Journal Papers

Authors Title Year Journal
G. Chou, N. Ozay, D. Berenson Learning Constraints from Locally-Optimal Demonstrations under Cost Function Uncertainty
[Abstract] [arXiv] [Cite]
2020 IEEE Robotics and Automation Letters (RA-L), with presentation at ICRA 2020
Abstract: We present an algorithm for learning parametric constraints from locally-optimal demonstrations, where the cost function being optimized is uncertain to the learner. Our method uses the Karush-Kuhn-Tucker (KKT) optimality conditions of the demonstrations within a mixed integer linear program (MILP) to learn constraints which are consistent with the local optimality of the demonstrations, by either using a known constraint parameterization or by incrementally growing a parameterization that is consistent with the demonstrations. We provide theoretical guarantees on the conservativeness of the recovered safe/unsafe sets and analyze the limits of constraint learnability when using locally-optimal demonstrations. We evaluate our method on high-dimensional constraints and systems by learning constraints for 7-DOF arm and quadrotor examples, show that it outperforms competing constraint-learning approaches, and can be effectively used to plan new constraint-satisfying trajectories in the environment.
BibTeX:
@inproceedings{Chou-RAL-20,
Author = "Glen Chou, Necmiye Ozay, and Dmitry Berenson", journal = {IEEE Robotics and Automation Letters (RA-L)},
Title = "Learning Constraints from Locally-Optimal Demonstrations under Cost Function Uncertainty",
year = {2020}
}
G. Chou, D. Berenson, N. Ozay Learning Constraints from Demonstrations with Grid and Parametric Representations (under review)
[Abstract] [Cite]
2019 International Journal of Robotics Research (IJRR) (under review)
Abstract: We extend the learning from demonstration paradigm by providing a method for learning unknown constraints shared across tasks, using demonstrations of the tasks, their cost functions, and knowledge of the system dynamics and control constraints. Given safe demonstrations, our method uses hit-and-run sampling to obtain lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a consistent representation of the unsafe set via solving an integer program. Our method generalizes across system dynamics and learns a guaranteed subset of the constraint. Additionally, by leveraging a known parameterization of the constraint, we modify our method to learn parametric constraints in high dimensions. We also provide theoretical analysis on what subset of the constraint and safe set can be learnable from safe demonstrations. We demonstrate our method on linear and nonlinear system dynamics, show that it can be modified to work with suboptimal demonstrations, and that it can also be used to learn constraints in a feature space.
G. Chou*, Y. E. Sahin*, L. Yang*, K. J. Rutledge, P. Nilsson, and N. Ozay Using control synthesis to generate corner cases: A case study on autonomous driving
[Abstract] [arXiv] [Cite] [Notes]
2018 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (ESWEEK-TCAD special issue)
Abstract: This paper employs correct-by-construction control synthesis, in particular controlled invariant set computations, for falsification. Our hypothesis is that if it is possible to compute a “large enough" controlled invariant set either for the actual system model or some simplification of the system model, interesting corner cases for other control designs can be generated by sampling initial conditions from the boundary of this controlled invariant set. Moreover, if falsifying trajectories for a given control design can be found through such sampling, then the controlled invariant set can be used as a supervisor to ensure safe operation of the control design under consideration. In addition to interesting initial conditions, which are mostly related to safety violations in transients, we use solutions from a dual game, a reachability game for the safety specification, to find falsifying inputs. We also propose optimization-based heuristics for input generation for cases when the state is outside the winning set of the dual game. To demonstrate the proposed ideas, we consider case studies from basic autonomous driving functionality, in particular, adaptive cruise control and lane keeping. We show how the proposed technique can be used to find interesting falsifying trajectories for classical control designs like proportional controllers, proportional integral controllers and model predictive controllers, as well as an open source real-world autonomous driving package.
BibTeX:
@article{Chou-et-al-Journal-18,
Author = "Glen Chou, Yunus E. Sahin, Liren Yang, Kwesi J. Rutledge, and Necmiye Ozay", journal = {IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (ESWEEK-TCAD special issue)},
Title = "Using control synthesis to generate corner cases: A case study on autonomous driving",
year = {2018}
}
Notes: Also presented at 2018 University of Michigan Engineering Graduate Symposium; won Emerging Research Social Impact award.


