A probabilistic approach to robot trajectory generation

Paraschos, Alexandros; Neumann, Gerhard; Peters, Jan

doi:10.1109/humanoids.2013.7030017

Cited by 16 publications

(18 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stochastic movement primitive representations can not only represent the task variance but also be trained from demonstration data. To this end, we use the Probabilistic Movement Primitives (ProMPs) approach [2], [3] as our representation.…”

Section: A Encoding Task Accuracy From Demonstrationsmentioning

confidence: 99%

“…The controller can follow the encoded task distribution exactly, i.e., it matches mean and variance of the distribution. In [2], [3], ProMPs are used to control the joints of the robot and, therefore, the controller outputs are joint torques. In this paper, we generalize ProMPs to model and control in operational space, e.g., the robot's end-effector space.…”

Section: A Encoding Task Accuracy From Demonstrationsmentioning

confidence: 99%

“…We combine Bayesian task prioritization [1] that allows the computation of the combined control signal from multiple tasks at different operational spaces with Probabilistic Movement Primitives (ProMPs) [2], [3] to learn prioritized complete motion sequences. MPs [2]- [6], are a powerful representation for encoding complex movements, much more flexible than using attractors or point-to-point movements, and enable adaptation of the learned movements without retraining.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probabilistic Prioritization of Movement Primitives

Paraschos

Lioutikov

Peters

et al. 2017

IEEE Robot. Autom. Lett.

Self Cite

233

410

View full text Add to dashboard Cite

Abstract-Movement prioritization is a common approach to combine controllers of different tasks for redundant robots, where each task is assigned a priority. The priorities of the tasks are often hand-tuned or the result of an optimization, but seldomly learned from data. This paper combines Bayesian task prioritization with probabilistic movement primitives to prioritize full motion sequences that are learned from demonstrations. Probabilistic movement primitives (ProMPs) can encode distributions of movements over full motion sequences and provide control laws to exactly follow these distributions. The probabilistic formulation allows for a natural application of Bayesian task prioritization. We extend the ProMP controllers with an additional feedback component that accounts inaccuracies in following the distribution and allows for a more robust prioritization of primitives. We demonstrate how the task priorities can be obtained from imitation learning and how different primitives can be combined to solve even unseen task-combinations. Due to the prioritization, our approach can efficiently learn a combination of tasks without requiring individual models per task combination. Further, our approach can adapt an existing primitive library by prioritizing additional controllers, for example, for implementing obstacle avoidance. Hence, the need of retraining the whole library is avoided in many cases. We evaluate our approach on reaching movements under constraints with redundant simulated planar robots and two physical robot platforms, the humanoid robot "iCub" and a KUKA LWR robot arm.

show abstract

Section: A Encoding Task Accuracy From Demonstrationsmentioning

confidence: 99%

Section: A Encoding Task Accuracy From Demonstrationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistic Prioritization of Movement Primitives

Paraschos

Lioutikov

Peters

et al. 2017

IEEE Robot. Autom. Lett.

Self Cite

233

410

View full text Add to dashboard Cite

show abstract

“…Thus, the ProMPs method is more accurate for our software. Ewerton et al (2015), Paraschos et al (2013b), and Maeda et al (2014) compared ProMPs and DMPs for learning primitives and specifically interaction primitives. With the DMP model, at the end of the movement, only a dynamic attractor is activated.…”

Section: Movement Primitivesmentioning

confidence: 99%

Prediction of Intention during Interaction with iCub with Probabilistic Movement Primitives

et al. 2017

Self Cite

View full text Add to dashboard Cite

This article describes our open-source software for predicting the intention of a user physically interacting with the humanoid robot iCub. Our goal is to allow the robot to infer the intention of the human partner during collaboration, by predicting the future intended trajectory: this capability is critical to design anticipatory behaviors that are crucial in human-robot collaborative scenarios, such as in co-manipulation, cooperative assembly, or transportation. We propose an approach to endow the iCub with basic capabilities of intention recognition, based on Probabilistic Movement Primitives (ProMPs), a versatile method for representing, generalizing, and reproducing complex motor skills. The robot learns a set of motion primitives from several demonstrations, provided by the human via physical interaction. During training, we model the collaborative scenario using human demonstrations. During the reproduction of the collaborative task, we use the acquired knowledge to recognize the intention of the human partner. Using a few early observations of the state of the robot, we can not only infer the intention of the partner but also complete the movement, even if the user breaks the physical interaction with the robot. We evaluate our approach in simulation and on the real iCub. In simulation, the iCub is driven by the user using the Geomagic Touch haptic device. In the real robot experiment, we directly interact with the iCub by grabbing and manually guiding the robot's arm. We realize two experiments on the real robot: one with simple reaching trajectories, and one inspired by collaborative object sorting. The software implementing our approach is open source and available on the GitHub platform. In addition, we provide tutorials and videos.

show abstract

“…While DMPs have several more benefits such as stability, and the ability to represent stroke based and rhythmic movements, DMPs also have several limitations, such as that they can not represent optimal behavior in stochastic systems and the adaptation of the trajectory due to the meta-parameters is based on heuristics. These issues have been addressed by the recently proposed Probabilistic Movement Primitives approach [17], [18]. ProMPs estimate a distribution of trajectories instead of encoding single trajectories.…”

Section: A Related Workmentioning

confidence: 99%

Extracting low-dimensional control variables for movement primitives

Rueckert

Mundo

Paraschos

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Abstract-Movement primitives (MPs) provide a powerful framework for data driven movement generation that has been successfully applied for learning from demonstrations and robot reinforcement learning. In robotics we often want to solve a multitude of different, but related tasks. As the parameters of the primitives are typically high dimensional, a common practice for the generalization of movement primitives to new tasks is to adapt only a small set of control variables, also called meta parameters, of the primitive. Yet, for most MP representations, the encoding of these control variables is precoded in the representation and can not be adapted to the considered tasks. In this paper, we want to learn the encoding of task-specific control variables also from data instead of relying on fixed meta-parameter representations. We use hierarchical Bayesian models (HBMs) to estimate a low dimensional latent variable model for probabilistic movement primitives (ProMPs), which is a recent movement primitive representation. We show on two real robot datasets that ProMPs based on HBMs outperform standard ProMPs in terms of generalization and learning from a small amount of data and also allows for an intuitive analysis of the movement. We also extend our HBM by a mixture model, such that we can model different movement types in the same dataset.

show abstract

A probabilistic approach to robot trajectory generation

Cited by 16 publications

References 14 publications

Probabilistic Prioritization of Movement Primitives

Probabilistic Prioritization of Movement Primitives

Prediction of Intention during Interaction with iCub with Probabilistic Movement Primitives

Extracting low-dimensional control variables for movement primitives

Contact Info

Product

Resources

About