Institute Homepage
Institute Homepage DE Sign In

Back

Autonomous Learning Conference Paper 2022

Risk-Averse Zero-Order Trajectory Optimization

no image
Autonomous Learning
Marin Vlastelica Pogancic
Thumb ticker sm img 20210812 091658 cropped
Robust Machine Learning
Sebastian Blaes
  • Postdoctoral Researcher
Thumb ticker sm clspicture
Autonomous Learning
Cristina Pinneri
Thumb ticker sm georg 2018 crop small
Empirical Inference, Autonomous Learning
Georg Martius
Senior Research Scientist
Solo8envsafetyoverlay v2

We introduce a simple but effective method for managing risk in zero-order trajectory optimization that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.

Author(s): Marin Vlastelica* and Sebastian Blaes* and Cristina Pinneri and Georg Martius
Book Title: Conference on Robot Learning
Volume: 164
Year: 2022
Series: PMLR
Project(s):
Bibtex Type: Conference Paper (inproceedings)
Event Name: 5th Conference on Robot Learning (CoRL 2021)
State: Published
URL: https://openreview.net/forum?id=WqUl7sNkDre
Electronic Archiving: grant_archive
Note: *Equal Contribution
Links:
Attachments:

BibTex 

@inproceedings{VlastelicaBlaesEtal2021:riskaverse,
  title = {Risk-Averse Zero-Order Trajectory Optimization},
  booktitle = {Conference on Robot Learning},
  abstract = {We introduce a simple but effective method for managing risk in zero-order trajectory optimization that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks. Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.},
  volume = {164},
  series = {PMLR},
  year = {2022},
  note = {*Equal Contribution},
  slug = {vlastelica2021riskaverse},
  author = {Vlastelica*, Marin and Blaes*, Sebastian and Pinneri, Cristina and Martius, Georg},
  url = {https://openreview.net/forum?id=WqUl7sNkDre}
}