Autonomous Vehicle Maneuver Control Using Decentralized V2X Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in reacting timely and appropriately to dangerous situations due to limitations in maneuver alternatives, leading to potential accidents, especially when centralized control approaches fail to meet safety specifications.
Innovation Solution
A decentralized control approach using Vehicle-to-Everything (V2X) communications allows vehicles to exchange location information and negotiate maneuver conflicts without a central coordinator, enabling cooperative awareness and safer decision-making through a safety driving model that assesses and prioritizes potential maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a centralized control approach is used to coordinate vehicle maneuvers, then safety assessment can be performed, but the system complexity increases and reaction time is delayed
Solution Approach 1:
The patent segments the centralized safety assessment function into distributed components at each vehicle. Each vehicle independently executes the safety driving model to assess its own maneuver options, eliminating the need for a central coordinator and reducing system complexity while maintaining safety assessment capability
Solution Approach 2:
Instead of having a central system assess safety for all vehicles, the patent inverts the approach by having each vehicle assess its own safety. This decentralized inversion reduces communication overhead and system complexity while improving reaction time
2Reliability
If a centralized control approach is used to coordinate vehicle maneuvers, then safety assessment can be performed, but the reaction time is delayed
Solution Approach 1:
The safety assessment function is segmented and executed locally at each vehicle simultaneously, rather than sequentially through a central system. This parallel execution dramatically reduces the time required for safety assessment and maneuver coordination
Solution Approach 2:
Vehicles pre-compute and share their maneuver lists with other vehicles in advance. This preliminary action allows receiving vehicles to immediately assess safety without waiting for central coordination, reducing reaction time while maintaining comprehensive safety evaluation
3Reliability
If driving models constrain vehicle reactions to guarantee safe behavior, then accident avoidance is improved, but the ability to respond timely in dangerous situations is reduced
Solution Approach 1:
The safety driving model generates multiple potential maneuvers (excessive action) rather than a single constrained response. This allows the vehicle to have pre-prepared alternative actions ready for immediate execution, improving both safety through multiple options and reaction speed through pre-computation
Solution Approach 2:
The system performs preliminary safety assessment and maneuver generation in advance, creating a ready pool of safe maneuver options. When a dangerous situation arises, the vehicle can immediately select and execute from pre-vetted options, eliminating delay while maintaining safety guarantees
Data Source
AI summary
A controller for an autonomous vehicle may include: one or more processors configured to: determine a maneuver planned for the vehicle based on a safety driving model and based on a first message from a network component external to the vehicle, the first message including a respective assessment for each proposed maneuver of at least two maneuvers proposed for the vehicle, and provide an in-vehicle instruction to perform the maneuver planned for the vehicle.