Intelligent Systems
Note: This research group has relocated.


2021


Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees
Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees

Fiedler, C., Scherer, C. W., Trimpe, S.

In 60th IEEE Conference on Decision and Control (CDC), IEEE, December 2021 (inproceedings) Accepted

Abstract
The combination of machine learning with control offers many opportunities, in particular for robust control. However, due to strong safety and reliability requirements in many real-world applications, providing rigorous statistical and control-theoretic guarantees is of utmost importance, yet difficult to achieve for learning-based control schemes. We present a general framework for learning-enhanced robust control that allows for systematic integration of prior engineering knowledge, is fully compatible with modern robust control and still comes with rigorous and practically meaningful guarantees. Building on the established Linear Fractional Representation and Integral Quadratic Constraints framework, we integrate Gaussian Process Regression as a learning component and stateof-the-art robust controller synthesis. In a concrete robust control example, our approach is demonstrated to yield improved performance with more data, while guarantees are maintained throughout.

link (url) [BibTex]

2021

link (url) [BibTex]


no image
Local policy search with Bayesian optimization

Müller, S., von Rohr, A., Trimpe, S.

In Advances in Neural Information Processing Systems 34, 25, pages: 20708-20720, (Editors: Ranzato, M. and Beygelzimer, A. and Dauphin, Y. and Liang, P. S. and Wortman Vaughan, J.), Curran Associates, Inc., Red Hook, NY, 35th Conference on Neural Information Processing Systems (NeurIPS 2021) , December 2021 (inproceedings)

Abstract
Reinforcement learning (RL) aims to find an optimal policy by interaction with an environment. Consequently, learning complex behavior requires a vast number of samples, which can be prohibitive in practice. Nevertheless, instead of systematically reasoning and actively choosing informative samples, policy gradients for local search are often obtained from random perturbations. These random samples yield high variance estimates and hence are sub-optimal in terms of sample complexity. Actively selecting informative samples is at the core of Bayesian optimization, which constructs a probabilistic surrogate of the objective from past samples to reason about informative subsequent ones. In this paper, we propose to join both worlds. We develop an algorithm utilizing a probabilistic model of the objective function and its gradient. Based on the model, the algorithm decides where to query a noisy zeroth-order oracle to improve the gradient estimates. The resulting algorithm is a novel type of policy search method, which we compare to existing black-box algorithms. The comparison reveals improved sample complexity and reduced variance in extensive empirical evaluations on synthetic objectives. Further, we highlight the benefits of active sampling on popular RL benchmarks.

arXiv GitHub link (url) [BibTex]

arXiv GitHub link (url) [BibTex]


Using Physics Knowledge for Learning Rigid-Body Forward Dynamics with Gaussian Process Force Priors
Using Physics Knowledge for Learning Rigid-Body Forward Dynamics with Gaussian Process Force Priors

Rath, L., Geist, A. R., Trimpe, S.

In Proceedings of the 5th Conference on Robot Learning, 164, pages: 101-111, Proceedings of Machine Learning Research, (Editors: Faust, Aleksandra and Hsu, David and Neumann, Gerhard), PMLR, 5th Conference on Robot Learning (CoRL 2021), November 2021 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


GoSafe: Globally Optimal Safe Robot Learning
GoSafe: Globally Optimal Safe Robot Learning

Baumann, D., Marco, A., Turchetta, M., Trimpe, S.

In 2021 IEEE International Conference on Robotics and Automation (ICRA 2021), pages: 4452-4458, IEEE, Piscataway, NJ, IEEE International Conference on Robotics and Automation (ICRA 2021), October 2021 (inproceedings)

DOI [BibTex]

DOI [BibTex]


Probabilistic robust linear quadratic regulators with Gaussian processes
Probabilistic robust linear quadratic regulators with Gaussian processes

von Rohr, A., Neumann-Brosig, M., Trimpe, S.

Proceedings of the 3rd Conference on Learning for Dynamics and Control, pages: 324-335, Proceedings of Machine Learning Research (PMLR), Vol. 144, (Editors: Jadbabaie, Ali and Lygeros, John and Pappas, George J. and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.), PMLR, Brookline, MA 02446 , 3rd Annual Conference on Learning for Dynamics and Control (L4DC), June 2021 (conference)

Abstract
Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. While learning-based control has the potential to yield superior performance in demanding applications, robustness to uncertainty remains an important challenge. Since Bayesian methods quantify uncertainty of the learning results, it is natural to incorporate these uncertainties in a robust design. In contrast to most state-of-the-art approaches that consider worst-case estimates, we leverage the learning methods’ posterior distribution in the controller synthesis. The result is a more informed and thus efficient trade-off between performance and robustness. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin. The formulation is based on a recently proposed algorithm for linear quadratic control synthesis, which we extend by giving probabilistic robustness guarantees in the form of credibility bounds for the system’s stability. Comparisons to existing methods based on worst-case and certainty-equivalence designs reveal superior performance and robustness properties of the proposed method.

link (url) DOI [BibTex]

link (url) DOI [BibTex]


On exploration requirements for learning safety constraints
On exploration requirements for learning safety constraints

Massiani, P., Heim, S., Trimpe, S.

