Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Rohr, Alexander"'
Diffusion models have recently gained popularity for policy learning in robotics due to their ability to capture high-dimensional and multimodal distributions. However, diffusion policies are inherently stochastic and typically trained offline, limit
Externí odkaz:
http://arxiv.org/abs/2412.09342
Publikováno v:
von Rohr, Alexander, Stenger, David, Scheurenberg, Dominik and Trimpe, Sebastian. "Local Bayesian optimization for controller tuning with crash constraints" at - Automatisierungstechnik, vol. 72, no. 4, 2024, pp. 281-292
Controller tuning is crucial for closed-loop performance but often involves manual adjustments. Although Bayesian optimization (BO) has been established as a data-efficient method for automated tuning, applying it to large and high-dimensional search
Externí odkaz:
http://arxiv.org/abs/2411.16267
How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on data-efficient policy i
Externí odkaz:
http://arxiv.org/abs/2411.14246
Deep Reinforcement Learning (DRL) in simulation often results in brittle and unrealistic learning outcomes. To push the agent towards more desirable solutions, prior information can be injected in the learning process through, for instance, reward sh
Externí odkaz:
http://arxiv.org/abs/2410.03246
We propose a data-driven control method for systems with aleatoric uncertainty, for example, robot fleets with variations between agents. Our method leverages shared trajectory data to increase the robustness of the designed controller and thus facil
Externí odkaz:
http://arxiv.org/abs/2306.16973
Automated bin-picking is a prerequisite for fully automated manufacturing and warehouses. To successfully pick an item from an unstructured bin the robot needs to first detect possible grasps for the objects, decide on the object to remove and conseq
Externí odkaz:
http://arxiv.org/abs/2211.11089
We consider the problem of sequentially optimizing a time-varying objective function using time-varying Bayesian optimization (TVBO). To cope with stale data arising from time variations, current approaches to TVBO require prior knowledge of a consta
Externí odkaz:
http://arxiv.org/abs/2208.10790
Robust controllers ensure stability in feedback loops designed under uncertainty but at the cost of performance. Model uncertainty in time-invariant systems can be reduced by recently proposed learning-based methods, which improve the performance of
Externí odkaz:
http://arxiv.org/abs/2207.14252
Publikováno v:
IEEE 61st Conference on Decision and Control (2022), p. 4046-4052
Changing conditions or environments can cause system dynamics to vary over time. To ensure optimal control performance, controllers should adapt to these changes. When the underlying cause and time of change is unknown, we need to rely on online data
Externí odkaz:
http://arxiv.org/abs/2207.11120