Autonomous Vehicle Interaction Control in Mixed-Autonomy Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in effectively interacting and coordinating with vehicles of varying levels of autonomy, as existing systems lack the ability to dynamically adjust driving parameters based on the capabilities and behaviors of surrounding vehicles, leading to inefficiencies and safety concerns in traffic management.
Innovation Solution
The implementation of a Vehicle Autonomous Driving System (VADS) that uses sensor information and Vehicle-to-Vehicle (V2V) communications to determine an Autonomous Capability Metric (ACM) for nearby vehicles, allowing for dynamic adjustment of driving parameters such as speed, separation distance, and following distance based on the level of autonomy and behavior of surrounding vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If autonomous vehicles maintain fixed driving parameters, then system simplicity is preserved, but traffic efficiency and safety deteriorate due to inability to adapt to varying vehicle capabilities
Solution Approach 1:
The system dynamically adjusts driving parameters (speed, separation distance, following distance) based on real-time assessment of surrounding vehicles' autonomy levels. The autonomous vehicle transitions from static parameter management to dynamic parameter adjustment, adapting its behavior to match the capabilities of nearby vehicles detected through sensors and V2V communications.
Solution Approach 2:
The system changes multiple driving parameters simultaneously based on the autonomous capability metric of surrounding vehicles. When a vehicle with lower autonomy is detected, the system increases separation distance, reduces speed, and adjusts following distance to compensate for the other vehicle's limited capabilities, thereby resolving the contradiction between adaptability and system complexity.
2Reliability
If autonomous vehicles increase separation distance to ensure safety, then collision risk is reduced, but traffic throughput and efficiency deteriorate
Solution Approach 1:
The separation distance is dynamically adjusted based on the autonomy level of surrounding vehicles. When fully autonomous vehicles are detected, the system reduces separation distance to maximize traffic throughput. When vehicles with lower autonomy levels are detected, the system increases separation distance to maintain safety, thereby resolving the contradiction between safety and efficiency through real-time parameter adaptation.
Solution Approach 2:
The system applies different separation distances to different surrounding vehicles based on their individual autonomy capabilities. Rather than using a uniform safety margin for all vehicles, the system tailors the separation distance to each detected vehicle's autonomous capability metric, allowing closer proximity to high-autonomy vehicles while maintaining larger distances from low-autonomy vehicles.
3Reliability
If autonomous vehicles communicate extensively with surrounding vehicles, then coordination and safety improve, but communication overhead and system complexity increase
Solution Approach 1:
The system extracts only the essential information needed for safe interaction from V2V communications - specifically the autonomous capability metric of surrounding vehicles. Rather than processing all possible communication data, the system focuses on extracting the critical autonomy level information required to adjust driving parameters, thereby reducing communication overhead while maintaining coordination effectiveness.
Solution Approach 2:
The autonomous capability metric serves as an intermediary that simplifies complex V2V communication data into a single actionable parameter. This metric acts as a mediator between the diverse capabilities of different vehicles and the driving parameter adjustment system, reducing the complexity of direct multi-vehicle coordination while maintaining reliability.
4Productivity
If autonomous vehicles adjust driving parameters dynamically, then traffic efficiency improves, but prediction difficulty and control complexity increase
Solution Approach 1:
The system performs preliminary assessment of surrounding vehicles' autonomy levels through sensors and V2V communications before adjusting driving parameters. By detecting and classifying the autonomous capability metric in advance, the system establishes a foundation for predictable parameter adjustments, reducing the difficulty of behavior prediction while enabling efficient traffic flow adaptation.
Data Source
AI summary
Methods, devices and systems enable controlling an autonomous vehicle by identifying a vehicle that is within a threshold distance of the autonomous vehicle, determining an autonomous capability metric (ACM) the identified vehicle, determining whether the ACM of the identified vehicle is greater than a first threshold, determining whether the ACM of the identified vehicle is less than a second threshold, and adjusting a driving parameter of the autonomous vehicle so that the autonomous vehicle is more or less reliant on the capabilities of the identified vehicle based on whether the ACM of the identified vehicle exceeds the thresholds.