Learning Disturbances in Autonomous Excavation. Maeda, G. J., Rye, D. C., & Singh, S. P. N. In Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2012. Submitteddoi abstract bibtex Disturbances that arise in material removal by repeated attempts to track the same path have the particular characteristics of non-repetitive magnitudes, but nearly-repetitive or gradual gradient transitions. This paper proposes and validates Iterative Learning Control (ILC) with a PD-type learning function for this class of disturbance as a predictive controller for autonomous excavation. However, parameters of the PD learning function may require different tunings for different excavation conditions, and convergence can be slow when compared to changes in excavation dynamics. In order to improve convergence, a plant inversion learning function is reinterpreted as a disturbance observer in the iteration domain, effectively rendering a disturbance learning controller (DLC). A hydraulic mini-excavator was used to evaluate experimentally the performance of the conventional ILC and the DLC against a robust controller. ILC achieved a desired cut profile with non-monotonic transients and DLC converged faster by learning disturbances directly from command discrepancies.
@INPROCEEDINGS{gjm.iros2012.draft,
author = {Guilherme J. Maeda and David C. Rye and Surya P. N. Singh},
title = {Learning Disturbances in Autonomous Excavation},
booktitle = {Proceedings of the International Conference on Intelligent Robots
and Systems ({IROS})},
year = {2012},
note = {Submitted},
abstract = {Disturbances that arise in material removal by repeated attempts to
track the same path have the particular characteristics of non-repetitive
magnitudes, but nearly-repetitive or gradual gradient transitions.
This paper proposes and validates Iterative Learning Control (ILC)
with a PD-type learning function for this class of disturbance as
a predictive controller for autonomous excavation. However, parameters
of the PD learning function may require different tunings for different
excavation conditions, and convergence can be slow when compared
to changes in excavation dynamics. In order to improve convergence,
a plant inversion learning function is reinterpreted as a disturbance
observer in the iteration domain, effectively rendering a disturbance
learning controller (DLC). A hydraulic mini-excavator was used to
evaluate experimentally the performance of the conventional ILC and
the DLC against a robust controller. ILC achieved a desired cut profile
with non-monotonic transients and DLC converged faster by learning
disturbances directly from command discrepancies.},
doi = {10.1109/IROS.2012.6385566},
pdf = {gjm.iros2012.draft.pdf},
review = {http://db.acfr.usyd.edu.au/download.php/Maeda2012_IROS_LearningDisturbances.pdf?id=2571}
}
Downloads: 0
