BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:brazovayeye

The blue social bookmark and publication sharing system.

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Evolution of the Driving Styles of Anticipatory Agent Remotely Operating a Scaled Model of Racing Car

by: Ivan Tanev, Michal Joachimczak, Hitoshi Hemmi, and Katsunori Shimohara

In: Proceedings of the 2005 IEEE Congress on Evolutionary Computation CEC-2005, Vol. 2 Edinburgh: IEEE (February 2005) , p. 1891--1898.

Abstract

We present an approach for automated evolutionary design of driving agent, able to remotely operate a scale model of racing car running in a fastest possible way. The agent's actions are conveyed to the car via standard radio control transmitter. The agent perceives the environment from a live video feedback of an overhead camera. In order to cope with the inherent video feed latency, which renders even the straightforward tasks of following simple routes unsolvable, we implement an anticipatory modeling - the agent considers its current actions based on anticipated intrinsic rather than currently available, outdated state of the car and its surrounding. The driving style i.e. the driving line combined with the speed at which the car travels along this line is first evolved offline on a software simulator of the car and then adapted online to the real world. Experimental results demonstrate that on long runs the agent'soperated car is only marginally slower than a humanoperated one, while the consistence of lap times posted by the evolved driving style of the agent is better than that of a human. This work can be viewed as a step towards the development of a framework for automated design of the controllers of remotely operated vehicles capable to find an optimal solution to various tasks in different traffic situations and road conditions.

BibTeX record

@inproceedings{tanev:2005:CEC,
  abstract = {We present an approach for automated evolutionary
                 design of driving agent, able to remotely operate a
                 scale model of racing car running in a fastest possible
                 way. The agent's actions are conveyed to the car via
                 standard radio control transmitter. The agent perceives
                 the environment from a live video feedback of an
                 overhead camera. In order to cope with the inherent
                 video feed latency, which renders even the
                 straightforward tasks of following simple routes
                 unsolvable, we implement an anticipatory modeling - the
                 agent considers its current actions based on
                 anticipated intrinsic (rather than currently available,
                 outdated) state of the car and its surrounding. The
                 driving style (i.e. the driving line combined with the
                 speed at which the car travels along this line) is
                 first evolved offline on a software simulator of the
                 car and then adapted online to the real world.
                 Experimental results demonstrate that on long runs the
                 agent'soperated car is only marginally slower than a
                 humanoperated one, while the consistence of lap times
                 posted by the evolved driving style of the agent is
                 better than that of a human. This work can be viewed as
                 a step towards the development of a framework for
                 automated design of the controllers of remotely
                 operated vehicles capable to find an optimal solution
                 to various tasks in different traffic situations and
                 road conditions.},
  added-at = {2008-06-19T17:46:40.000+0200},
  address = {Edinburgh},
  author = {Tanev, Ivan and Joachimczak, Michal and Hemmi, Hitoshi and Shimohara, Katsunori},
  biburl = {http://www.bibsonomy.org/bibtex/255e1991ffb29cc47c17580275f7dce2c/brazovayeye},
  booktitle = {Proceedings of the 2005 IEEE Congress on Evolutionary
                 Computation (CEC-2005)},
  email = {itanev@mail.doshisha.ac.jp},
  interhash = {63c09042c28dd0d435ff53578eb6432b},
  intrahash = {55e1991ffb29cc47c17580275f7dce2c},
  isbn = {0-7803-9363-5},
  keywords = {algorithms, genetic programming},
  month = {2-4 September},
  notes = {CEC 2005 - A joint meeting of the IEEE, the EPS, and
                 the IEE.},
  pages = {1891--1898},
  publisher = {IEEE},
  size = {8 pages},
  timestamp = {2008-06-19T17:46:40.000+0200},
  title = {Evolution of the Driving Styles of Anticipatory Agent
                 Remotely Operating a Scaled Model of Racing Car},
  volume = 2,
  year = 2005
}

Endnote record

%0 Conference Paper
%1 tanev:2005:CEC
%A Tanev, Ivan
%A Joachimczak, Michal
%A Hemmi, Hitoshi
%A Shimohara, Katsunori
%B Proceedings of the 2005 IEEE Congress on Evolutionary
                 Computation (CEC-2005)
%@ 0-7803-9363-5
%C Edinburgh
%D 2005
%I IEEE
%K 
%P 1891--1898
%T Evolution of the Driving Styles of Anticipatory Agent
                 Remotely Operating a Scaled Model of Racing Car
%V 2
%X We present an approach for automated evolutionary
                 design of driving agent, able to remotely operate a
                 scale model of racing car running in a fastest possible
                 way. The agent's actions are conveyed to the car via
                 standard radio control transmitter. The agent perceives
                 the environment from a live video feedback of an
                 overhead camera. In order to cope with the inherent
                 video feed latency, which renders even the
                 straightforward tasks of following simple routes
                 unsolvable, we implement an anticipatory modeling - the
                 agent considers its current actions based on
                 anticipated intrinsic (rather than currently available,
                 outdated) state of the car and its surrounding. The
                 driving style (i.e. the driving line combined with the
                 speed at which the car travels along this line) is
                 first evolved offline on a software simulator of the
                 car and then adapted online to the real world.
                 Experimental results demonstrate that on long runs the
                 agent'soperated car is only marginally slower than a
                 humanoperated one, while the consistence of lap times
                 posted by the evolved driving style of the agent is
                 better than that of a human. This work can be viewed as
                 a step towards the development of a framework for
                 automated design of the controllers of remotely
                 operated vehicles capable to find an optimal solution
                 to various tasks in different traffic situations and
                 road conditions.