Autonomous Vehicle Nudge Algorithm for Self-Reverse Lane Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in navigating self-reverse lanes without lane markers, where incoming objects can appear unexpectedly, as existing systems are not cost-efficiently modified to handle these scenarios.
Innovation Solution
The implementation of a computer-implemented method that detects incoming objects in a self-reverse lane by creating a temporary lane with a second reference line to nudge the object, and then returns to the center of the lane once the object has passed, using dynamic updates to the high-definition map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the ADV follows the first reference line in the self-reverse lane, then the ADV can maintain its original trajectory, but it cannot avoid collisions with incoming objects in the same lane
Solution Approach 1:
The system dynamically switches between the first reference line (original lane center) and the second reference line (temporary nudging lane) based on the presence of incoming objects. This dynamic adaptation allows the ADV to maintain simplicity in normal conditions while achieving collision avoidance when necessary, resolving the contradiction between reliability and device complexity.
Solution Approach 2:
The second reference line acts as an intermediary element that mediates between the ADV's original trajectory and the need to avoid incoming objects. By introducing this intermediate reference line, the system achieves collision avoidance without fundamentally redesigning the entire navigation system, thus resolving the contradiction between reliability improvement and device complexity.
2Reliability
If the ADV creates a temporary lane with a second reference line to nudge incoming objects, then collision avoidance is achieved, but the navigation system complexity increases
Solution Approach 1:
The system performs preliminary actions by detecting incoming objects in advance and proactively creating the temporary lane with the second reference line before collision becomes inevitable. This preliminary intervention allows the ADV to avoid collisions while managing complexity through structured, pre-planned responses rather than reactive complex maneuvers.
Solution Approach 2:
The temporary lane with the second reference line is created locally only in the specific region where incoming objects are detected, rather than modifying the entire navigation system globally. This localized approach achieves collision avoidance in the critical area while minimizing the increase in overall system complexity.
3Reliability
If the ADV returns to the center of the self-reverse lane after the object passes, then the original trajectory is restored, but time is lost during the nudge and return process
Solution Approach 1:
The ADV rushes through the nudge maneuver by quickly switching to the second reference line, performing the lateral movement to avoid the incoming object, and then rapidly returning to the first reference line once the object has passed. This rushing through of the necessary safety maneuver minimizes the time loss while ensuring reliable safe lane usage.
Solution Approach 2:
The system employs periodic monitoring of the self-reverse lane for incoming objects, and only activates the temporary lane and nudge maneuver when objects are detected. This periodic approach rather than continuous maneuvering reduces time loss by keeping the ADV on the original trajectory during safe periods while maintaining reliability through continuous monitoring.
Data Source
AI summary
According to various embodiments, systems and methods are provided for use by an ADV to nudge incoming objects in a self-reverse lane. In an embodiment, an ADV determines that a self-reverse lane has a predetermined width before entering the self-reverse lane. After entering the self-reverse lane, the ADV can follow a first reference line at the center of the self-reverse lane. In response to detecting an incoming object, the ADV creates an alternative lane in the self-reverse lane by temporarily modifying a high definition map. The ADV subsequently follows a second reference line in the alternative lane to nudge the incoming object. In response to detecting that the incoming object has passed and the self-reverse lane is clear, the ADV can drive back to the center of the self-reverse lane, to continue to follow the first reference line in the self-reverse lane.