Autonomous Vehicle Route Loop Detection Using Roadgraph Overlap
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles can become engaged in loops, causing them to repeatedly traverse the same portion of a roadway without reaching their destination, leading to wasted time and resources and a poor user experience.
Innovation Solution
The vehicle's routing system uses a roadgraph to generate and track routes, comparing nodes and edges to identify overlaps, determining if the vehicle is in a loop, and initiating mitigation responses such as setting a new destination or connecting to remote assistance when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the autonomous vehicle continuously follows the planned route without monitoring, then the vehicle can operate autonomously with simple control logic, but the vehicle may become engaged in infinite loops and waste time and resources
Solution Approach 1:
The system performs preliminary actions by tracking locations traversed during the trip and comparing them against the planned route before infinite loops occur. The routing system monitors the vehicle's progress along the route and detects when the vehicle has completed a full circuit, allowing intervention before significant time is wasted.
Solution Approach 2:
The system implements feedback by continuously monitoring the vehicle's location and comparing it to the planned route progress. When the system detects that the vehicle has returned to a previously visited location without reaching the destination, it triggers a response to recalculate the route, preventing continuous looping.
2Productivity
If the vehicle implements loop detection by tracking and comparing locations, then the vehicle can avoid infinite loops and improve efficiency, but the system complexity increases
Solution Approach 1:
The system establishes a planned route using a roadgraph with nodes and edges before the vehicle begins traversal. This preliminary route planning includes predefined paths that the vehicle should follow, allowing the system to detect deviations and loops by comparing actual traversal against the planned path.
Solution Approach 2:
The system creates a digital representation (copy) of the vehicle's traversal path by tracking locations visited during the trip. This copied path information is then compared against the planned route to detect loops, allowing the system to identify when the vehicle is revisiting locations without reaching the destination.
3Speed
If the vehicle detects a loop and immediately sets a new destination to current location, then the vehicle can exit the loop quickly, but the user experience may be degraded due to abrupt changes
Solution Approach 1:
The system performs preliminary actions by detecting loops early in the traversal process and calculating alternative routes before the vehicle completes full circuits. By identifying loop conditions early and having pre-calculated alternative paths ready, the system can transition smoothly without abrupt destination changes.
Solution Approach 2:
The system changes parameters by adjusting the destination or route parameters when a loop is detected. Instead of abruptly setting the destination to the current location, the system modifies route parameters to guide the vehicle along an alternative path that exits the loop while maintaining progress toward the original destination.
Data Source
AI summary
Aspects of the disclosure provide for determining whether a vehicle is in a loop for an autonomous vehicle. For instance, a route from a current location of the vehicle to a destination for a trip may be generated. Locations traversed by the vehicle during the trip may be tracked. Locations of the route may be compared to the tracked locations to determine an overlap value. Whether the vehicle is in a loop may be determined based on the overlap value.