In Proceedings of the 3rd Conference on Learning for Dynamics and Control, pages: 905-916, Proceedings of Machine Learning Research (PMLR), Vol. 144, (Editors: Jadbabaie, Ali and Lygeros, John and Pappas, George J. and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie), PMLR, 3rd Annual Conference on Learning for Dynamics and Control (L4DC), June 2021 (inproceedings)

Abstract
Enforcing safety for dynamical systems is challenging, since it requires constraint satisfaction along trajectory predictions. Equivalent control constraints can be computed in the form of sets that enforce positive invariance, and can thus guarantee safety in feedback controllers without predictions. However, these constraints are cumbersome to compute from models, and it is not yet well established how to infer constraints from data. In this paper, we shed light on the key objects involved in learning control constraints from data in a model-free setting. In particular, we discuss the family of constraints that enforce safety in the context of a nominal control policy, and expose that these constraints do not need to be accurate everywhere. They only need to correctly exclude a subset of the state-actions that would cause failure, which we call the critical set.

link (url) [BibTex]

link (url) [BibTex]


Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression
Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression

Fiedler, C., Scherer, C. W., Trimpe, S.

In The Thirty-Fifth AAAI Conference on Artificial Intelligence, the Thirty-Third Conference on Innovative Applications of Artificial Intelligence, the Eleventh Symposium on Educational Advances in Artificial Intelligence, 8, pages: 7439-7447, AAAI Press, Palo Alto, CA, Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021), Thirty-Third Conference on Innovative Applications of Artificial Intelligence (IAAI 2021), Eleventh Symposium on Educational Advances in Artificial Intelligence (EAAI 2021), May 2021 (inproceedings)

Abstract
Gaussian Process regression is a popular nonparametric regression method based on Bayesian principles that provides uncertainty estimates for its predictions. However, these estimates are of a Bayesian nature, whereas for some important applications, like learning-based control with safety guarantees, frequentist uncertainty bounds are required. Although such rigorous bounds are available for Gaussian Processes, they are too conservative to be useful in applications. This often leads practitioners to replacing these bounds by heuristics, thus breaking all theoretical guarantees. To address this problem, we introduce new uncertainty bounds that are rigorous, yet practically useful at the same time. In particular, the bounds can be explicitly evaluated and are much less conservative than state of the art results. Furthermore, we show that certain model misspecifications lead to only graceful degradation. We demonstrate these advantages and the usefulness of our results for learning-based control with numerical examples.},

link (url) [BibTex]

link (url) [BibTex]


A little damping goes a long way
A little damping goes a long way

Heim, S., Millard, M., Mouel, C. L., Badri-Spröwitz, A.

In Integrative and Comparative Biology, 61(Supplement 1):E367-E367, Oxford University Press, Society for Integrative and Comparative Biology Annual Meeting (SICB Annual Meeting 2021) , March 2021 (inproceedings)

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2020


Learning of sub-optimal gait controllers for magnetic walking soft millirobots
Learning of sub-optimal gait controllers for magnetic walking soft millirobots

Culha, U., Demir, S. O., Trimpe, S., Sitti, M.

In Robotics: Science and Systems XVI, pages: P070, (Editors: Toussaint, Marc and Bicchi, Antonio and Hermans, Tucker), RSS Foundation, Robotics: Science and Systems 2020 (RSS 2020), 2020 (inproceedings)

Abstract
Untethered small-scale soft robots have promising applications in minimally invasive surgery, targeted drug delivery, and bioengineering applications as they can access confined spaces in the human body. However, due to highly nonlinear soft continuum deformation kinematics, inherent stochastic variability during fabrication at the small scale, and lack of accurate models, the conventional control methods cannot be easily applied. Adaptivity of robot control is additionally crucial for medical operations, as operation environments show large variability, and robot materials may degrade or change over time,which would have deteriorating effects on the robot motion and task performance. Therefore, we propose using a probabilistic learning approach for millimeter-scale magnetic walking soft robots using Bayesian optimization (BO) and Gaussian processes (GPs). Our approach provides a data-efficient learning scheme to find controller parameters while optimizing the stride length performance of the walking soft millirobot robot within a small number of physical experiments. We demonstrate adaptation to fabrication variabilities in three different robots and to walking surfaces with different roughness. We also show an improvement in the learning performance by transferring the learning results of one robot to the others as prior information.

link (url) DOI Project Page [BibTex]

2020

link (url) DOI Project Page [BibTex]


Actively Learning Gaussian Process Dynamics
Actively Learning Gaussian Process Dynamics

Buisson-Fenet, M., Solowjow, F., Trimpe, S.

