Sven Magg

Wenhao Lu, Xufeng Zhao, Sven Magg et al.

Explaining the behaviour of intelligent agents learned by reinforcement learning (RL) to humans is challenging yet crucial due to their incomprehensible proprioceptive states, variational intermediate goals, and resultant unpredictability. Moreover, one-step explanations for RL agents can be ambiguous as they fail to account for the agent's future behaviour at each transition, adding to the complexity of explaining robot actions. By leveraging abstracted actions that map to task-specific primitives, we avoid explanations on the movement level. To further improve the transparency and explainability of robotic systems, we propose an explainable Q-Map learning framework that combines reward decomposition (RD) with abstracted action spaces, allowing for non-ambiguous and high-level explanations based on object properties in the task. We demonstrate the effectiveness of our framework through quantitative and qualitative analysis of two robotic scenarios, showcasing visual and textual explanations, from output artefacts of RD explanations, that are easy for humans to comprehend. Additionally, we demonstrate the versatility of integrating these artefacts with large language models (LLMs) for reasoning and interactive querying.

Martin Gromniak, Sven Magg, Stefan Wermter

Neural fields are neural networks which map coordinates to a desired signal. When a neural field should jointly model multiple signals, and not memorize only one, it needs to be conditioned on a latent code which describes the signal at hand. Despite being an important aspect, there has been little research on conditioning strategies for neural fields. In this work, we explore the use of neural fields as decoders for 2D semantic segmentation. For this task, we compare three conditioning methods, simple concatenation of the latent code, Feature Wise Linear Modulation (FiLM), and Cross-Attention, in conjunction with latent codes which either describe the full image or only a local region of the image. Our results show a considerable difference in performance between the examined conditioning strategies. Furthermore, we show that conditioning via Cross-Attention achieves the best results and is competitive with a CNN-based decoder for semantic segmentation.

Martin Gromniak, Jan-Gerrit Habekost, Sebastian Kamp et al.

We introduce a Generalizable Neural Radiance Field approach for predicting 3D workspace occupancy from egocentric robot observations. Unlike prior methods operating in camera-centric coordinates, our model constructs occupancy representations in a global workspace frame, making it directly applicable to robotic manipulation. The model integrates flexible source views and generalizes to unseen object arrangements without scene-specific finetuning. We demonstrate the approach on a humanoid robot and evaluate predicted geometry against 3D sensor ground truth. Trained on 40 real scenes, our model achieves 26mm reconstruction error, including occluded regions, validating its ability to infer complete 3D occupancy beyond traditional stereo vision methods.

Egor Lakomkin, Sven Magg, Cornelius Weber et al.

In this paper, we describe KT-Speech-Crawler: an approach for automatic dataset construction for speech recognition by crawling YouTube videos. We outline several filtering and post-processing steps, which extract samples that can be used for training end-to-end neural speech recognition systems. In our experiments, we demonstrate that a single-core version of the crawler can obtain around 150 hours of transcribed speech within a day, containing an estimated 3.5% word error rate in the transcriptions. Automatically collected samples contain reading and spontaneous speech recorded in various conditions including background noise and music, distant microphone recordings, and a variety of accents and reverberation. When training a deep neural network on speech recognition, we observed around 40\% word error rate reduction on the Wall Street Journal dataset by integrating 200 hours of the collected samples into the training set. The demo (http://emnlp-demo.lakomkin.me/) and the crawler code (https://github.com/EgorLakomkin/KTSpeechCrawler) are publicly available.

Wenhao Lu, Xufeng Zhao, Thilo Fryen et al.