Peer-Reviewed Conference Papers

Authors Title Year Conference
G. Chou, N. Ozay, D. Berenson Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations
[Abstract] [arXiv] [Cite]
2020 Proceedings of Robotics: Science and Systems (RSS) XVI
Abstract: We present a method for learning multi-stage tasks from demonstrations by learning the logical structure and atomic propositions of a consistent linear temporal logic (LTL) formula. The learner is given successful but potentially suboptimal demonstrations, where the demonstrator is optimizing a cost function while satisfying the LTL formula, and the cost function is uncertain to the learner. Our algorithm uses the Karush-Kuhn-Tucker (KKT) optimality conditions of the demonstrations together with a counterexample-guided falsification strategy to learn the atomic proposition parameters and logical structure of the LTL formula, respectively. We provide theoretical guarantees on the conservativeness of the recovered atomic proposition sets, as well as completeness in the search for finding an LTL formula consistent with the demonstrations. We evaluate our method on high-dimensional nonlinear systems by learning LTL formulas explaining multi-stage tasks on 7-DOF arm and quadrotor systems and show that it outperforms competing methods for learning LTL formulas from positive examples.
BibTeX:
@inproceedings{Chou-CoRL-19,
Author = "Glen Chou, Necmiye Ozay, and Dmitry Berenson", journal = {Proceedings of Robotics: Science and Systems (RSS) XVI},
Title = "Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations",
year = {2020}
}
C. Knuth, G. Chou, N. Ozay, D. Berenson Inferring Obstacles and Path Validity from Visibility-Constrained Demonstrations
[Abstract] [arXiv] [Cite]
2020 Proceedings of the 14th International Workshop on the Algorithmic Foundations of Robotics (WAFR)
Abstract: Many methods in learning from demonstration assume that the demonstrator has knowledge of the full environment. However, in many scenarios, a demonstrator only sees part of the environment and they continuously replan as they gather information. To plan new paths or to reconstruct the environment, we must consider the visibility constraints and replanning process of the demonstrator, which, to our knowledge, has not been done in previous work. We consider the problem of inferring obstacle configurations in a 2D environment from demonstrated paths for a point robot that is capable of seeing in any direction but not through obstacles. Given a set of \textit{survey points}, which describe where the demonstrator obtains new information, and a candidate path, we construct a Constraint Satisfaction Problem (CSP) on a cell decomposition of the environment. We parameterize a set of obstacles corresponding to an assignment from the CSP and sample from the set to find valid environments. We show that there is a probabilistically-complete, yet not entirely tractable, algorithm that can guarantee novel paths in the space are unsafe or possibly safe. We also present an incomplete, but empirically-successful, heuristic-guided algorithm that we apply in our experiments to 1) planning novel paths and 2) recovering a probabilistic representation of the environment.
BibTeX:
@inproceedings{Knuth-WAFR-20,
Author = "Craig Knuth, Glen Chou, Necmiye Ozay, and Dmitry Berenson", journal = {Proceedings of the 14th International Workshop on the Algorithmic Foundations of Robotics (WAFR)},
Title = "Inferring Obstacles and Path Validity from Visibility-Constrained Demonstrations",
year = {2020}
}
G. Chou, N. Ozay, D. Berenson Learning Parametric Constraints in High Dimensions from Demonstrations
[Abstract] [arXiv] [Cite]
2019 Proceedings of the 3rd Conference on Robot Learning (CoRL)
Abstract: We present a scalable algorithm for learning parametric constraints in high dimensions from safe expert demonstrations. To reduce the ill-posedness of the constraint recovery problem, our method uses hit-and-run sampling to generate lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a representation of the unsafe set that is compatible with the data by solving an integer program in that representation's parameter space. Our method can either leverage a known parameterization or incrementally grow a parameterization while remaining consistent with the data, and we provide theoretical guarantees on the conservativeness of the recovered unsafe set. We evaluate our method on high-dimensional constraints for high-dimensional systems by learning constraints for 7-DOF arm, quadrotor, and planar pushing examples, and show that our method outperforms baseline approaches.
