Autonomous Vehicle Rerouting Based on Traffic Reaction Cost
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in dynamically adjusting navigation routes to accommodate non-essential passenger requests without significantly impacting other vehicles or causing traffic inefficiencies, as existing systems struggle to balance user desires with the costs and impacts on other vehicles and traffic flow.
Innovation Solution
A computer-implemented method that determines positional data for autonomous vehicles, including geographic coordinates, speed, and lane position, to assess the impact of requested maneuvers on traffic flow, estimating costs based on historical data and traffic volume, and executing the lowest-cost option that meets user objectives while minimizing disruptions to other vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If autonomous vehicles execute non-essential route changes to accommodate passenger requests, then passenger satisfaction is improved, but traffic flow efficiency deteriorates due to increased disruptions and delays for other vehicles
Solution Approach 1:
The system performs preliminary analysis of requested route changes by simulating their potential impact on traffic flow before execution. The impact assessment module evaluates multiple scenarios and selects the lowest-cost option that minimizes disruptions to other vehicles while still accommodating non-essential passenger requests.
Solution Approach 2:
The system dynamically adjusts routing parameters based on real-time traffic conditions, vehicle density, and the nature of passenger requests. By changing parameters such as route selection, timing, and maneuver types, the system balances passenger satisfaction with minimal impact on overall traffic flow efficiency.
2Adaptability or versatility
If autonomous vehicles frequently adjust routes in response to passenger requests, then user flexibility is improved, but travel time increases due to suboptimal routing decisions
Solution Approach 1:
The system continuously monitors traffic conditions, vehicle positional data, and the outcomes of previous routing decisions. This feedback loop enables the system to learn from past experiences and make more informed routing choices that accommodate user flexibility while minimizing additional travel time caused by non-essential maneuvers.
Solution Approach 2:
The routing system dynamically adapts to changing traffic conditions and user requests in real-time. By continuously evaluating current traffic flow, vehicle positions, and request priorities, the system can make flexible routing decisions that minimize travel time while still providing user adaptability for non-essential requests.
3Ease of operation
If autonomous vehicles prioritize passenger requests over traffic flow optimization, then user needs are met, but fuel consumption increases due to inefficient maneuvers
Solution Approach 1:
The system evaluates multiple routing parameters including fuel consumption estimates, traffic conditions, and user request priorities. By dynamically adjusting these parameters and selecting the lowest-cost option, the system fulfills user needs while minimizing additional fuel consumption from non-essential maneuvers.
Solution Approach 2:
Before executing non-essential route changes, the system performs preliminary impact assessments that include estimating fuel consumption consequences. This allows the vehicle to prioritize requests that can be accommodated with minimal energy expenditure while still meeting user needs.
Data Source
AI summary
Aspects of the present invention determine positional data for each of a plurality of autonomous vehicles travelling on a common roadway that includes geographic coordinate location, vehicle speed, speed change and vehicle lane position data; determine a reaction value as an amount of change in positional data of a first autonomous vehicles caused in reaction to a causal change in positional data of a second of the autonomous vehicle; associate the reaction value to a volume of traffic flow at a time of occurrence; and, in response to a request for a change to positional data of a third autonomous vehicle that is similar to the causal change, estimate a cost of the request as a change to positional data of a fourth autonomous vehicles projected from the reaction value in proportion to a similarity of a traffic flow volume.