Connected autonomous intelligent agents (AIA) with enhanced decision making through machine learning can improve intersection performance and resilience for the transportation infrastructure. An agent is an autonomous decision maker whose decision making is determined internally but may be altered by interactions with the environment or other agents. Implementing agent-based modeling techniques to advance communication for more appropriate decision making will provide great benefits to autonomous vehicle technology.

A new algorithm is proposed to improve the decision-making process of autonomous vehicles and intelligent traffic signals, specifically at city like intersections. This is completed by understanding vehicle to vehicle (V2V), vehicle to infrastructure (V2I), and infrastructure to infrastructure (I2I) communication and using gathered data to ensure these agents make more appropriate decisions given the circumstances. These vehicles and signals are modeled to adapt to the common traffic flow of the intersection to ultimately find an optimum flow that will decrease average vehicle time to reduce inefficiency through each intersection. Considering each light and vehicle as an agent and utilizing communication between these agents will enable opportunity for data transmission. Improving agent based I2I communication and decision making will provide performance benefits to traffic flow capacities.

Evaluations were completed comparing intersections with fixed, coordinated, and adaptive timing signals. A fixed timing signal scenario is an intersection that uses a fixed maximum green light time with no opportunity for adjustment. The coordinated signals adapt and change light status based on the current light status of adjacent intersections. Adaptive signals add in a recognition of vehicle load in one direction and adjust their own status either based on the load at the individual intersection or a neighboring light status change with the intent to improve traffic flow. The three light setup scenarios were evaluated in various intersection grid setups to determine the improved efficiency of the city environment.


Agent Based Resilient Transportation Infrastructure With Surrogate Adaptive Networks

Division / Sponsors: 
Design Engineering Division and Computers & Information In Engineering Division


Paper Proceedings: https://asmedigitalcollection.asme.org/IDETC-CIE/IDETC-CIE2020/volume/83907

IDETC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.