BibTeX:
@inproceedings{Chou-CoRL-19,
Author = "Glen Chou, Necmiye Ozay, and Dmitry Berenson", journal = {Proceedings of the 3rd Conference on Robot Learning (CoRL)},
Title = "Learning Parametric Constraints in High Dimensions from Demonstration",
year = {2019}
}
G. Chou, D. Berenson, N. Ozay Learning Constraints from Demonstrations
[Abstract] [arXiv] [Cite] [Notes]
2018 Proceedings of the 13th International Workshop on the Algorithmic Foundations of Robotics (WAFR)
Abstract: We extend the learning from demonstration paradigm by providing a method for learning unknown constraints shared across tasks, using demonstrations of the tasks, their cost functions, and knowledge of the system dynamics and control constraints. Given safe demonstrations, our method uses hit-and-run sampling to obtain lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a consistent representation of the unsafe set via solving an integer program. Our method generalizes across system dynamics and learns a guaranteed subset of the constraint. We also provide theoretical analysis on what subset of the constraint can be learnable from safe demonstrations. We demonstrate our method on linear and nonlinear system dynamics, show that it can be modi ed to work with suboptimal demonstrations, and that it can also be used to solve a transfer learning task.
BibTeX:
@inproceedings{Chou-WAFR-18,
Author = "Glen Chou, Dmitry Berenson, and Necmiye Ozay", journal = {Proceedings of the 13th International Workshop on the Algorithmic Foundations of Robotics (WAFR)},
Title = "Learning Constraints from Demonstration",
year = {2018}
}
Notes: Invited to IJRR special issue.
G. Chou*, Y. E. Sahin*, L. Yang*, K. J. Rutledge, P. Nilsson, and N. Ozay Using control synthesis to generate corner cases: A case study on autonomous driving
[Abstract] [arXiv] [Cite] [Notes]
2018 Proceedings of the ACM SIGBED International Conference on Embedded Software (EMSOFT)
Abstract: This paper employs correct-by-construction control synthesis, in particular controlled invariant set computations, for falsification. Our hypothesis is that if it is possible to compute a “large enough" controlled invariant set either for the actual system model or some simplification of the system model, interesting corner cases for other control designs can be generated by sampling initial conditions from the boundary of this controlled invariant set. Moreover, if falsifying trajectories for a given control design can be found through such sampling, then the controlled invariant set can be used as a supervisor to ensure safe operation of the control design under consideration. In addition to interesting initial conditions, which are mostly related to safety violations in transients, we use solutions from a dual game, a reachability game for the safety specification, to find falsifying inputs. We also propose optimization-based heuristics for input generation for cases when the state is outside the winning set of the dual game. To demonstrate the proposed ideas, we consider case studies from basic autonomous driving functionality, in particular, adaptive cruise control and lane keeping. We show how the proposed technique can be used to find interesting falsifying trajectories for classical control designs like proportional controllers, proportional integral controllers and model predictive controllers, as well as an open source real-world autonomous driving package.
BibTeX:
@inproceedings{Chou-et-al-EMSOFT-18,
Author = "Glen Chou, Yunus E. Sahin, Liren Yang, Kwesi J. Rutledge, and Necmiye Ozay", journal = {Proceedings of the ACM SIGBED International Conference on Embedded Software (EMSOFT)},
Title = "Using control synthesis to generate corner cases: A case study on autonomous driving",
year = {2018}
}
Notes: Also presented at 2018 University of Michigan Engineering Graduate Symposium; won Emerging Research Social Impact award.
G. Chou, N. Ozay, D. Berenson Incremental Segmentation of ARX Models
[Abstract] [PDF] [Cite]
2018 Proceedings of the 18th IFAC Symposium on System Identification (SYSID)
Abstract: We consider the problem of incrementally segmenting auto-regressive models with exogenous inputs (ARX models) when the data is received sequentially at run-time. In particular, we extend a recently proposed dynamic programming based polynomial-time algorithm for offline (batch) ARX model segmentation to the incremental setting. The new algorithm enables sequential updating of the models, eliminating repeated computation, while remaining optimal. We also show how certain noise bounds can be used to detect switches automatically at run-time. The efficiency of the approach compared to the batch method is illustrated on synthetic and real data.
