Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Achterhold, Jan"'
Mobile robots should be capable of planning cost-efficient paths for autonomous navigation. Typically, the terrain and robot properties are subject to variations. For instance, properties of the terrain such as friction may vary across different loca
Externí odkaz:
http://arxiv.org/abs/2409.11452
Object-centric scene decompositions are important representations for downstream tasks in fields such as computer vision and robotics. The recently proposed Slot Attention module, already leveraged by several derivative works for image segmentation a
Externí odkaz:
http://arxiv.org/abs/2407.04170
In autonomous navigation settings, several quantities can be subject to variations. Terrain properties such as friction coefficients may vary over time depending on the location of the robot. Also, the dynamics of the robot may change due to, e.g., d
Externí odkaz:
http://arxiv.org/abs/2307.09206
Autor:
Achterhold, Jan, Tobuschat, Philip, Ma, Hao, Buechler, Dieter, Muehlebach, Michael, Stueckler, Joerg
In this paper, we present a method for table tennis ball trajectory filtering and prediction. Our gray-box approach builds on a physical model. At the same time, we use data to learn parameters of the dynamics model, of an extended Kalman filter, and
Externí odkaz:
http://arxiv.org/abs/2305.15189
Problems which require both long-horizon planning and continuous control capabilities pose significant challenges to existing reinforcement learning agents. In this paper we introduce a novel hierarchical reinforcement learning agent which links temp
Externí odkaz:
http://arxiv.org/abs/2207.05018
Autor:
Achterhold, Jan, Stueckler, Joerg
In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transi
Externí odkaz:
http://arxiv.org/abs/2102.11394
Video representation learning has recently attracted attention in computer vision due to its applications for activity and scene forecasting or vision-based planning and control. Video prediction models often learn a latent representation of video wh
Externí odkaz:
http://arxiv.org/abs/2009.08292
Autor:
Pinneri, Cristina, Sawant, Shambhuraj, Blaes, Sebastian, Achterhold, Jan, Stueckler, Joerg, Rolinek, Michal, Martius, Georg
Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency prevents th
Externí odkaz:
http://arxiv.org/abs/2008.06389
Planning is a powerful approach to control problems with known environment dynamics. In unknown environments the agent needs to learn a model of the system dynamics to make planning applicable. This is particularly challenging when the underlying sta
Externí odkaz:
http://arxiv.org/abs/2005.03770
Autor:
Kandukuri, Rama Krishna1 (AUTHOR) rama.kandukuri@tue.mpg.de, Achterhold, Jan1 (AUTHOR), Moeller, Michael2 (AUTHOR), Stueckler, Joerg1 (AUTHOR)
Publikováno v:
International Journal of Computer Vision. Jan2022, Vol. 130 Issue 1, p3-16. 14p.