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing problem, making it difficult for users to grasp the reasons behind an agent's behaviour. Various approaches have been explored to address this problem, with one promising avenue being reward decomposition (RD). RD is appealing as it sidesteps some of the concerns associated with other methods that attempt to rationalize an agent's behaviour in a post-hoc manner. RD works by exposing various facets of the rewards that contribute to the agent's objectives during training. However, RD alone has limitations as it primarily offers insights based on sub-rewards and does not delve into the intricate cause-and-effect relationships that occur within an RL agent's neural model. In this paper, we present an extension of RD that goes beyond sub-rewards to provide more informative explanations. Our approach is centred on a causal learning framework that leverages information-theoretic measures for explanation objectives that encourage three crucial properties of causal factors: causal sufficiency, sparseness, and orthogonality. These properties help us distill the cause-and-effect relationships between the agent's states and actions or rewards, allowing for a deeper understanding of its decision-making processes. Our framework is designed to generate local explanations and can be applied to a wide range of RL tasks with multiple reward channels. Through a series of experiments, we demonstrate that our approach offers more meaningful and insightful explanations for the agent's action selections.

Henrique Siqueira, Pablo Barros, Sven Magg et al.

In domains where computational resources and labeled data are limited, such as in robotics, deep networks with millions of weights might not be the optimal solution. In this paper, we introduce a connectivity scheme for pyramidal architectures to increase their capacity for learning features. Experiments on facial expression recognition of unseen people demonstrate that our approach is a potential candidate for applications with restricted resources, due to good generalization performance and low computational cost. We show that our approach generalizes as well as convolutional architectures in this task but uses fewer trainable parameters and is more robust for low-resolution faces.

Henrique Siqueira, Alexander Sutherland, Pablo Barros et al.

Effectively recognising and applying emotions to interactions is a highly desirable trait for social robots. Implicitly understanding how subjects experience different kinds of actions and objects in the world is crucial for natural HRI interactions, with the possibility to perform positive actions and avoid negative actions. In this paper, we utilize the NICO robot's appearance and capabilities to give the NICO the ability to model a coherent affective association between a perceived auditory stimulus and a temporally asynchronous emotion expression. This is done by combining evaluations of emotional valence from vision and language. NICO uses this information to make decisions about when to extend conversations in order to accrue more affective information if the representation of the association is not coherent. Our primary contribution is providing a NICO robot with the ability to learn the affective associations between a perceived auditory stimulus and an emotional expression. NICO is able to do this for both individual subjects and specific stimuli, with the aid of an emotion-driven dialogue system that rectifies emotional expression incoherences. The robot is then able to use this information to determine a subject's enjoyment of perceived auditory stimuli in a real HRI scenario.

Henrique Siqueira, Pablo Barros, Sven Magg et al.

Social robots able to continually learn facial expressions could progressively improve their emotion recognition capability towards people interacting with them. Semi-supervised learning through ensemble predictions is an efficient strategy to leverage the high exposure of unlabelled facial expressions during human-robot interactions. Traditional ensemble-based systems, however, are composed of several independent classifiers leading to a high degree of redundancy, and unnecessary allocation of computational resources. In this paper, we proposed an ensemble based on convolutional networks where the early layers are strong low-level feature extractors, and their representations shared with an ensemble of convolutional branches. This results in a significant drop in redundancy of low-level features processing. Training in a semi-supervised setting, we show that our approach is able to continually learn facial expressions through ensemble predictions using unlabelled samples from different data distributions.

Henrique Siqueira, Sven Magg, Stefan Wermter

Ensemble methods, traditionally built with independently trained de-correlated models, have proven to be efficient methods for reducing the remaining residual generalization error, which results in robust and accurate methods for real-world applications. In the context of deep learning, however, training an ensemble of deep networks is costly and generates high redundancy which is inefficient. In this paper, we present experiments on Ensembles with Shared Representations (ESRs) based on convolutional networks to demonstrate, quantitatively and qualitatively, their data processing efficiency and scalability to large-scale datasets of facial expressions. We show that redundancy and computational load can be dramatically reduced by varying the branching level of the ESR without loss of diversity and generalization power, which are both important for ensemble performance. Experiments on large-scale datasets suggest that ESRs reduce the remaining residual generalization error on the AffectNet and FER+ datasets, reach human-level performance, and outperform state-of-the-art methods on facial expression recognition in the wild using emotion and affect concepts.

Chandrakant Bothe, Cornelius Weber, Sven Magg et al.