BibTeX:
@inproceedings{Chou-SYSID-18,
Author = "Glen Chou, Necmiye Ozay, and Dmitry Berenson", journal = {Proceedings of the 18th IFAC Symposium on System Identification (SYSID)},
Title = "Incremental Segmentation of ARX Models",
year = {2018}
}
A. Dhinakaran*, M. Chen*, G. Chou, J. C. Shih, C. J. Tomlin A Hybrid Framework for Multi-Vehicle Collision Avoidance
[Abstract] [arXiv] [Cite]
2017 Proceedings of the 57th IEEE Conference on Decision and Control (CDC)
Abstract: With the recent surge of interest in UAVs for civilian services, the importance of developing tractable multi-agent analysis techniques that provide safety and performance guarantees have drastically increased. Hamilton-Jacobi (HJ) reachability has successfully provided these guarantees to small-scale systems and is flexible in terms of system dynamics. However, the exponential complexity scaling of HJ reachability with respect to system dimension prevents its direct application to larger-scale problems where the number of vehicles is greater than two. In this paper, we propose a collision avoidance algorithm using a hybrid framework for N+1 vehicles through higher-level control logic given any N-vehicle collision avoidance algorithm. Our algorithm conservatively approximates a guaranteed-safe region in the joint state space of the N+1 vehicles and produces a safety-preserving controller. In addition, our algorithm does not incur significant additional computation cost. We demonstrate our proposed method in simulation.
BibTeX:
@inproceedings{Dhinakaran-et-al-CDC-17,
  	author    = {Aparna Dhinakaran and
               Mo Chen and
               Glen Chou and
               Jennifer C. Shih and
               Claire J. Tomlin},
  title     = {A hybrid framework for multi-vehicle collision avoidance},
  booktitle = {56th {IEEE} Annual Conference on Decision and Control, {CDC} 2017,
               Melbourne, Australia, December 12-15, 2017},
  pages     = {2979--2984},
  year      = {2017},
}


Workshop Papers/Technical Reports

Authors Title Year Venue
G. Chou, N. Ozay, D. Berenson Learning Parametric Constraints in High Dimensions from Demonstrations
[Abstract] [PDF] [Cite] [Notes]
2019 Robotics: Science and Systems, Workshop on Robust Autonomy
Abstract: We extend the learning from demonstration paradigm by providing a method for learning unknown constraints shared across tasks, using demonstrations of the tasks, their cost functions, and knowledge of the system dynamics and control constraints. Given safe demonstrations, our method uses hit-and-run sampling to obtain lower cost, and thus unsafe, trajectories. Both safe and unsafe trajectories are used to obtain a consistent representation of the unsafe set via solving a mixed integer program. Additionally, by leveraging a known parameterization of the constraint, we modify our method to learn parametric constraints in high dimensions. We show that our method can learn a six-dimensional pose constraint for a 7-DOF robot arm.
BibTeX:
@inproceedings{Chou-RSSWS-19,
Author = "Glen Chou, Dmitry Berenson, and Necmiye Ozay", journal = {Robotics: Science and Systems, Workshop on Robust Autonomy},
Title = "Learning Parametric Constraints in High Dimensions from Demonstration",
year = {2019}
}
Notes: Selected for long contributed talk.
F. Jiang*, G. Chou*, M. Chen, C. J. Tomlin Using neural networks to compute approximate and guaranteed feasible Hamilton-Jacobi-Bellman PDE solutions
[Abstract] [arXiv] [Cite]
2016 arXiv
Abstract: To sidestep the curse of dimensionality when computing solutions to Hamilton-Jacobi-Bellman partial differential equations (HJB PDE), we propose an algorithm that leverages a neural network to approximate the value function. We show that our final approximation of the value function generates near optimal controls which are guaranteed to successfully drive the system to a target state. Our framework is not dependent on state space discretization, leading to a significant reduction in computation time and space complexity in comparison with dynamic programming-based approaches. Using this grid-free approach also enables us to plan over longer time horizons with relatively little additional computation overhead. Unlike many previous neural network HJB PDE approximating formulations, our approximation is strictly conservative and hence any trajectories we generate will be strictly feasible. For demonstration, we specialize our new general framework to the Dubins car model and discuss how the framework can be applied to other models with higher-dimensional state spaces.
BibTeX:
@inproceedings{Jiang-et-al-16,
  	author    = {Frank J. Jiang and
               Glen Chou and
               Mo Chen and
               Claire J. Tomlin},
  title     = {Using neural networks to compute approximate and guaranteed feasible Hamilton-Jacobi-Bellman PDE solutions},
  journal   = {CoRR},
  volume    = {abs/1611.03158},
  year      = {2016},
}