Autonomous Vehicle Corridor Selection for Ambiguous Traffic Redirection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating ambiguous traffic redirections, particularly when non-standard signage or cues are not detectable by their computing systems, leading to potential safety issues such as becoming stuck or driving in the wrong direction.
Innovation Solution
The vehicle's computing devices process sensor data to identify ambiguities, analyze corridors, and determine traffic flow by using reverse analysis, sign recognition, observing vehicle behavior, and sharing information with other vehicles, and if necessary, requesting human intervention to ensure safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles use standard map information for navigation, then navigation reliability is improved, but the vehicle cannot detect or respond to unexpected traffic redirections caused by construction or incidents
Solution Approach 1:
The system performs preliminary detection of traffic redirection features (cones, barrels, signs) before they become obstacles, using sensor data to identify and catalog these features in advance. This allows the vehicle to prepare navigation decisions proactively rather than reactively when encountering unexpected road conditions.
Solution Approach 2:
The patent introduces an intermediary processing layer between standard map information and vehicle navigation decisions. This layer uses sensor data to detect traffic redirection features and creates an enhanced environmental model that combines predefined map data with real-time observations, allowing the vehicle to adapt to unexpected conditions while maintaining navigation reliability.
2Adaptability or versatility
If the vehicle uses sensor data to detect traffic redirection features not in maps, then adaptability to unexpected circumstances is improved, but the complexity of the detection and decision-making system increases
Solution Approach 1:
The detection system is segmented into distinct functional modules: sensor data acquisition, traffic redirection feature detection, corridor identification, and navigation decision-making. Each module handles a specific aspect of the problem, reducing overall system complexity by breaking down the complex task of navigating unexpected conditions into manageable, specialized components.
Solution Approach 2:
The sensor system and processing algorithms are designed to perform multiple functions: detecting cones, barrels, signs, identifying corridor boundaries, determining traffic flow direction, and making navigation decisions. This multi-functionality reduces the need for separate specialized systems for each detection and decision task, thereby managing complexity while maintaining high adaptability.
3Adaptability or versatility
If the vehicle must identify and analyze multiple corridors and traffic flow directions, then the ability to navigate ambiguous redirections is improved, but the time required for decision-making increases
Solution Approach 1:
Instead of analyzing all possible corridors and then selecting the correct one, the system inverts the approach by using detected traffic flow indicators (such as vehicle movement patterns, signage orientation, and corridor geometry) to directly infer the intended direction. This inversion reduces analysis time by working backwards from observable cues to the correct navigation decision rather than evaluating all possibilities.
Solution Approach 2:
The system uses feedback from sensor data about other vehicles' behavior and traffic patterns to rapidly determine correct corridor selection. By observing how other vehicles navigate the redirection and using this feedback to validate or correct its own analysis, the system accelerates decision-making while maintaining accuracy in ambiguous situations.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
The technology relates to controlling a vehicle in an autonomous driving mode, the method. For instance, a vehicle 100 may be maneuvered in the autonomous driving mode using pre-stored map information identifying traffic flow directions. Data may be received from a perception system of the vehicle identifying objects in an external environment of the vehicle related to a traffic redirection not identified the map information. The received data may be used to identify one or more corridors 910, 920 of a traffic redirection. One of the one or more corridors may be selected based on a direction of traffic flow through the selected corridor. The vehicle may then be controlled in the autonomous driving mode to enter and follow the selected one of the one or more corridors based on the determined direction of flow of traffic through each of the one or more corridors.