Proceedings of the 2nd Conference on Learning for Dynamics and Control, 120, pages: 5-15, Proceedings of Machine Learning Research (PMLR), (Editors: Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie), PMLR, 2nd Annual Conference on Learning for Dynamics and Control (L4DC), June 2020 (conference)

Abstract
Despite the availability of ever more data enabled through modern sensor and computer technology, it still remains an open problem to learn dynamical systems in a sample-efficient way. We propose active learning strategies that leverage information-theoretical properties arising naturally during Gaussian process regression, while respecting constraints on the sampling process imposed by the system dynamics. Sample points are selected in regions with high uncertainty, leading to exploratory behavior and data-efficient training of the model. All results are verified in an extensive numerical benchmark.

ArXiv link (url) [BibTex]

ArXiv link (url) [BibTex]


Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes
Learning Constrained Dynamics with Gauss Principle adhering Gaussian Processes

Geist, A. R., Trimpe, S.

In Proceedings of the 2nd Conference on Learning for Dynamics and Control, 120, pages: 225-234, Proceedings of Machine Learning Research (PMLR), (Editors: Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie), PMLR, 2nd Annual Conference on Learning for Dynamics and Control (L4DC), June 2020 (inproceedings)

Abstract
The identification of the constrained dynamics of mechanical systems is often challenging. Learning methods promise to ease an analytical analysis, but require considerable amounts of data for training. We propose to combine insights from analytical mechanics with Gaussian process regression to improve the model's data efficiency and constraint integrity. The result is a Gaussian process model that incorporates a priori constraint knowledge such that its predictions adhere to Gauss' principle of least constraint. In return, predictions of the system's acceleration naturally respect potentially non-ideal (non-)holonomic equality constraints. As corollary results, our model enables to infer the acceleration of the unconstrained system from data of the constrained system and enables knowledge transfer between differing constraint configurations.

Proceedings of Machine Learning Research link (url) [BibTex]

Proceedings of Machine Learning Research link (url) [BibTex]


no image
Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization

Turchetta, M., Krause, A., Trimpe, S.

In 2020 IEEE International Conference on Robotics and Automation (ICRA 2020), pages: 10702-10708, IEEE, Piscataway, NJ, IEEE International Conference on Robotics and Automation (ICRA 2020), May 2020 (inproceedings)

DOI [BibTex]

DOI [BibTex]


Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures

Marco, A., Rohr, A. V., Baumann, D., Hernández-Lobato, J. M., Trimpe, S.

2020 (proceedings) In revision

Abstract
When learning to ride a bike, a child falls down a number of times before achieving the first success. As falling down usually has only mild consequences, it can be seen as a tolerable failure in exchange for a faster learning process, as it provides rich information about an undesired behavior. In the context of Bayesian optimization under unknown constraints (BOC), typical strategies for safe learning explore conservatively and avoid failures by all means. On the other side of the spectrum, non conservative BOC algorithms that allow failing may fail an unbounded number of times before reaching the optimum. In this work, we propose a novel decision maker grounded in control theory that controls the amount of risk we allow in the search as a function of a given budget of failures. Empirical validation shows that our algorithm uses the failures budget more efficiently in a variety of optimization experiments, and generally achieves lower regret, than state-of-the-art methods. In addition, we propose an original algorithm for unconstrained Bayesian optimization inspired by the notion of excursion sets in stochastic processes, upon which the failures-aware algorithm is built.

arXiv code (python) PDF [BibTex]

2019


Controlling Heterogeneous Stochastic Growth Processes on Lattices with Limited Resources
Controlling Heterogeneous Stochastic Growth Processes on Lattices with Limited Resources

Haksar, R., Solowjow, F., Trimpe, S., Schwager, M.

In Proceedings of the 58th IEEE International Conference on Decision and Control (CDC) , pages: 1315-1322, 58th IEEE International Conference on Decision and Control (CDC), December 2019 (conference)

PDF [BibTex]

2019

PDF [BibTex]


Predictive Triggering for Distributed Control of Resource Constrained Multi-agent Systems
Predictive Triggering for Distributed Control of Resource Constrained Multi-agent Systems

Mastrangelo, J. M., Baumann, D., Trimpe, S.

In Proceedings of the 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems, pages: 79-84, 8th IFAC Workshop on Distributed Estimation and Control in Networked Systems (NecSys), September 2019 (inproceedings)

arXiv PDF DOI [BibTex]

arXiv PDF DOI [BibTex]


Event-triggered Pulse Control with Model Learning (if Necessary)
Event-triggered Pulse Control with Model Learning (if Necessary)

Baumann, D., Solowjow, F., Johansson, K. H., Trimpe, S.

