Connected Vehicle Control Using Multi-Timestep Input Coordination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advanced driver assistance systems (ADAS) struggle to maintain efficient average speeds and prevent temporary traffic jams, known as 'phantom jams,' which are caused by typical human driving behaviors.
Innovation Solution
A system of communicatively coupled vehicles that coordinate by transmitting projected control inputs for multiple future timesteps, allowing each vehicle to determine its own control inputs based on the inputs from other vehicles, thereby maintaining efficient average speeds and reducing the likelihood of slowdowns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If vehicles use traditional human driving behaviors, then individual vehicle operation is simple, but average speed decreases and phantom jams occur
Solution Approach 1:
The system segments the traffic flow control into individual vehicle control units, where each vehicle independently determines its control inputs based on received projected control inputs from other vehicles. This segmentation allows distributed decision-making that maintains high average speeds while preventing phantom jams without requiring a centralized complex control system.
Solution Approach 2:
Each vehicle receives and processes projected control inputs from other vehicles for future timesteps before making its own control decisions. This preliminary action of anticipating other vehicles' movements allows each vehicle to proactively adjust its control inputs to maintain efficient traffic flow and prevent phantom jams before they occur.
2Productivity
If vehicles coordinate control inputs for multiple future timesteps, then traffic efficiency improves, but computational requirements increase
Solution Approach 1:
The system computes projected control inputs for multiple future timesteps, but only applies the control input for the next immediate timestep to vehicle actuation. This partial action approach allows vehicles to benefit from multi-timestep coordination planning while keeping the actual actuation simple and computationally efficient, avoiding the burden of continuously re-computing and re-actuating multiple future control inputs.
3Reliability
If centralized control is implemented, then coordination is improved, but system complexity and communication overhead increase
Solution Approach 1:
Each vehicle independently determines its own control inputs by processing received projected control inputs from other vehicles, rather than receiving direct control commands from a centralized system. This self-service approach maintains reliable coordination through distributed intelligence while avoiding the complexity and communication overhead of a centralized control architecture.
Data Source
AI summary
A plurality of vehicles can be communicatively coupled with each other. Each vehicle can include a vehicle computer programmed to receive a transmission including non-ego projected control inputs for at least one of the other vehicles, determine ego projected control inputs for the vehicle based on the non-ego projected control inputs, actuate the vehicle according to the ego projected control input paired with a next timestep after a current time, and transmit the ego projected control inputs to at least one of the other vehicles. The transmission originates from the at least one of the other vehicles. The non-ego projected control inputs are paired with respective future timesteps starting at the next timestep. The ego projected control inputs are paired with the respective future timesteps starting at the next timestep.