3 citations · 3 across the 7 of their papers we have counts for
10 papers
PhysibleMDM: Enforcing Inference-Time Physical Feasibility Constraints on Motion Diffusion Models via Noise Optimization
Maximilian Stölzle, David Müller, Agon Serifi +3
Motion Diffusion Models (MDMs) can generate diverse and visually appealing human motion; yet, the resulting trajectories frequently violate physical constraints, limiting their dow…
BFMTrack: Latent Sequence Optimization for Physics-Based Motion Tracking with Behavioral Foundation Models
Thomas Rupf, Agon Serifi, David Müller +4
Behavioral Foundation Models (BFMs) offer a promising path toward universal physics-based character control by organizing a rich repertoire of physically plausible behaviors into a…
CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios
Michael Baumgartner, David Müller, Agon Serifi +4
Robust state estimation for highly dynamic motion of legged robots remains challenging, especially in dynamic, contact-rich scenarios. Traditional approaches often rely on binary c…
ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
David Müller, Agon Serifi, Sammy Christen +3
Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding…
Kamino: GPU-based Simulation of Rigid Multi-Body Physics with Kinematic Loops
Vassilios Tsounis, Guirec Maloisel, Christian Schumacher +6
We present Kamino, a GPU-based physics solver for massively parallel simulations of heterogeneous highly-coupled mechanical systems. Implemented in Python using NVIDIA Warp and int…
Olaf: Bringing an Animated Character to Life in the Physical World
David Müller, Espen Knoop, Dario Mylonopoulos +4
Animated characters often move in non-physical ways and have proportions that are far from a typical walking robot. This provides an ideal platform for innovation in both mechanica…
Robot Crash Course: Learning Soft and Stylized Falling
Pascal Strauch, David Müller, Sammy Christen +4
Despite recent advances in robust locomotion, bipedal robots operating in the real world remain at risk of falling. While most research focuses on preventing such events, we instea…
AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning
Lucas N. Alegre, Agon Serifi, Ruben Grandia +3
Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on…
Spline-based Transformers
Prashanth Chandran, Agon Serifi, Markus Gross +1
We introduce Spline-based Transformers, a novel class of Transformer models that eliminate the need for positional encoding. Inspired by workflows using splines in computer animati…
Autonomous Human-Robot Interaction via Operator Imitation
Sammy Christen, David Müller, Agon Serifi +5
Teleoperated robotic characters can perform expressive interactions with humans, relying on the operators' experience and social intuition. In this work, we propose to create auton…