no code implementations • 27 Sep 2023 • Rama Krishna Kandukuri, Michael Strecke, Joerg Stueckler
In this paper, we propose a novel approach for real-to-sim which tracks rigid objects in 3D from RGB-D images and infers physical properties of the objects.
no code implementations • 20 Sep 2023 • Haolong Li, Joerg Stueckler
Our method calibrates and adapts the dynamics model online and facilitates accurate forward prediction conditioned on future control inputs.
no code implementations • 18 Jul 2023 • Suresh Guttikonda, Jan Achterhold, Haolong Li, Joschka Boedecker, Joerg Stueckler
Terrain properties such as friction coefficients may vary over time depending on the location of the robot.
no code implementations • 24 May 2023 • Jan Achterhold, Philip Tobuschat, Hao Ma, Dieter Buechler, Michael Muehlebach, Joerg Stueckler
Our gray-box approach builds on a physical model.
no code implementations • 3 May 2023 • Cathrin Elich, Iro Armeni, Martin R. Oswald, Marc Pollefeys, Joerg Stueckler
Our approach compares favorably to previous state-of-the-art object-level matching approaches and achieves improved performance over a pure keypoint-based approach for large view-point changes.
no code implementations • 11 Jul 2022 • Jan Achterhold, Markus Krimmel, Joerg Stueckler
In this paper we introduce a novel hierarchical reinforcement learning agent which links temporally extended skills for continuous control with a forward model in a symbolic discrete abstraction of the environment's state for planning.
no code implementations • 14 Apr 2022 • Haolong Li, Joerg Stueckler
Visual-inertial odometry (VIO) is an important technology for autonomous robots with power and payload constraints.
no code implementations • 30 Nov 2021 • Michael Strecke, Joerg Stueckler
Differentiable physics is a powerful tool in computer vision and robotics for scene understanding and reasoning about interactions.
no code implementations • 29 Mar 2021 • Haolong Li, Joerg Stueckler
Event cameras are promising devices for lowlatency tracking and high-dynamic range imaging.
1 code implementation • 22 Feb 2021 • Jan Achterhold, Joerg Stueckler
In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties.
no code implementations • 8 Oct 2020 • Cathrin Elich, Martin R. Oswald, Marc Pollefeys, Joerg Stueckler
Our approach learns to decompose images of synthetic scenes with multiple objects on a planar surface into its constituent scene objects and to infer their 3D properties from a single view.
no code implementations • 28 Sep 2020 • Cathrin Elich, Martin R. Oswald, Marc Pollefeys, Joerg Stueckler
By differentiable rendering, we train our model to decompose scenes self-supervised from RGB-D images.
1 code implementation • 14 Aug 2020 • Cristina Pinneri, Shambhuraj Sawant, Sebastian Blaes, Jan Achterhold, Joerg Stueckler, Michal Rolinek, Georg Martius
However, their sampling inefficiency prevents them from being used for real-time planning and control.
Model-based Reinforcement Learning reinforcement-learning +1
1 code implementation • 9 Apr 2020 • Michael Strecke, Joerg Stueckler
To the best of our knowledge, our approach is the first method to incorporate such physical plausibility constraints on object intersections for shape completion of dynamic objects in an energy minimization framework.
no code implementations • 22 Apr 2019 • Rui Wang, Nan Yang, Joerg Stueckler, Daniel Cremers
Scene understanding from images is a challenging problem encountered in autonomous driving.