**Peter Englert**

From 2013 to 2018, I was a Ph.D. student in the

*Machine Learning and Robotics Lab*at the University of Stuttgart. My main research interests are in skill learning, robotic manipulations, and motion planning.

Research

Combining optimization and reinforcement learning

As an alternative to the standard reinforcement learning formulation where all objectives are defined in a single reward function, we propose to decompose the problem into analytically known objectives, such as motion smoothness, and black-box objectives, such as trial success or reward depending on the interaction with the environment. The skill learning problem is separated into an optimal control part that improves the skill with respect to the known parts of a problem and a reinforcement learning part that learns the unknown parts by interacting with the environment.

[1] **Learning Manipulation Skills from a Single Demonstration**

Peter Englert
and Marc Toussaint *International Journal of Robotics Research*
37(1):137-154, 2018

[ bib |
pdf |
video ]

Extracting compact task representations from depth data

Kinematic morphing networks find the relation of different geometric environments and use this relation to transfer skills between the environments. We assume that the environment can be modeled as a kinematic structure and represented with a low-dimensional parametrization. A key element of this work is the usage of the concatenation property of affine transformations and the ability to convert point clouds to depth images, which allows to apply the network in an iterative manner.

[1] **Kinematic Morphing Networks for Manipulation Skill Transfer**

Peter Englert and Marc Toussaint

In *Proceedings of the IEEE International Conference on
Intelligent Robotics Systems*, 2018

[ bib |
pdf |
video ]

Learning generalizable skills from demonstrations

The method presented in [1] captures the essential features of a demonstrated task in a cost function that is generalizable to various environment configurations. For this purpose, it assumes that the demonstrations are optimal with respect to an underlying constrained optimization problem. The aim of this approach is to push learning from demonstration to more complex manipulation scenarios that include the interaction with objects and therefore the realization of contacts/constraints within the motion.

[1] **Inverse KKT - Learning Cost Functions of Manipulation Tasks from
Demonstrations**

Peter Englert, Ngo Anh Vien, and Marc Toussaint *
International Journal of Robotics Research* 36(13-14):1474-1488, 2017

[ bib |
pdf ]

Learning with probabilistic models

Probabilistic models like Gaussian processes are the right choice if an uncertainty estimate of a model is important for the task. In [1], we proposed a probabilistic imitation learning formulation that learns a robot dynamics model from data. This model is used to perform a probabilistic trajectory matching to imitate the distribution of expert demonstrations. In [2], the robot only uses its tactile sensors to explore the shape of an unknown object by sliding on it. Gaussian processes are used to represent the implicit surface of the unknown object shape. The uncertainty of the model is used to guide the exploration into regions with the highest uncertainty.

[1] **Probabilistic Model-based Imitation Learning**

Peter Englert, Alexandros
Paraschos, Marc Peter Deisenroth, and Jan Peters *Adaptive Behavior
Journal* 21(5):388-403, 2013

[ bib |
pdf ]

[2] **Active Learning with Query Paths for Tactile Object Shape Exploration**

Danny Driess, Peter Englert, and Marc Toussaint

In *Proceedings of the IEEE International Conference on
Intelligent Robotics Systems*, 2017

[ bib |
pdf |
video ]

Publications

**Kinematic Morphing Networks for Manipulation Skill Transfer**

Peter Englert and Marc Toussaint

In *Proceedings of the IEEE International Conference on
Intelligent Robotics Systems*, 2018

[ bib |
pdf |
video ]

**Learning Manipulation Skills from a Single Demonstration**

Peter Englert
and Marc Toussaint *International Journal of Robotics Research*
37(1):137-154, 2018

[ bib |
pdf |
video ]

**Inverse KKT - Learning Cost Functions of Manipulation Tasks from
Demonstrations**

Peter Englert, Ngo Anh Vien, and Marc Toussaint *
International Journal of Robotics Research* 36(13-14):1474-1488, 2017