In Proceedings of the American Control Conference, pages: 792-797, American Control Conference (ACC), July 2019 (inproceedings)

arXiv PDF [BibTex]

arXiv PDF [BibTex]


Data-driven inference of passivity properties via Gaussian process optimization
Data-driven inference of passivity properties via Gaussian process optimization

Romer, A., Trimpe, S., Allgöwer, F.

In Proceedings of the European Control Conference, European Control Conference (ECC), June 2019 (inproceedings)

PDF [BibTex]

PDF [BibTex]


Trajectory-Based Off-Policy Deep Reinforcement Learning
Trajectory-Based Off-Policy Deep Reinforcement Learning

Doerr, A., Volpp, M., Toussaint, M., Trimpe, S., Daniel, C.

In Proceedings of the International Conference on Machine Learning (ICML), International Conference on Machine Learning (ICML), June 2019 (inproceedings)

Abstract
Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently get stuck in local optima. This work addresses these weaknesses by combining recent improvements in the reuse of off-policy data and exploration in parameter space with deterministic behavioral policies. The resulting objective is amenable to standard neural network optimization strategies like stochastic gradient descent or stochastic gradient Hamiltonian Monte Carlo. Incorporation of previous rollouts via importance sampling greatly improves data-efficiency, whilst stochastic optimization schemes facilitate the escape from local optima. We evaluate the proposed approach on a series of continuous control benchmark tasks. The results show that the proposed algorithm is able to successfully and reliably learn solutions using fewer system interactions than standard policy gradient methods.

arXiv PDF [BibTex]

arXiv PDF [BibTex]


Feedback Control Goes Wireless: Guaranteed Stability over Low-power Multi-hop Networks
Feedback Control Goes Wireless: Guaranteed Stability over Low-power Multi-hop Networks

(Best Paper Award)

Mager, F., Baumann, D., Jacob, R., Thiele, L., Trimpe, S., Zimmerling, M.

In Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical Systems, pages: 97-108, 10th ACM/IEEE International Conference on Cyber-Physical Systems, April 2019 (inproceedings)

Abstract
Closing feedback loops fast and over long distances is key to emerging applications; for example, robot motion control and swarm coordination require update intervals below 100 ms. Low-power wireless is preferred for its flexibility, low cost, and small form factor, especially if the devices support multi-hop communication. Thus far, however, closed-loop control over multi-hop low-power wireless has only been demonstrated for update intervals on the order of multiple seconds. This paper presents a wireless embedded system that tames imperfections impairing control performance such as jitter or packet loss, and a control design that exploits the essential properties of this system to provably guarantee closed-loop stability for linear dynamic systems. Using experiments on a testbed with multiple cart-pole systems, we are the first to demonstrate the feasibility and to assess the performance of closed-loop control and coordination over multi-hop low-power wireless for update intervals from 20 ms to 50 ms.

arXiv PDF DOI Project Page [BibTex]

arXiv PDF DOI Project Page [BibTex]

2018


Deep Reinforcement Learning for Event-Triggered Control
Deep Reinforcement Learning for Event-Triggered Control

Baumann, D., Zhu, J., Martius, G., Trimpe, S.

In Proceedings of the 57th IEEE International Conference on Decision and Control (CDC), pages: 943-950, 57th IEEE International Conference on Decision and Control (CDC), December 2018 (inproceedings)

arXiv PDF DOI Project Page [BibTex]

2018

arXiv PDF DOI Project Page [BibTex]


Efficient Encoding of Dynamical Systems through Local Approximations
Efficient Encoding of Dynamical Systems through Local Approximations

Solowjow, F., Mehrjou, A., Schölkopf, B., Trimpe, S.

In Proceedings of the 57th IEEE International Conference on Decision and Control (CDC), pages: 6073 - 6079 , Miami, Fl, USA, December 2018 (inproceedings)

arXiv PDF DOI [BibTex]

arXiv PDF DOI [BibTex]


Depth Control of Underwater Robots using Sliding Modes and Gaussian Process Regression
Depth Control of Underwater Robots using Sliding Modes and Gaussian Process Regression

Lima, G. S., Bessa, W. M., Trimpe, S.

In Proceeding of the 15th Latin American Robotics Symposium, João Pessoa, Brazil, 15th Latin American Robotics Symposium, November 2018 (inproceedings)

Abstract
The development of accurate control systems for underwater robotic vehicles relies on the adequate compensation for hydrodynamic effects. In this work, a new robust control scheme is presented for remotely operated underwater vehicles. In order to meet both robustness and tracking requirements, sliding mode control is combined with Gaussian process regression. The convergence properties of the closed-loop signals are analytically proven. Numerical results confirm the stronger improved performance of the proposed control scheme.

