UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
A Protocol for Mixed Autonomous and Human-Operated Vehicles at Intersections (2017)
Guni Sharon
and
Peter Stone
Connected and autonomous vehicle technology has advanced rapidly in recent years. These technologies create possibilities for highly efficient, AI-based, transportation systems. One such system is the Autonomous Intersection Management (AIM), an intersection management protocol designed for the time when all vehicles are fully autonomous and connected. Experts, however, anticipate a long transition period during which human and autonomously operated vehicles will coexist. Unfortunately, AIM has been shown to provide little or no improvement over today's traffic signals when less than 90 percent of the vehicles are autonomous, making AIM ineffective for a large portion of the transition period. This paper introduces a new protocol denoted Hybrid Autonomous Intersection Management (HIM), that is applicable as long as AIM is applicable and the infrastructure is able to sense approaching vehicles. Our experiments show that this protocol can decrease traffic delay for autonomous vehicles even at 1 percent technology penetration rate.
View:
PDF
,
PS
,
HTML
Citation:
In
Proceedings of the 2nd International Workshop on Agent-based modeling of urban systems (ABMUS-2017)
, Sao Paulo, Brazil, May 2017.
Bibtex:
@inproceedings{ABMUS17-Sharon, title={A Protocol for Mixed Autonomous and Human-Operated Vehicles at Intersections}, author={Guni Sharon and Peter Stone}, booktitle={Proceedings of the 2nd International Workshop on Agent-based modeling of urban systems (ABMUS-2017)}, month={May}, address={Sao Paulo, Brazil}, url="http://www.cs.utexas.edu/users/ai-lab?sharon:abmus17", year={2017} }
Presentation:
Slides (PPT)
People
Guni Sharon
Postdoctoral Fellow
gunisharon [at] gmail com
Peter Stone
Faculty
pstone [at] cs utexas edu
Areas of Interest
Autonomous Traffic Management
Multiagent Systems
Labs
Learning Agents