103 citations · 138 across the 13 of their papers we have counts for
15 papers
WAMJET: A Harness for World Action Model Acceleration
Le Chen, Lixin Liu, Jan Schneider +4
World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive. Although exis…
Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks
Jan Schneider, Mridul Mahajan, Le Chen +4
Tendon drives paired with soft muscle actuation enable faster and safer robots while potentially accelerating skill acquisition. Still, these systems are rarely used in practice du…
Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies
Armin Kekić, Jan Schneider, Dieter Büchler +2
Why do reinforcement learning (RL) policies fail or succeed? This is a challenging question due to the complex, high-dimensional nature of agent-environment interactions. In this w…
RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands
Yi Zhao, Le Chen, Jan Schneider +5
It has been a long-standing research goal to endow robot hands with human-level dexterity. Bi-manual robot piano playing constitutes a task that combines challenges from dynamic ta…
Learning to Control Emulated Muscles in Real Robots: Towards Exploiting Bio-Inspired Actuator Morphology
Pierre Schumacher, Lorenz Krause, Jan Schneider +3
Recent studies have demonstrated the immense potential of exploiting muscle actuator morphology for natural and robust movement -- in simulation. A validation on real robotic hardw…
Identifying Policy Gradient Subspaces
Jan Schneider, Pierre Schumacher, Simon Guist +4
Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optim…
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Embodiment Collaboration, Abby O'Neill, Abdul Rehman +291
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, thi…
Synchronizing Machine Learning Algorithms, Realtime Robotic Control and Simulated Environment with o80
Vincent Berenz, Felix Widmaier, Simon Guist +2
Robotic applications require the integration of various modalities, encompassing perception, control of real robots and possibly the control of simulated environments. While the st…
Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning
Simon Guist, Jan Schneider, Alexander Dittrich +3
Reinforcement learning has shown great potential in solving complex tasks when large amounts of data can be generated with little effort. In robotics, one approach to generate trai…
AIMY: An Open-source Table Tennis Ball Launcher for Versatile and High-fidelity Trajectory Generation
Alexander Dittrich, Jan Schneider, Simon Guist +5
To approach the level of advanced human players in table tennis with robots, generating varied ball trajectories in a reproducible and controlled manner is essential. Current ball…
Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
Isabell Wochner, Pierre Schumacher, Georg Martius +3
Humans are able to outperform robots in terms of robustness, versatility, and learning of new tasks in a wide variety of movements. We hypothesize that highly nonlinear muscle dyna…
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Pierre Schumacher, Daniel Häufle, Dieter Büchler +2
Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles. Reinforcement learning (RL) on large muscul…
Hierarchical Reinforcement Learning with Timed Subgoals
Nico Gürtler, Dieter Büchler, Georg Martius
Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoa…
Learning to Play Table Tennis From Scratch using Muscular Robots
Dieter Büchler, Simon Guist, Roberto Calandra +3
Dynamic tasks like table tennis are relatively easy to learn for humans but pose significant challenges to robots. Such tasks require accurate control of fast movements and precise…
Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots
Dieter Büchler, Roberto Calandra, Jan Peters
High-speed and high-acceleration movements are inherently hard to control. Applying learning to the control of such motions on anthropomorphic robot arms can improve the accuracy o…