{"_id":{"_str":"51fd4b4ac5b22c38760016ce"},"__v":34,"authorIDs":["25JLGLMgHDQdFcbEd","2pNN7j4TWs2sdPq2b","34dFKNX3cFW2RkuZi","35Xv7osbm3zXk62F8","3SKHrAB8wMRysGFy8","47GNnFb6EPKma3Srt","48H54WhqNYjnD95ui","4SntEAiXntKARkNgS","5462d4748a9aab071c0005c7","5T75juAmsAB4z6bD6","5WvQsNxqBRyW2RSQi","5e34214741f782de01000022","5e3426cb41f782de01000084","5e3429b441f782de010000b9","5e34312341f782de0100013e","5e34390b41f782de010001e6","5e34392441f782de010001eb","5e6b0e1e86bf9cde0100000e","5sfq2WJ4W5g8mskFe","6a8JHmpJfRqSEQkqb","6hGsP8HLkwinYXigD","6zbapqaBfYNicQRXv","7CkZJwcgcj75uyjun","7DA6BoSFi7tnffK8H","7WRSvEmwiLfubqe8f","8HnjdunXqJG4QDLAd","8ntKbqqhqJyvrfK6r","9zqTiopbnCKBBJEHw","B7m7NjLbfonZHkc6g","BifZh9Ad6N9fnehRi","CL6tPXijZ3hpfr78G","CmEkRJvYX5Tr4Pnfk","DExNFWbRJaceGfGum","DY3kZm8P2JayQgduy","EyvXqoGdM2qS93CN7","Fdd27HCHQMmQXfGLs","GqK42ji4y7PtPXZ3F","Gy3fvTPGQkczs42ez","HLcHzprYn3r3Xe84b","HdmdEWKvJektnYR7y","Hj7KYhXTskqMzhg7u","HzDPAyHXF2wTA7zGu","JHBPkDMYpmfwpcT8A","JMwRZPisoDhWDzWhm","K37JaQLteDSHdqyjx","K7AXubjaKLhA3pNTA","KqPDgQxE6zxpxX67e","LRjJSNBWHuWanhqNM","LjXJLGxM3QELAoaNP","Mc9S7iNhTFJWsRkeb","Mww7bu4yZkujgW5ns","NAGpXYkKmHQ29Mvjb","NKMyNZac6Y89jH6Qr","PZGS54s4e74ZKchZy","PcR3YBj9m6B3nvjG4","Q7eQ2ycHNYkfAF6nP","QR4SjtXbj8siaJg4K","QReRjpmwvPkeefcfK","QkREvvTHfouEvisjF","Rg9JW68PMYmedw2jv","RxHhvDjoid9t5F7uJ","Sju6B3BiCKw3CtwpM","TYZYfD6XShucnrAkf","XviLSraASaqofFM4Z","XwzuwxPG3rMWe5q7S","XzKRCGm3o924pvPcu","YHiJHk6hwmzPyR4nL","ZezE89A6WSniSjNvd","ZtbB3GZNz96JBnnL6","aFQJQukES2Lw58sS5","aPafrdEuKAitYSfiA","afAXjw75m99Km4Fgj","afwmjw9TTkZfveNzE","bNN2E3KLq5WFdzKTF","cfwHoA5cnQ6eGD4bg","dDWF4crzWnW8RyG9p","dFqdXn6WnDTzTnEqQ","dLkDhYcDM2PSSEZk3","dmJYK8FNXWAAu5G7T","dvJ37AfDNYzAuD9PK","eiYowsdjQ9Mcw2Thz","evxzRHu7G7fbeoibY","fid77jGJy9yzcHJr2","fuEkxmax5jFbtxCYy","gAmxy4SvWarbPBeTX","gFrSDrvd4JrFP9kTP","gXJZBJPrZddgZ7YoH","ggsiWBRuBugZgRE8f","gqQQ75hZq9ros28RR","h3u9YL2Ae2DNrQCqi","hiXcvvFucmwxJEZ9y","hth6XiDc9jGYzRe5H","i2DexC5F5rxsC5PHg","iELGk3WWqbGkdYzPc","ijX6hDPyFBq7xgoma","ip7PgT6GfbdZreojv","is7DZGXrEJDXNvotf","j6o4kAC79ZjvEeijw","jJbSbk2LoomLaPG7h","kTAMCAkfLFo4f89Gp","kXmyRRzRyEi5cz83e","kz4FwssxjbAeByCEF","nRtwjECYR2WAxoeFJ","oDxo3ZMAB4phpqr5o","p64zTgE7XqWDjvB7v","pHCFNdiRdm4dHD4JE","pJd6uJtiZnuhNGMpH","paBtjfzxNGmPkJgFy","pu6XsJacuRdqyidu3","qLFpKhtC29Rk9jeS8","rBLmXAceeFPWAntch","sHdkaG8cdJP4GriPy","tsgNGCAcyhTm8BeQB","u3sfcQ8RovYYpKjLb","uGrPMtPgNJq2bBX47","uHkfdT8WqEWJyDjRg","ucoBD8M4z8ezYE8bc","upFqY33vPBba6wxh8","v9z9AicS8PCAymgiR","vAQtv8TCRg4oNqGSn","vDknP8BNi6WY35SDp","vQekzHzAimvgtFT3G","vg9Go2zuYX2Xq8HJf","vve7zKuHuKZmDZ6FB","w4erytKzHZZj3bnbZ","wmuqnoGDizWJe8P2H","xGz64z5uDaXxM3ZHF","xSFFddhsMR36EEcYu","y52p2nvza87XinHws","yBp5Pq56pbsjD6f8H","z6nH83SNs79e3uH2u","zgA7uYAasRk8ezQ9e","zj2qr55FtWLxKhX9E","zsFBk8a7A7dEouo2u"],"author_short":["Maeda, G. J.","Rye, D. C.","Singh, S. P. N."],"bibbaseid":"maeda-rye-singh-learningdisturbancesinautonomousexcavation-2012","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Guilherme","J."],"propositions":[],"lastnames":["Maeda"],"suffixes":[]},{"firstnames":["David","C."],"propositions":[],"lastnames":["Rye"],"suffixes":[]},{"firstnames":["Surya","P.","N."],"propositions":[],"lastnames":["Singh"],"suffixes":[]}],"title":"Learning Disturbances in Autonomous Excavation","booktitle":"Proceedings of the International Conference on Intelligent Robots and Systems (IROS)","year":"2012","note":"Submitted","abstract":"Disturbances that arise in material removal by repeated attempts to track the same path have the particular characteristics of non-repetitive magnitudes, but nearly-repetitive or gradual gradient transitions. This paper proposes and validates Iterative Learning Control (ILC) with a PD-type