[BibTex]

[BibTex]


Gait learning for soft microrobots controlled by light fields
Gait learning for soft microrobots controlled by light fields

Rohr, A. V., Trimpe, S., Marco, A., Fischer, P., Palagi, S.

In International Conference on Intelligent Robots and Systems (IROS) 2018, pages: 6199-6206, Piscataway, NJ, USA, International Conference on Intelligent Robots and Systems 2018, October 2018 (inproceedings)

Abstract
Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits. This inherent flexibility can be exploited to maximize their locomotion performance in a given environment and used to adapt them to changing environments. However, because of the lack of accurate locomotion models, and given the intrinsic variability among microrobots, analytical control design is not possible. Common data-driven approaches, on the other hand, require running prohibitive numbers of experiments and lead to very sample-specific results. Here we propose a probabilistic learning approach for light-controlled soft microrobots based on Bayesian Optimization (BO) and Gaussian Processes (GPs). The proposed approach results in a learning scheme that is highly data-efficient, enabling gait optimization with a limited experimental budget, and robust against differences among microrobot samples. These features are obtained by designing the learning scheme through the comparison of different GP priors and BO settings on a semisynthetic data set. The developed learning scheme is validated in microrobot experiments, resulting in a 115% improvement in a microrobot’s locomotion performance with an experimental budget of only 20 tests. These encouraging results lead the way toward self-adaptive microrobotic systems based on lightcontrolled soft microrobots and probabilistic learning control.

arXiv IEEE Xplore link (url) DOI Project Page Project Page [BibTex]

arXiv IEEE Xplore link (url) DOI Project Page Project Page [BibTex]


no image
Learning-Based Robust Model Predictive Control with State-Dependent Uncertainty

Soloperto, R., Müller, M. A., Trimpe, S., Allgöwer, F.

In Proceedings of the IFAC Conference on Nonlinear Model Predictive Control (NMPC), Madison, Wisconsin, USA, 6th IFAC Conference on Nonlinear Model Predictive Control, August 2018 (inproceedings)

PDF [BibTex]

PDF [BibTex]


Probabilistic Recurrent State-Space Models
Probabilistic Recurrent State-Space Models

Doerr, A., Daniel, C., Schiegg, M., Nguyen-Tuong, D., Schaal, S., Toussaint, M., Trimpe, S.

In Proceedings of the International Conference on Machine Learning (ICML), International Conference on Machine Learning (ICML), July 2018 (inproceedings)

Abstract
State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g., LSTMs) proved extremely successful in modeling complex time-series data. Fully probabilistic SSMs, however, unfortunately often prove hard to train, even for smaller problems. To overcome this limitation, we propose a scalable initialization and training algorithm based on doubly stochastic variational inference and Gaussian processes. In the variational approximation we propose in contrast to related approaches to fully capture the latent state temporal correlations to allow for robust training.

arXiv pdf Project Page [BibTex]

arXiv pdf Project Page [BibTex]


Event-triggered Learning for Resource-efficient Networked Control
Event-triggered Learning for Resource-efficient Networked Control

Solowjow, F., Baumann, D., Garcke, J., Trimpe, S.

In Proceedings of the American Control Conference (ACC), pages: 6506 - 6512, American Control Conference, June 2018 (inproceedings)

arXiv PDF DOI Project Page [BibTex]

arXiv PDF DOI Project Page [BibTex]


Evaluating Low-Power Wireless Cyber-Physical Systems
Evaluating Low-Power Wireless Cyber-Physical Systems

Baumann, D., Mager, F., Singh, H., Zimmerling, M., Trimpe, S.

In Proceedings of the IEEE Workshop on Benchmarking Cyber-Physical Networks and Systems (CPSBench), pages: 13-18, IEEE Workshop on Benchmarking Cyber-Physical Networks and Systems (CPSBench), April 2018 (inproceedings)

arXiv PDF DOI Project Page [BibTex]

arXiv PDF DOI Project Page [BibTex]

2017


On the Design of {LQR} Kernels for Efficient Controller Learning
On the Design of LQR Kernels for Efficient Controller Learning

Marco, A., Hennig, P., Schaal, S., Trimpe, S.

Proceedings of the 56th IEEE Annual Conference on Decision and Control (CDC), pages: 5193-5200, IEEE, IEEE Conference on Decision and Control, December 2017 (conference)

Abstract
Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic description of the latent objective function, typically a Gaussian process (GP). As is shown herein, GPs with a common kernel choice can, however, lead to poor learning outcomes on standard quadratic control problems. For a first-order system, we construct two kernels that specifically leverage the structure of the well-known Linear Quadratic Regulator (LQR), yet retain the flexibility of Bayesian nonparametric learning. Simulations of uncertain linear and nonlinear systems demonstrate that the LQR kernels yield superior learning performance.

