Matthias Höfer

Matthias Hofer, Tuan Anh Le, Roger Levy et al.

Humans have the ability to rapidly understand rich combinatorial concepts from limited data. Here we investigate this ability in the context of auditory signals, which have been evolved in a cultural transmission experiment to study the emergence of combinatorial structure in language. We propose a neuro-symbolic generative model which combines the strengths of previous approaches to concept learning. Our model performs fast inference drawing on neural network methods, while still retaining the interpretability and generalization from limited data seen in structured generative approaches. This model outperforms a purely neural network-based approach on classification as evaluated against both ground truth and human experimental classification preferences, and produces superior reproductions of observed signals as well. Our results demonstrate the power of flexible combined neural-symbolic architectures for human-like generalization in raw perceptual domains and offers a step towards developing precise computational models of inductive biases in language evolution.

Yaohui Huang, Matthias Hofer, Raffaello D'Andrea

This paper presents an offset-free model predictive controller for fast and accurate control of a spherical soft robotic arm. In this control scheme, a linear model is combined with an online disturbance estimation technique to systematically compensate model deviations. Dynamic effects such as material relaxation resulting from the use of soft materials can be addressed to achieve offset-free tracking. The tracking error can be reduced by 35% when compared to a standard model predictive controller without a disturbance compensation scheme. The improved tracking performance enables the realization of a ball catching application, where the spherical soft robotic arm can catch a ball thrown by a human.

Jasan Zughaibi, Matthias Hofer, Raffaello D'Andrea

This paper presents the application of a learning control approach for the realization of a fast and reliable pick-and-place application with a spherical soft robotic arm. The arm is characterized by a lightweight design and exhibits compliant behavior due to the soft materials deployed. A soft, continuum joint is employed, which allows for simultaneous control of one translational and two rotational degrees of freedom in a single joint. This allows us to axially approach and pick an object with the attached suction cup during the pick-and-place application. A control allocation based on pressure differences and the antagonistic actuator configuration is introduced, allowing decoupling of the system dynamics and simplifying the modeling and control. A linear parameter-varying model is identified, which is parametrized by the attached load mass and a parameter related to the joint stiffness. A gain-scheduled feedback controller is proposed, which asymptotically stabilizes the robotic system for aggressive tuning and over large variations of the parameters considered. The control architecture is augmented with an iterative learning control scheme enabling accurate tracking of aggressive trajectories involving set point transitions of 60 degrees within 0.3 seconds (no mass attached) to 0.6 seconds (load mass attached). The modeling and control approach proposed results in a reliable realization of a pick-and-place application and is experimentally demonstrated.

Matthias Hofer, Lukas Spannagl, Raffaello D'Andrea

This paper presents the application of an iterative learning control scheme to improve the position tracking performance for an articulated soft robotic arm during aggressive maneuvers. Two antagonistically arranged, inflatable bellows actuate the robotic arm and provide high compliance while enabling fast actuation. Switching valves are used for pressure control of the soft actuators. A norm-optimal iterative learning control scheme based on a linear model of the system is presented and applied in parallel with a feedback controller. The learning scheme is experimentally evaluated on an aggressive trajectory involving set point shifts of 60 degrees within 0.2 seconds. The effectiveness of the learning approach is demonstrated by a reduction of the root-mean-square tracking error from 13 degrees to less than 2 degrees after applying the learning scheme for less than 30 iterations.

Judy Hanwen Shen, Matthias Hofer, Bjarke Felbo et al.

Simple reference games are of central theoretical and empirical importance in the study of situated language use. Although language provides rich, compositional truth-conditional semantics to facilitate reference, speakers and listeners may sometimes lack the overall lexical and cognitive resources to guarantee successful reference through these means alone. However, language also has rich associational structures that can serve as a further resource for achieving successful reference. Here we investigate this use of associational information in a setting where only associational information is available: a simplified version of the popular game Codenames. Using optimal experiment design techniques, we compare a range of models varying in the type of associative information deployed and in level of pragmatic sophistication against human behavior. In this setting, we find that listeners' behavior reflects direct bigram collocational associations more strongly than word-embedding or semantic knowledge graph-based associations and that there is little evidence for pragmatically sophisticated behavior by either speakers or listeners of the type that might be predicted by recursive-reasoning models such as the Rational Speech Acts theory. These results shed light on the nature of the lexical resources that speakers and listeners can bring to bear in achieving reference through associative meaning alone.