Sensorless but not senseless

Prediction in evolutionary car racing

Hugo Marques, Julian Togelius, Magdalena Kogutowska, Owen Holland, Simon M. Lucas

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    In this paper we try to develop predictors in order to drive a simulated car around a track without the most recent sensor data. In order to test the predictive abilities of our car we developed two experiments: one where the sensor data was interrupted for a certain time and another where the sensor data is constantly delayed by a certain amount. The predictors are based on neural networks, and we compare backpropagation and evolutionary computation as methods of training these. In the end we found that predictors with good driving performance do not sample the set of predictors which minimize the prediction error in the sensors.

    Original languageEnglish (US)
    Title of host publicationProceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007
    Pages370-377
    Number of pages8
    DOIs
    StatePublished - 2007
    Event1st IEEE Symposium on Artificial Life, IEEE-ALife'07 - Honolulu, HI, United States
    Duration: Apr 1 2007Apr 5 2007

    Other

    Other1st IEEE Symposium on Artificial Life, IEEE-ALife'07
    CountryUnited States
    CityHonolulu, HI
    Period4/1/074/5/07

    Fingerprint

    Railroad cars
    Sensors
    Railroad tracks
    Backpropagation
    Evolutionary algorithms
    Neural networks
    Experiments

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Biochemistry, Genetics and Molecular Biology(all)

    Cite this

    Marques, H., Togelius, J., Kogutowska, M., Holland, O., & Lucas, S. M. (2007). Sensorless but not senseless: Prediction in evolutionary car racing. In Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007 (pp. 370-377). [4218909] https://doi.org/10.1109/ALIFE.2007.367819

    Sensorless but not senseless : Prediction in evolutionary car racing. / Marques, Hugo; Togelius, Julian; Kogutowska, Magdalena; Holland, Owen; Lucas, Simon M.

    Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007. 2007. p. 370-377 4218909.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Marques, H, Togelius, J, Kogutowska, M, Holland, O & Lucas, SM 2007, Sensorless but not senseless: Prediction in evolutionary car racing. in Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007., 4218909, pp. 370-377, 1st IEEE Symposium on Artificial Life, IEEE-ALife'07, Honolulu, HI, United States, 4/1/07. https://doi.org/10.1109/ALIFE.2007.367819
    Marques H, Togelius J, Kogutowska M, Holland O, Lucas SM. Sensorless but not senseless: Prediction in evolutionary car racing. In Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007. 2007. p. 370-377. 4218909 https://doi.org/10.1109/ALIFE.2007.367819
    Marques, Hugo ; Togelius, Julian ; Kogutowska, Magdalena ; Holland, Owen ; Lucas, Simon M. / Sensorless but not senseless : Prediction in evolutionary car racing. Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007. 2007. pp. 370-377
    @inproceedings{69ec10df151d46c283b16acd3616f267,
    title = "Sensorless but not senseless: Prediction in evolutionary car racing",
    abstract = "In this paper we try to develop predictors in order to drive a simulated car around a track without the most recent sensor data. In order to test the predictive abilities of our car we developed two experiments: one where the sensor data was interrupted for a certain time and another where the sensor data is constantly delayed by a certain amount. The predictors are based on neural networks, and we compare backpropagation and evolutionary computation as methods of training these. In the end we found that predictors with good driving performance do not sample the set of predictors which minimize the prediction error in the sensors.",
    author = "Hugo Marques and Julian Togelius and Magdalena Kogutowska and Owen Holland and Lucas, {Simon M.}",
    year = "2007",
    doi = "10.1109/ALIFE.2007.367819",
    language = "English (US)",
    isbn = "142440701X",
    pages = "370--377",
    booktitle = "Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007",

    }

    TY - GEN

    T1 - Sensorless but not senseless

    T2 - Prediction in evolutionary car racing

    AU - Marques, Hugo

    AU - Togelius, Julian

    AU - Kogutowska, Magdalena

    AU - Holland, Owen

    AU - Lucas, Simon M.

    PY - 2007

    Y1 - 2007

    N2 - In this paper we try to develop predictors in order to drive a simulated car around a track without the most recent sensor data. In order to test the predictive abilities of our car we developed two experiments: one where the sensor data was interrupted for a certain time and another where the sensor data is constantly delayed by a certain amount. The predictors are based on neural networks, and we compare backpropagation and evolutionary computation as methods of training these. In the end we found that predictors with good driving performance do not sample the set of predictors which minimize the prediction error in the sensors.

    AB - In this paper we try to develop predictors in order to drive a simulated car around a track without the most recent sensor data. In order to test the predictive abilities of our car we developed two experiments: one where the sensor data was interrupted for a certain time and another where the sensor data is constantly delayed by a certain amount. The predictors are based on neural networks, and we compare backpropagation and evolutionary computation as methods of training these. In the end we found that predictors with good driving performance do not sample the set of predictors which minimize the prediction error in the sensors.

    UR - http://www.scopus.com/inward/record.url?scp=34548732468&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34548732468&partnerID=8YFLogxK

    U2 - 10.1109/ALIFE.2007.367819

    DO - 10.1109/ALIFE.2007.367819

    M3 - Conference contribution

    SN - 142440701X

    SN - 9781424407019

    SP - 370

    EP - 377

    BT - Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007

    ER -