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page Project Page [BibTex]

2017

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page Project Page [BibTex]


Optimizing Long-term Predictions for Model-based Policy Search
Optimizing Long-term Predictions for Model-based Policy Search

Doerr, A., Daniel, C., Nguyen-Tuong, D., Marco, A., Schaal, S., Toussaint, M., Trimpe, S.

Proceedings of 1st Annual Conference on Robot Learning (CoRL), 78, pages: 227-238, (Editors: Sergey Levine and Vincent Vanhoucke and Ken Goldberg), 1st Annual Conference on Robot Learning, November 2017 (conference)

Abstract
We propose a novel long-term optimization criterion to improve the robustness of model-based reinforcement learning in real-world scenarios. Learning a dynamics model to derive a solution promises much greater data-efficiency and reusability compared to model-free alternatives. In practice, however, modelbased RL suffers from various imperfections such as noisy input and output data, delays and unmeasured (latent) states. To achieve higher resilience against such effects, we propose to optimize a generative long-term prediction model directly with respect to the likelihood of observed trajectories as opposed to the common approach of optimizing a dynamics model for one-step-ahead predictions. We evaluate the proposed method on several artificial and real-world benchmark problems and compare it to PILCO, a model-based RL framework, in experiments on a manipulation robot. The results show that the proposed method is competitive compared to state-of-the-art model learning methods. In contrast to these more involved models, our model can directly be employed for policy search and outperforms a baseline method in the robot experiment.

PDF Project Page [BibTex]

PDF Project Page [BibTex]


Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers
Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers

Doerr, A., Nguyen-Tuong, D., Marco, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 5295-5301, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), May 2017 (inproceedings)

PDF arXiv DOI Project Page [BibTex]

PDF arXiv DOI Project Page [BibTex]


Virtual vs. {R}eal: Trading Off Simulations and Physical Experiments in Reinforcement Learning with {B}ayesian Optimization
Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization

Marco, A., Berkenkamp, F., Hennig, P., Schoellig, A. P., Krause, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 1557-1563, IEEE, Piscataway, NJ, USA, May 2017 (inproceedings)

PDF arXiv ICRA 2017 Spotlight presentation Virtual vs. Real - Video explanation DOI Project Page Project Page [BibTex]

PDF arXiv ICRA 2017 Spotlight presentation Virtual vs. Real - Video explanation DOI Project Page Project Page [BibTex]

2016


no image
Predictive and Self Triggering for Event-based State Estimation

Trimpe, S.

In Proceedings of the 55th IEEE Conference on Decision and Control (CDC), pages: 3098-3105, Las Vegas, NV, USA, December 2016 (inproceedings)

arXiv PDF DOI Project Page [BibTex]

2016

arXiv PDF DOI Project Page [BibTex]


Robust Gaussian Filtering using a Pseudo Measurement
Robust Gaussian Filtering using a Pseudo Measurement

Wüthrich, M., Garcia Cifuentes, C., Trimpe, S., Meier, F., Bohg, J., Issac, J., Schaal, S.

In Proceedings of the American Control Conference (ACC), Boston, MA, USA, July 2016 (inproceedings)

Abstract
Most widely-used state estimation algorithms, such as the Extended Kalman Filter and the Unscented Kalman Filter, belong to the family of Gaussian Filters (GF). Unfortunately, GFs fail if the measurement process is modelled by a fat-tailed distribution. This is a severe limitation, because thin-tailed measurement models, such as the analytically-convenient and therefore widely-used Gaussian distribution, are sensitive to outliers. In this paper, we show that mapping the measurements into a specific feature space enables any existing GF algorithm to work with fat-tailed measurement models. We find a feature function which is optimal under certain conditions. Simulation results show that the proposed method allows for robust filtering in both linear and nonlinear systems with measurements contaminated by fat-tailed noise.

Web link (url) DOI Project Page [BibTex]

Web link (url) DOI Project Page [BibTex]


Automatic LQR Tuning Based on Gaussian Process Global Optimization
Automatic LQR Tuning Based on Gaussian Process Global Optimization

Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 270-277, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree- of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Results of a two- and four- dimensional tuning problems highlight the method’s potential for automatic controller tuning on robotic platforms.

