Daniel F. B. Haeufle

Isabell Wochner, Pierre Schumacher, Georg Martius et al.

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 dynamics play a large role in providing inherent stability, which is favorable to learning. While recent advances have been made in applying modern learning techniques to muscle-actuated systems both in simulation as well as in robotics, so far, no detailed analysis has been performed to show the benefits of muscles when learning from scratch. Our study closes this gap and showcases the potential of muscle actuators for core robotics challenges in terms of data-efficiency, hyperparameter sensitivity, and robustness.

Pierre Schumacher, Thomas Geijtenbeek, Vittorio Caggiano et al.

Humans excel at robust bipedal walking in complex natural environments. In each step, they adequately tune the interaction of biomechanical muscle dynamics and neuronal signals to be robust against uncertainties in ground conditions. However, it is still not fully understood how the nervous system resolves the musculoskeletal redundancy to solve the multi-objective control problem considering stability, robustness, and energy efficiency. In computer simulations, energy minimization has been shown to be a successful optimization target, reproducing natural walking with trajectory optimization or reflex-based control methods. However, these methods focus on particular motions at a time and the resulting controllers are limited when compensating for perturbations. In robotics, reinforcement learning~(RL) methods recently achieved highly stable (and efficient) locomotion on quadruped systems, but the generation of human-like walking with bipedal biomechanical models has required extensive use of expert data sets. This strong reliance on demonstrations often results in brittle policies and limits the application to new behaviors, especially considering the potential variety of movements for high-dimensional musculoskeletal models in 3D. Achieving natural locomotion with RL without sacrificing its incredible robustness might pave the way for a novel approach to studying human walking in complex natural environments. Videos: https://sites.google.com/view/naturalwalkingrl

Zhiming Hu, Zheming Yin, Daniel Haeufle et al.

We present HOIMotion - a novel approach for human motion forecasting during human-object interactions that integrates information about past body poses and egocentric 3D object bounding boxes. Human motion forecasting is important in many augmented reality applications but most existing methods have only used past body poses to predict future motion. HOIMotion first uses an encoder-residual graph convolutional network (GCN) and multi-layer perceptrons to extract features from body poses and egocentric 3D object bounding boxes, respectively. Our method then fuses pose and object features into a novel pose-object graph and uses a residual-decoder GCN to forecast future body motion. We extensively evaluate our method on the Aria digital twin (ADT) and MoGaze datasets and show that HOIMotion consistently outperforms state-of-the-art methods by a large margin of up to 8.7% on ADT and 7.2% on MoGaze in terms of mean per joint position error. Complementing these evaluations, we report a human study (N=20) that shows that the improvements achieved by our method result in forecasted poses being perceived as both more precise and more realistic than those of existing methods. Taken together, these results reveal the significant information content available in egocentric 3D object bounding boxes for human motion forecasting and the effectiveness of our method in exploiting this information.

Nikola Milosevic, Leonard Franz, Daniel Haeufle et al.

Constrained Markov decision processes (CMDPs) provide a principled model for handling constraints, such as safety and other auxiliary objectives, in reinforcement learning. The common approach of using additive-cost constraints and dual variables often hinders off-policy scalability. We propose a Control as Inference formulation based on stochastic decision horizons, where constraint violations attenuate reward contributions and shorten the effective planning horizon via state-action-dependent continuation. This yields survival-weighted objectives that remain replay-compatible for off-policy actor-critic learning. We propose two violation semantics, absorbing and virtual termination, that share the same survival-weighted return but result in distinct optimization structures that lead to SAC/MPO-style policy improvement. Experiments demonstrate improved sample efficiency and favorable return-violation trade-offs on standard benchmarks. Moreover, MPO with virtual termination (VT-MPO) scales effectively to our high-dimensional musculoskeletal Hyfydy setup.

Zhiming Hu, Guanhua Zhang, Zheming Yin et al.

Human hand and head movements are the most pervasive input modalities in extended reality (XR) and are significant for a wide range of applications. However, prior works on hand and head modelling in XR only explored a single modality or focused on specific applications. We present HaHeAE - a novel self-supervised method for learning generalisable joint representations of hand and head movements in XR. At the core of our method is an autoencoder (AE) that uses a graph convolutional network-based semantic encoder and a diffusion-based stochastic encoder to learn the joint semantic and stochastic representations of hand-head movements. It also features a diffusion-based decoder to reconstruct the original signals. Through extensive evaluations on three public XR datasets, we show that our method 1) significantly outperforms commonly used self-supervised methods by up to 74.0% in terms of reconstruction quality and is generalisable across users, activities, and XR environments, 2) enables new applications, including interpretable hand-head cluster identification and variable hand-head movement generation, and 3) can serve as an effective feature extractor for downstream tasks. Together, these results demonstrate the effectiveness of our method and underline the potential of self-supervised methods for jointly modelling hand-head behaviours in extended reality.

Zhiming Hu, Syn Schmitt, Daniel Haeufle et al.

We present GazeMotion, a novel method for human motion forecasting that combines information on past human poses with human eye gaze. Inspired by evidence from behavioural sciences showing that human eye and body movements are closely coordinated, GazeMotion first predicts future eye gaze from past gaze, then fuses predicted future gaze and past poses into a gaze-pose graph, and finally uses a residual graph convolutional network to forecast body motion. We extensively evaluate our method on the MoGaze, ADT, and GIMO benchmark datasets and show that it outperforms state-of-the-art methods by up to 7.4% improvement in mean per joint position error. Using head direction as a proxy to gaze, our method still achieves an average improvement of 5.5%. We finally report an online user study showing that our method also outperforms prior methods in terms of perceived realism. These results show the significant information content available in eye gaze for human motion forecasting as well as the effectiveness of our method in exploiting this information.

An Mo, Fabio Izzi, Daniel F. B. Haeufle et al.

Muscle models and animal observations suggest that physical damping is beneficial for stabilization. Still, only a few implementations of mechanical damping exist in compliant robotic legged locomotion. It remains unclear how physical damping can be exploited for locomotion tasks, while its advantages as sensor-free, adaptive force- and negative work-producing actuators are promising. In a simplified numerical leg model, we studied the energy dissipation from viscous and Coulomb damping during vertical drops with ground-level perturbations. A parallel spring-damper is engaged between touch-down and mid-stance, and its damper auto-disengages during mid-stance and takeoff. Our simulations indicate that an adjustable and viscous damper is desired. In hardware we explored effective viscous damping and adjustability and quantified the dissipated energy. We tested two mechanical, leg-mounted damping mechanisms; a commercial hydraulic damper, and a custom-made pneumatic damper. The pneumatic damper exploits a rolling diaphragm with an adjustable orifice, minimizing Coulomb damping effects while permitting adjustable resistance. Experimental results show that the leg-mounted, hydraulic damper exhibits the most effective viscous damping. Adjusting the orifice setting did not result in substantial changes of dissipated energy per drop, unlike adjusting damping parameters in the numerical model. Consequently, we also emphasize the importance of characterizing physical dampers during real legged impacts to evaluate their effectiveness for compliant legged locomotion.