their impact on forward progress, the system processes sensor information proactively, allowing for more efficient navigation decisions without overwhelming the processing system with reactive complexity.
Data Source
AI summary
Aspects of the disclosure provide for controlling an autonomous vehicle. For instance, one or more processors of one or more first systems of the autonomous vehicles may receive a signal indicating a predicted traffic stack for a lane in which the autonomous vehicle is currently traveling. In response to the received signal, costs of edges of a roadgraph between the autonomous vehicle and a location of the predicted traffic stack may be adjusted in order to encourage the autonomous vehicle to change lanes in response to the predicted traffic stack. A route may be generated to a destination based on at least one of the adjusted costs. The route may be provided to one or more second systems of the autonomous vehicle in order to control the autonomous vehicle according to the route.