Video - Automatic LQR Tuning Based on Gaussian Process Global Optimization - ICRA 2016 Video - Automatic Controller Tuning on a Two-legged Robot PDF DOI Project Page Project Page [BibTex]

Video - Automatic LQR Tuning Based on Gaussian Process Global Optimization - ICRA 2016 Video - Automatic Controller Tuning on a Two-legged Robot PDF DOI Project Page Project Page [BibTex]


Depth-based Object Tracking Using a Robust Gaussian Filter
Depth-based Object Tracking Using a Robust Gaussian Filter

Issac, J., Wüthrich, M., Garcia Cifuentes, C., Bohg, J., Trimpe, S., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2016, IEEE, IEEE International Conference on Robotics and Automation, May 2016 (inproceedings)

Abstract
We consider the problem of model-based 3D- tracking of objects given dense depth images as input. Two difficulties preclude the application of a standard Gaussian filter to this problem. First of all, depth sensors are characterized by fat-tailed measurement noise. To address this issue, we show how a recently published robustification method for Gaussian filters can be applied to the problem at hand. Thereby, we avoid using heuristic outlier detection methods that simply reject measurements if they do not match the model. Secondly, the computational cost of the standard Gaussian filter is prohibitive due to the high-dimensional measurement, i.e. the depth image. To address this problem, we propose an approximation to reduce the computational complexity of the filter. In quantitative experiments on real data we show how our method clearly outperforms the standard Gaussian filter. Furthermore, we compare its performance to a particle-filter-based tracking method, and observe comparable computational efficiency and improved accuracy and smoothness of the estimates.

Video Bayesian Object Tracking Library Bayesian Filtering Framework Object Tracking Dataset link (url) DOI Project Page [BibTex]

Video Bayesian Object Tracking Library Bayesian Filtering Framework Object Tracking Dataset link (url) DOI Project Page [BibTex]


no image
Communication Rate Analysis for Event-based State Estimation

(Best student paper finalist)

Ebner, S., Trimpe, S.

In Proceedings of the 13th International Workshop on Discrete Event Systems, May 2016 (inproceedings)

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Supplemental material for ’Communication Rate Analysis for Event-based State Estimation’

Ebner, S., Trimpe, S.

Max Planck Institute for Intelligent Systems, January 2016 (techreport)

PDF [BibTex]

2015


no image
Distributed Event-based State Estimation

Trimpe, S.

Max Planck Institute for Intelligent Systems, November 2015 (techreport)

Abstract
An event-based state estimation approach for reducing communication in a networked control system is proposed. Multiple distributed sensor-actuator-agents observe a dynamic process and sporadically exchange their measurements and inputs over a bus network. Based on these data, each agent estimates the full state of the dynamic system, which may exhibit arbitrary inter-agent couplings. Local event-based protocols ensure that data is transmitted only when necessary to meet a desired estimation accuracy. This event-based scheme is shown to mimic a centralized Luenberger observer design up to guaranteed bounds, and stability is proven in the sense of bounded estimation errors for bounded disturbances. The stability result extends to the distributed control system that results when the local state estimates are used for distributed feedback control. Simulation results highlight the benefit of the event-based approach over classical periodic ones in reducing communication requirements.

arXiv [BibTex]

2015

arXiv [BibTex]


Automatic LQR Tuning Based on Gaussian Process Optimization: Early Experimental Results
Automatic LQR Tuning Based on Gaussian Process Optimization: Early Experimental Results

Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.

Machine Learning in Planning and Control of Robot Motion Workshop at the IEEE/RSJ International Conference on Intelligent Robots and Systems (iROS), pages: , , Machine Learning in Planning and Control of Robot Motion Workshop, October 2015 (conference)

Abstract
This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree-of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Preliminary results of a low-dimensional tuning problem highlight the method’s potential for automatic controller tuning on robotic platforms.

PDF DOI Project Page Project Page [BibTex]

PDF DOI Project Page Project Page [BibTex]


Direct Loss Minimization Inverse Optimal Control
Direct Loss Minimization Inverse Optimal Control

Doerr, A., Ratliff, N., Bohg, J., Toussaint, M., Schaal, S.

In Proceedings of Robotics: Science and Systems, Rome, Italy, Robotics: Science and Systems XI, July 2015 (inproceedings)

Abstract
Inverse Optimal Control (IOC) has strongly impacted the systems engineering process, enabling automated planner tuning through straightforward and intuitive demonstration. The most successful and established applications, though, have been in lower dimensional problems such as navigation planning where exact optimal planning or control is feasible. In higher dimensional systems, such as humanoid robots, research has made substantial progress toward generalizing the ideas to model free or locally optimal settings, but these systems are complicated to the point where demonstration itself can be difficult. Typically, real-world applications are restricted to at best noisy or even partial or incomplete demonstrations that prove cumbersome in existing frameworks. This work derives a very flexible method of IOC based on a form of Structured Prediction known as Direct Loss Minimization. The resulting algorithm is essentially Policy Search on a reward function that rewards similarity to demonstrated behavior (using Covariance Matrix Adaptation (CMA) in our experiments). Our framework blurs the distinction between IOC, other forms of Imitation Learning, and Reinforcement Learning, enabling us to derive simple, versatile, and practical algorithms that blend imitation and reinforcement signals into a unified framework. Our experiments analyze various aspects of its performance and demonstrate its efficacy on conveying preferences for motion shaping and combined reach and grasp quality optimization.

