Intersection Maneuver Control With Zone-Based Autonomous Handover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating intersections due to obstacles that occlude the view of sensing devices, particularly when stationary and attempting to turn into oncoming traffic, leading to difficulties in controlling vehicle maneuvers effectively.
Innovation Solution
The system employs sensing devices and a processor to determine the type of intersection, traffic control devices, and their signals, defining zones for vehicle control, allowing for a blend of driver and autonomous control by evaluating the current zone, operator instructions, and autonomous control instructions to manage lateral and longitudinal movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle uses sensing devices to monitor oncoming traffic at an intersection, then the vehicle can detect traffic conditions and make navigation decisions, but obstacles occluding the field of view prevent effective detection of oncoming traffic
Solution Approach 1:
The system segments the intersection environment into multiple zones (first zone for oncoming traffic, second zone for cross traffic, third zone for protected turns) based on traffic control device signals. This segmentation allows the vehicle to apply different sensing and control strategies to each zone, improving detection reliability in areas that would otherwise be occluded by obstacles.
Solution Approach 2:
The system introduces map data as an intermediary information source to supplement direct sensor data. By combining real-time sensor inputs with pre-stored map information about intersection geometry and traffic patterns, the system can infer traffic conditions in occluded areas where direct sensing is blocked by obstacles.
2Extent of automation
If the autonomous vehicle operates fully autonomously at intersections, then navigation can be automated, but the system lacks flexibility to adapt to complex traffic scenarios and occluded views
Solution Approach 1:
The system dynamically adjusts the level of automation and control based on the vehicle's current zone and traffic conditions. In the first zone with oncoming traffic and potential occlusions, the system maintains higher driver involvement. In the second and third zones with more predictable traffic patterns, the system increases autonomous control. This dynamic adaptation resolves the contradiction by allowing high automation where safe and driver input where adaptability is needed.
Solution Approach 2:
The system applies different control qualities to different spatial zones. Zone 1 (oncoming traffic) receives more conservative, driver-in-the-loop control. Zone 2 (cross traffic) and Zone 3 (protected turns) receive more aggressive autonomous control. This local differentiation allows the system to achieve high automation levels in safe zones while maintaining adaptability in complex zones.
3Measurement precision
If the vehicle defines multiple zones for different traffic scenarios, then control precision can be improved, but the system complexity increases
Solution Approach 1:
The system segments the intersection into three distinct zones based on traffic control device signals and map data. This segmentation provides precise control by allowing different maneuvers and safety parameters for each zone. The complexity is managed by using consistent zone-definition logic across all intersections, leveraging map data structures that already organize spatial information.
Solution Approach 2:
The zone-definition mechanism serves multiple functions: it determines control precision, selects appropriate sensing strategies, guides maneuver planning, and manages risk assessment. By creating a universal zone-based framework that handles all these functions, the system achieves high control precision without proportionally increasing complexity, as the same zone structure supports multiple control objectives.
Data Source
AI summary
Systems and method are provided for controlling a vehicle. In one embodiment, method includes: receiving, via one or more sensing devices, sensor data relating to an environment associated with the vehicle; determining, by a processor, at least one of a type of an intersection, a type of a traffic control device, and a signal of the traffic control device associated with an upcoming intersection based on at least one of the sensor data and map data; defining, by the processor, a first zone and a second zone of the upcoming intersection based on the at least one of the type of the intersection, the type of the traffic control device, and the signal of the traffic control device associated with an upcoming intersection; determining, by the processor, a current zone of the vehicle based on the first zone and the second zone and a position of the vehicle; and selectively controlling, by the processor, lateral movement and longitudinal movement of the vehicle based on a control method that evaluates the current zone, operator instructions, and autonomous control instructions when controlling the vehicle.