Autonomous negotiation of freeway traffic

Zvi Shiller; Paolo Fiorini

doi:10.1117/12.228906

27 December 1995 Autonomous negotiation of freeway traffic

Zvi Shiller, Paolo Fiorini

Proceedings Volume 2592, Collision Avoidance and Automated Traffic Management Sensors; (1995) https://doi.org/10.1117/12.228906
Event: Photonics East '95, 1995, Philadelphia, PA, United States

Abstract

This paper presents a new approach for autonomously negotiating freeway traffic. It is based on the concept of Velocity Obstacle (VO) which maps the set of vehicle's velocities that would result in a collision with the other moving vehicles. The Velocity Obstacle is computed by measuring the relative velocities and positions of the neighboring vehicles. The vehicle then negotiates through the moving traffic by selecting velocities that are out of that set, but are directed towards the intermediate goal, which may be an exit ramp or another lane. The computation of the VO and the feasible velocity is repeated at regular time intervals, to account for the time evolution of the freeway traffic. This representation can be used to automatically plan the vehicle's motion, or to advise the driver of potential unsafe maneuvers. For automatic planning, we developed heuristics that select the safe velocity based on the location of the goal and the acceptable risk level of the maneuvering vehicle. For advisory purposes, we developed a graphic representation of the VO which clearly shows the unsafe velocities to be avoided at all times. Attempting to drive at an unsafe velocity may sound an alarm and suggest a corrective maneuver. This representation is computationally efficient, and is applicable for on-line planning and warning. The method is demonstrated in simulations for planning the trajectory of an automated vehicle in an Intelligent vehicle Highway System (IVHS) scenario.

Citation Download Citation

Zvi Shiller and Paolo Fiorini "Autonomous negotiation of freeway traffic", Proc. SPIE 2592, Collision Avoidance and Automated Traffic Management Sensors, (27 December 1995); https://doi.org/10.1117/12.228906

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available