Lane Graph Pruning for Autonomous Routing Around Lane Closures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Lane closures due to objects, accidents, or construction cause traffic congestion and negatively impact road usage, as existing systems struggle to efficiently handle these closures.
Innovation Solution
Implementing lane graphs that utilize sensor data to identify lane closures and generate a pruned graph for autonomous vehicles to avoid blocked lanes by removing relevant nodes, allowing the vehicle to change lanes proactively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional systems are used to handle lane closures, then comprehensive monitoring can be maintained, but route determination speed decreases and traffic congestion increases
Solution Approach 1:
The patent segments the road network into discrete lane graphs with nodes representing specific lane segments. This segmentation allows the system to process and communicate only relevant closure information for affected nodes rather than entire road networks, thereby increasing route determination speed while maintaining comprehensive monitoring capability.
Solution Approach 2:
The system performs preliminary identification of lane closures and pre-prunes the lane graph by removing closed nodes before route calculation. This preliminary action enables autonomous vehicles to receive already-processed route information that avoids closures, significantly speeding up route determination and improving traffic flow efficiency.
2Measurement precision
If detailed sensor data is transmitted to identify lane closures, then detection accuracy improves, but data transmission volume increases
Solution Approach 1:
The patent extracts only the essential closure information from sensor data - specifically identifying closed lane segments and representing them as closed nodes in the lane graph. This extraction approach maintains detection accuracy by capturing the critical closure status while dramatically reducing the volume of data that needs to be transmitted to autonomous vehicles.
Solution Approach 2:
Instead of transmitting raw sensor data and letting vehicles process it, the system inverts the approach by pre-processing sensor data to create a pruned lane graph with closed nodes identified, then transmitting only this processed graphical representation. This inversion maintains detection accuracy while minimizing data transmission volume.
3Ease of operation
If the lane graph is maintained without pruning, then complete route information is available, but route calculation complexity increases
Solution Approach 1:
The system performs preliminary pruning of the lane graph by removing closed nodes before route calculation. This preliminary action simplifies the lane graph structure, making route calculation easier and more efficient while maintaining reliability because the pruning process systematically identifies and removes only closed segments, preserving all valid route options.
Solution Approach 2:
The patent extracts and removes closed nodes from the lane graph, separating the closure information from the route calculation process. This extraction simplifies the graph structure for easier calculation while maintaining route completeness by ensuring that all unclosed lanes and valid paths remain intact in the pruned graph.
Data Source
AI summary
Provided are methods for handling lane closures, which can include obtaining a lane graph including a plurality of nodes and a plurality of edges. A route from a first location to a second location is represented on the lane graph Some methods described also include obtaining at least one node corresponding to a lane segment comprising a lane closure along the route and pruning the lane graph based on the at least one node. Some methods described also include determining an updated route from a current location to the second location using the pruned lane graph and causing the vehicle to navigate along the updated route avoiding the lane closure. Systems and computer program products are also provided.