Autonomous Vehicle Route Biasing for Predicted Traffic Stacks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through intersections with predicted traffic stacks, as existing systems struggle to effectively encourage lane changes to avoid being stopped behind such stacks, particularly in dense urban environments.
Innovation Solution
The method involves receiving signals indicating predicted traffic stacks, adjusting the costs of edges in the roadgraph to encourage lane changes, and generating routes based on these adjusted costs to control the autonomous vehicle's trajectory, thereby avoiding traffic stacks by biasing the route selection towards lane changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle follows the current lane to reach the destination, then the route is simple and direct, but the vehicle may be stopped behind traffic stacks at intersections
Solution Approach 1:
The system performs preliminary detection of traffic stacks at intersections before the autonomous vehicle reaches them. By identifying traffic stacks in advance using sensor data and prediction algorithms, the system can proactively adjust the route to avoid stopping behind stacked traffic, thereby preventing time loss before it occurs.
Solution Approach 2:
The routing system dynamically adjusts the route based on real-time detection of traffic stacks. When a traffic stack is detected in the current lane, the system dynamically recalculates and switches to an alternative route, allowing the vehicle to adapt its path dynamically rather than following a fixed predetermined route.
2Productivity
If the autonomous vehicle changes lanes to avoid traffic stacks, then forward progress is improved, but the control system complexity increases
Solution Approach 1:
The existing routing system, originally designed for basic navigation, is enhanced to perform multiple functions: it now detects traffic stacks, predicts their impact on progress, and automatically adjusts routes accordingly. This multi-functionality allows the system to improve forward progress without adding entirely new specialized subsystems.
Solution Approach 2:
The system continuously monitors sensor data to detect traffic stacks and feeds this information back to the routing algorithm. Based on this feedback, the system automatically recalculates routes and adjusts navigation commands, creating a closed-loop control system that adapts to real-time traffic conditions while maintaining manageable complexity through iterative refinement.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
The present invention relates to a method for controlling an autonomous vehicle (100), the method comprising receiving, by one or more processors of one or more first systems of the autonomous vehicles (100), a signal indicating a predicted traffic stack for a lane (428) in which the autonomous vehicle (100) is currently traveling; in response to the received signal, adjusting, by the one or more processors, costs of edges (31-43) of a roadgraph between the autonomous vehicle (100) and a location (510) of the predicted traffic stack in order to encourage the autonomous vehicle (100) to change lanes (428, 426) in response to the predicted traffic stack; generating, by the one or more processors, a route to a destination based on at least one of the adjusted costs; and providing, by the one or more processors, the route to one or more second systems of the autonomous vehicle (100) in order to control the autonomous vehicle (100) according to the route.