[ bib |
pdf ]

**Active Learning with Query Paths for Tactile Object Shape Exploration**

Danny Driess, Peter Englert, and Marc Toussaint

In *Proceedings of the IEEE International Conference on
Intelligent Robotics Systems*, 2017

[ bib |
pdf |
video ]

**Constrained Bayesian Optimization of Combined Interaction Force/Task Space
Controllers for Manipulations**

Danny Driess, Peter Englert, and Marc Toussaint

In *Proceedings of the IEEE International Conference on Robotics
and Automation*, 2017

[ bib |
pdf |
video ]

**Combined Optimization and Reinforcement Learning for Manipulations
Skills**

Peter Englert and Marc Toussaint

In *Proceedings of Robotics: Science and Systems*, 2016

[ bib |
pdf |
video ]

**Policy Search in Reproducing Kernel Hilbert Space**

Vien Ngo Anh, Peter Englert, and Marc Toussaint

In *Proceedings of the International Joint Conference on
Artificial Intelligence*, 2016

[ bib |
pdf ]

**Inverse KKT - Learning Cost Functions of Manipulation Tasks from
Demonstrations**

Peter Englert and Marc Toussaint

In *Proceedings of the International Symposium of Robotics
Research*, 2015

[ bib |
pdf |
video ]

**Sparse Gaussian Process Regression for Compliant, Real-Time Robot
Control**

Jens Schreiter, Peter Englert, Duy Nguyen-Tuong, and Marc Toussaint

In *Proceedings of the IEEE International Conference on Robotics
and Automation*, 2015

[ bib |
pdf ]

**Inverse KKT Motion Optimization: A Newton Method to Efficiently Extract
Task Spaces and Cost Parameters from Demonstrations**

Peter Englert and
Marc Toussaint *NIPS Workshop on Autonomously Learning Robots*, 2014

[ bib |
pdf ]

**Dual Execution of Optimized Contact Interaction Trajectories**

Marc Toussaint, Nathan Ratliff, Jeannette Bohg, Ludovic Righetti,
Peter Englert, and Stefan Schaal

In *Proceedings of the IEEE International Conference on
Intelligent Robotics Systems*, 2014

[ bib |
pdf ]

**Reactive Phase and Task Space Adaptation for Robust Motion Execution**

Peter Englert and Marc Toussaint

In *Proceedings of the IEEE International Conference on
Intelligent Robotics Systems*, 2014

[ bib |
pdf ]

**Multi-Task Policy Search for Robotics**

Marc Peter Deisenroth, Peter Englert, Jan Peters, and Dieter Fox

In *Proceedings of the IEEE International Conference on Robotics
and Automation*, 2014

[ bib |
pdf ]

**Probabilistic Model-based Imitation Learning**

Peter Englert, Alexandros
Paraschos, Marc Peter Deisenroth, and Jan Peters *Adaptive Behavior
Journal* 21(5):388-403, 2013

[ bib |
pdf ]

**Model-based Imitation Learning by Probabilistic Trajectory Matching**

Peter Englert, Alexandros Paraschos, Jan Peters, and Marc Peter
Deisenroth

In *Proceedings of the IEEE International Conference on Robotics
and Automation*, 2013

[ bib |
pdf ]

Teaching

TA at University of Stuttgart:- Practical Course Robotics (Summer 18)
- Lecture: Robotics (Winter 17)
- Lecture: Robotics (Winter 16)
- Lecture: Machine Learning (Summer 16)
- Lecture: Robotics (Winter 15)
- Lecture: Machine Learning (Summer 15)
- Seminar: Topics in Robotics (Winter 14)
- Lecture: Robotics (Winter 14)
- Lecture: Machine Learning (Summer 14)
- Lecture: Artificial Intelligence (Winter 13)

Contact

**Email:**

englertpr AT gmail.com

**Skype:**

englert.peter