learning function for this class of disturbance as a predictive controller for autonomous excavation. However, parameters of the PD learning function may require different tunings for different excavation conditions, and convergence can be slow when compared to changes in excavation dynamics. In order to improve convergence, a plant inversion learning function is reinterpreted as a disturbance observer in the iteration domain, effectively rendering a disturbance learning controller (DLC). A hydraulic mini-excavator was used to evaluate experimentally the performance of the conventional ILC and the DLC against a robust controller. ILC achieved a desired cut profile with non-monotonic transients and DLC converged faster by learning disturbances directly from command discrepancies.","doi":"10.1109/IROS.2012.6385566","pdf":"gjm.iros2012.draft.pdf","review":"http://db.acfr.usyd.edu.au/download.php/Maeda2012_IROS_LearningDisturbances.pdf?id=2571","bibtex":"@INPROCEEDINGS{gjm.iros2012.draft,\r\n author = {Guilherme J. Maeda and David C. Rye and Surya P. N. Singh},\r\n title = {Learning Disturbances in Autonomous Excavation},\r\n booktitle = {Proceedings of the International Conference on Intelligent Robots\r\n\tand Systems ({IROS})},\r\n year = {2012},\r\n note = {Submitted},\r\n abstract = {Disturbances that arise in material removal by repeated attempts to\r\n\ttrack the same path have the particular characteristics of non-repetitive\r\n\tmagnitudes, but nearly-repetitive or gradual gradient transitions.\r\n\tThis paper proposes and validates Iterative Learning Control (ILC)\r\n\twith a PD-type learning function for this class of disturbance as\r\n\ta predictive controller for autonomous excavation. However, parameters\r\n\tof the PD learning function may require different tunings for different\r\n\texcavation conditions, and convergence can be slow when compared\r\n\tto changes in excavation dynamics. In order to improve convergence,\r\n\ta plant inversion learning function is reinterpreted as a disturbance\r\n\tobserver in the iteration domain, effectively rendering a disturbance\r\n\tlearning controller (DLC). A hydraulic mini-excavator was used to\r\n\tevaluate experimentally the performance of the conventional ILC and\r\n\tthe DLC against a robust controller. ILC achieved a desired cut profile\r\n\twith non-monotonic transients and DLC converged faster by learning\r\n\tdisturbances directly from command discrepancies.},\r\n doi = {10.1109/IROS.2012.6385566},\r\n pdf = {gjm.iros2012.draft.pdf},\r\n review = {http://db.acfr.usyd.edu.au/download.php/Maeda2012_IROS_LearningDisturbances.pdf?id=2571}\r\n}\r\n\r\n","author_short":["Maeda, G. J.","Rye, D. C.","Singh, S. P. N."],"key":"gjm.iros2012.draft","id":"gjm.iros2012.draft","bibbaseid":"maeda-rye-singh-learningdisturbancesinautonomousexcavation-2012","role":"author","urls":{},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"http://robotics.itee.uq.edu.au/~spns/pubcache/SpnS_PubList.bib","downloads":0,"keywords":[],"search_terms":["learning","disturbances","autonomous","excavation","maeda","rye","singh"],"title":"Learning Disturbances in Autonomous Excavation","title_words":["learning","disturbances","autonomous","excavation"],"year":2012,"dataSources":["zNCf6MTxXnpkNN9Zz"]}