PDF Video Project Page [BibTex]

PDF Video Project Page [BibTex]


no image
LMI-Based Synthesis for Distributed Event-Based State Estimation

Muehlebach, M., Trimpe, S.

In Proceedings of the American Control Conference, July 2015 (inproceedings)

Abstract
This paper presents an LMI-based synthesis procedure for distributed event-based state estimation. Multiple agents observe and control a dynamic process by sporadically exchanging data over a broadcast network according to an event-based protocol. In previous work [1], the synthesis of event-based state estimators is based on a centralized design. In that case three different types of communication are required: event-based communication of measurements, periodic reset of all estimates to their joint average, and communication of inputs. The proposed synthesis problem eliminates the communication of inputs as well as the periodic resets (under favorable circumstances) by accounting explicitly for the distributed structure of the control system.

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


no image
Guaranteed H2 Performance in Distributed Event-Based State Estimation

Muehlebach, M., Trimpe, S.

In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


no image
On the Choice of the Event Trigger in Event-based Estimation

Trimpe, S., Campi, M.

In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


no image
Event-based Estimation and Control for Remote Robot Operation with Reduced Communication

Trimpe, S., Buchli, J.

In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

Abstract
An event-based communication framework for remote operation of a robot via a bandwidth-limited network is proposed. The robot sends state and environment estimation data to the operator, and the operator transmits updated control commands or policies to the robot. Event-based communication protocols are designed to ensure that data is transmitted only when required: the robot sends new estimation data only if this yields a significant information gain at the operator, and the operator transmits an updated control policy only if this comes with a significant improvement in control performance. The developed framework is modular and can be used with any standard estimation and control algorithms. Simulation results of a robotic arm highlight its potential for an efficient use of limited communication resources, for example, in disaster response scenarios such as the DARPA Robotics Challenge.

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


no image
Lernende Roboter

Trimpe, S.

In Jahrbuch der Max-Planck-Gesellschaft, Max Planck Society, May 2015, (popular science article in German) (inbook)

link (url) [BibTex]

link (url) [BibTex]


no image
A New Perspective and Extension of the Gaussian Filter

Wüthrich, M., Trimpe, S., Kappler, D., Schaal, S.

In Robotics: Science and Systems, 2015 (inproceedings)

Abstract
The Gaussian Filter (GF) is one of the most widely used filtering algorithms; instances are the Extended Kalman Filter, the Unscented Kalman Filter and the Divided Difference Filter. GFs represent the belief of the current state by a Gaussian with the mean being an affine function of the measurement. We show that this representation can be too restrictive to accurately capture the dependencies in systems with nonlinear observation models, and we investigate how the GF can be generalized to alleviate this problem. To this end we view the GF from a variational-inference perspective, and analyze how restrictions on the form of the belief can be relaxed while maintaining simplicity and efficiency. This analysis provides a basis for generalizations of the GF. We propose one such generalization which coincides with a GF using a virtual measurement, obtained by applying a nonlinear function to the actual measurement. Numerical experiments show that the proposed Feature Gaussian Filter (FGF) can have a substantial performance advantage over the standard GF for systems with nonlinear observation models.

Web PDF Project Page [BibTex]

2014


no image
A Self-Tuning LQR Approach Demonstrated on an Inverted Pendulum

Trimpe, S., Millane, A., Doessegger, S., D’Andrea, R.

In Proceedings of the 19th IFAC World Congress, Cape Town, South Africa, 2014 (inproceedings)

PDF Supplementary material DOI [BibTex]

2014

PDF Supplementary material DOI [BibTex]


no image
Stability Analysis of Distributed Event-Based State Estimation

Trimpe, S.

In Proceedings of the 53rd IEEE Conference on Decision and Control, Los Angeles, CA, 2014 (inproceedings)

Abstract
An approach for distributed and event-based state estimation that was proposed in previous work [1] is analyzed and extended to practical networked systems in this paper. Multiple sensor-actuator-agents observe a dynamic process, sporadically exchange their measurements over a broadcast network according to an event-based protocol, and estimate the process state from the received data. The event-based approach was shown in [1] to mimic a centralized Luenberger observer up to guaranteed bounds, under the assumption of identical estimates on all agents. This assumption, however, is unrealistic (it is violated by a single packet drop or slight numerical inaccuracy) and removed herein. By means of a simulation example, it is shown that non-identical estimates can actually destabilize the overall system. To achieve stability, the event-based communication scheme is supplemented by periodic (but infrequent) exchange of the agentsâ?? estimates and reset to their joint average. When the local estimates are used for feedback control, the stability guarantee for the estimation problem extends to the event-based control system.

PDF Supplementary material DOI Project Page [BibTex]

PDF Supplementary material DOI Project Page [BibTex]