Introduction and Problem Statement
Intersections are killing fields. 40% of crashes, 50% of serious collisions, 20% of fatalities occur in intersections. Bay Area fatalities increased 43% between 2010 and 2016 to reach 455 killed, of which, in San Francisco, 62% were cyclists or pedestrians. It is claimed that AVs will prevent 94% of all crashes involving human error with no sacrifice of mobility. However, current safety performance of AVs is far below that of human-driven cars. Responding to the road safety crisis, cities have launched Vision Zero (VZ) plans, seeking to eliminate traffic injuries and deaths through physical modification of the road infrastructure to reduce vehicle mobility and create a safe passage for cyclists.
However, crashes happen because drivers, cyclists and pedestrians face uncertainties that lead to wrong decisions and end in crashes. Spatial uncertainty occurs when an agent at an intersection is unable to detect other agents; temporal uncertainty occurs when the agent is unable to accurately predict its own and others right of way. These challenges are not fully addressed by the road diet and road redesign prescribed in VZ plans. Nor are they handled by AVs that only rely on on-board sensors.
Intersection conflict can be eliminated by the implementation of intelligent intersections which can generate I2V messages that give complete phase information, predict the signal phase and timing in the next cycle, accurately assess the occupancy of blind zones, and warn of the danger from traffic signal violators.
Research Team
The principal investigator for this project was Offer Grembek of UC Berkeley. Other team members from UC Berkeley included, Alex Kurzhanskiy, Aditya Medury, Pravin Varaiya, Mengqiao Yu, and Asfand Siddiqui of Caltrans.
Partners
We would like to express great appreciation to our colleagues Ching-Yao Chan, Christopher Flores and Steven Shladover for their comments and ideas.
This research was sponsored by the Division of Research, Innovation and System Information (DRISI) of the California Department of Transportation.
Objective
Discuss advantages of intelligent intersections.
Status, Conclusions and Recommendations
Intersections present a very demanding environment for all the parties involved. Challenges arise from complex vehicle trajectories; the absence of lane markings to guide vehicles; split phases that prevent determining who has the right of way; invisible vehicle approaches; illegal movements; simultaneous interactions among pedestrians, bicycles and vehicles. Unsurprisingly, most demonstrations of AVs are on freeways; but the full potential of automated vehicles – personalized transit, driverless taxis, delivery vehicles – can only be realized when AVs can sense the intersection environment to safely and efficiently maneuver through intersections. As is evident from intersection incidents with Google, Uber and Tesla AVs, their performance can be improved.
Any connected vehicle (CV) with Advanced Driving Assistance System (ADAS) or an AV can form a real-time map of an intersection, provided that its on-board sensing capability is augmented by infrastructure sensors that
- capture all vehicle movements in the intersection;
- provide full signal phase information;
- indicate vehicle encroachment on bicycle and pedestrian movements; and
- detect hazardous illegal movements.
We refer to an intersection capable of providing all this functionality as an Intelligent Intersection. Intelligent Intersection requires the following algorithms:
- analysis of intersection geometry to identify possible maneuvers, conflicts and blind zones;
- computation of blind zone activation likelihood, given a traffic pattern and signal timing;
- classification of conflicts and blind zones by their importance;
- computation of optimal and minimal viable sensor placements in the intersection to ensure desired coverage of blind zones;
- interpretation of sensor readings to determine traffic presence and dynamics in the blind zones; and
- prediction of signal phase duration for adaptive and actuated signals.
Additionally, we must be able to quantify intersection’s safety and mobility performance. All these algorithms will be implemented in an open-source software suite called Intelligent Intersection Toolbox [1] that we started developing in the course of this project. The impacts of this development will include:
- Cities will be given a tool to evaluate performance of their signalized intersections. In particular, compare potential improvements resulting from VZ plans with those provided by Intelligent Intersection.
- Caltrans and DMV are unavoidably getting more engaged in the regulation (i.e. design, testing and modifying the rules of deployment) of AVs in California. In most intersections safe operation of AVs will require augmentation of their capabilities with infrastructure-based sensing. Such sensing capability must be provided by Caltrans and local transportation authorities both because they own and operate the intersection and because this capability will be provided to all AVs. This project is a step towards specifying what these sensing capabilities should be.
For AV makers it is important to know, which intersections have hidden dangers, such as blind zones. Knowledge of blind zones improves AV’s safety. Additional real-time information about presence of agents in blind zones improves AV’s efficiency.
Related Content
content