@article{2021_3C_imitation,
  title={Imitation Learning with Stability and Safety Guarantees},
  author={Yin, He and Seiler, Peter and Jin, Ming and Arcak, Murat},
  year={2021},
  note={IEEE Control Systems Letters}, 
  url_pdf={SafeIL2020.pdf},
  url_arXiv={https://arxiv.org/abs/2012.09293},
  keywords = {Control theory, Machine learning},
  abstract={A method is presented to synthesize neural network (NN) controllers with stability and safety guarantees through imitation learning. Convex stability and safety conditions are derived for linear time-invariant plant dynamics with NN controllers. The proposed approach merges Lyapunov theory with local quadratic constraints to bound the nonlinear activation functions in the NN. The safe imitation learning problem is formulated as an optimization problem with the goal of minimizing the imitation learning loss, and maximizing volume of the region of attraction associated with the NN controller, while enforcing the stability and safety conditions. An alternating direction method of multipliers based algorithm is proposed to solve the optimization. The method is illustrated on an inverted pendulum system and aircraft longitudinal dynamics.}}

{"_id":"XzBEkommhiDRQvajC","bibbaseid":"yin-seiler-jin-arcak-imitationlearningwithstabilityandsafetyguarantees-2021","author_short":["Yin, H.","Seiler, P.","Jin, M.","Arcak, M."],"bibdata":{"bibtype":"article","type":"article","title":"Imitation Learning with Stability and Safety Guarantees","author":[{"propositions":[],"lastnames":["Yin"],"firstnames":["He"],"suffixes":[]},{"propositions":[],"lastnames":["Seiler"],"firstnames":["Peter"],"suffixes":[]},{"propositions":[],"lastnames":["Jin"],"firstnames":["Ming"],"suffixes":[]},{"propositions":[],"lastnames":["Arcak"],"firstnames":["Murat"],"suffixes":[]}],"year":"2021","note":"IEEE Control Systems Letters","url_pdf":"SafeIL2020.pdf","url_arxiv":"https://arxiv.org/abs/2012.09293","keywords":"Control theory, Machine learning","abstract":"A method is presented to synthesize neural network (NN) controllers with stability and safety guarantees through imitation learning. Convex stability and safety conditions are derived for linear time-invariant plant dynamics with NN controllers. The proposed approach merges Lyapunov theory with local quadratic constraints to bound the nonlinear activation functions in the NN. The safe imitation learning problem is formulated as an optimization problem with the goal of minimizing the imitation learning loss, and maximizing volume of the region of attraction associated with the NN controller, while enforcing the stability and safety conditions. An alternating direction method of multipliers based algorithm is proposed to solve the optimization. The method is illustrated on an inverted pendulum system and aircraft longitudinal dynamics.","bibtex":"@article{2021_3C_imitation,\n title={Imitation Learning with Stability and Safety Guarantees},\n author={Yin, He and Seiler, Peter and Jin, Ming and Arcak, Murat},\n year={2021},\n note={IEEE Control Systems Letters}, \n url_pdf={SafeIL2020.pdf},\n url_arXiv={https://arxiv.org/abs/2012.09293},\n keywords = {Control theory, Machine learning},\n abstract={A method is presented to synthesize neural network (NN) controllers with stability and safety guarantees through imitation learning. Convex stability and safety conditions are derived for linear time-invariant plant dynamics with NN controllers. The proposed approach merges Lyapunov theory with local quadratic constraints to bound the nonlinear activation functions in the NN. The safe imitation learning problem is formulated as an optimization problem with the goal of minimizing the imitation learning loss, and maximizing volume of the region of attraction associated with the NN controller, while enforcing the stability and safety conditions. An alternating direction method of multipliers based algorithm is proposed to solve the optimization. The method is illustrated on an inverted pendulum system and aircraft longitudinal dynamics.}}\n\n","author_short":["Yin, H.","Seiler, P.","Jin, M.","Arcak, M."],"key":"2021_3C_imitation","id":"2021_3C_imitation","bibbaseid":"yin-seiler-jin-arcak-imitationlearningwithstabilityandsafetyguarantees-2021","role":"author","urls":{" pdf":"http://www.jinming.tech/papers/SafeIL2020.pdf"," arxiv":"https://arxiv.org/abs/2012.09293"},"keyword":["Control theory","Machine learning"],"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"article","biburl":"http://www.jinming.tech/papers/myref.bib","dataSources":["sTzDHHaipTZWjp8oe","Y64tp2HnDCfXgLdc5"],"keywords":["control theory","machine learning"],"search_terms":["imitation","learning","stability","safety","guarantees","yin","seiler","jin","arcak"],"title":"Imitation Learning with Stability and Safety Guarantees","year":2021,"downloads":1}