The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. Emotion interpretation makes us understand feelings and dialogue acts reflect the intentions and performative functions in the utterances. However, most of the textual and multi-modal conversational emotion corpora contain only emotion labels but not dialogue acts. To address this problem, we propose to use a pool of various recurrent neural models trained on a dialogue act corpus, with and without context. These neural models annotate the emotion corpora with dialogue act labels, and an ensemble annotator extracts the final dialogue act label. We annotated two accessible multi-modal emotion corpora: IEMOCAP and MELD. We analyzed the co-occurrence of emotion and dialogue act labels and discovered specific relations. For example, Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy. We make the Emotional Dialogue Acts (EDA) corpus publicly available to the research community for further study and analysis.

Sayantan Auddy, Sven Magg, Stefan Wermter

The complexity of bipedal locomotion may be attributed to the difficulty in synchronizing joint movements while at the same time achieving high-level objectives such as walking in a particular direction. Artificial central pattern generators (CPGs) can produce synchronized joint movements and have been used in the past for bipedal locomotion. However, most existing CPG-based approaches do not address the problem of high-level control explicitly. We propose a novel hierarchical control mechanism for bipedal locomotion where an optimized CPG network is used for joint control and a neural network acts as a high-level controller for modulating the CPG network. By separating motion generation from motion modulation, the high-level controller does not need to control individual joints directly but instead can develop to achieve a higher goal using a low-dimensional control signal. The feasibility of the hierarchical controller is demonstrated through simulation experiments using the Neuro-Inspired Companion (NICO) robot. Experimental results demonstrate the controller's ability to function even without the availability of an exact robot model.

Marcus Soll, Tobias Hinz, Sven Magg et al.

Adversarial examples are artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classification, especially as research shows that many adversarial examples are transferable between different classifiers. In this work, we evaluate the performance of a popular defensive strategy for adversarial examples called defensive distillation, which can be successful in hardening neural networks against adversarial examples in the image domain. However, instead of applying defensive distillation to networks for image classification, we examine, for the first time, its performance on text classification tasks and also evaluate its effect on the transferability of adversarial text examples. Our results indicate that defensive distillation only has a minimal impact on text classifying neural networks and does neither help with increasing their robustness against adversarial examples nor prevent the transferability of adversarial examples between neural networks.

Francisco Cruz, Sven Magg, Yukie Nagai et al.

Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which uses a parent-like trainer to propose the next action to be performed and by doing so reduces the search space by advice. On some occasions, the trainer may be another artificial agent which in turn was trained using reinforcement learning methods to afterward becoming an advisor for other learner-agents. In this work, we analyze internal representations and characteristics of artificial agents to determine which agent may outperform others to become a better trainer-agent. Using a polymath agent, as compared to a specialist agent, an advisor leads to a larger reward and faster convergence of the reward signal and also to a more stable behavior in terms of the state visit frequency of the learner-agents. Moreover, we analyze system interaction parameters in order to determine how influential they are in the apprenticeship process, where the consistency of feedback is much more relevant when dealing with different learner obedience parameters.

Egor Lakomkin, Mohammad Ali Zamani, Cornelius Weber et al.

Previous work on emotion recognition demonstrated a synergistic effect of combining several modalities such as auditory, visual, and transcribed text to estimate the affective state of a speaker. Among these, the linguistic modality is crucial for the evaluation of an expressed emotion. However, manually transcribed spoken text cannot be given as input to a system practically. We argue that using ground-truth transcriptions during training and evaluation phases leads to a significant discrepancy in performance compared to real-world conditions, as the spoken text has to be recognized on the fly and can contain speech recognition mistakes. In this paper, we propose a method of integrating an automatic speech recognition (ASR) output with a character-level recurrent neural network for sentiment recognition. In addition, we conduct several experiments investigating sentiment recognition for human-robot interaction in a noise-realistic scenario which is challenging for the ASR systems. We quantify the improvement compared to using only the acoustic modality in sentiment recognition. We demonstrate the effectiveness of this approach on the Multimodal Corpus of Sentiment Intensity (MOSI) by achieving 73,6% accuracy in a binary sentiment classification task, exceeding previously reported results that use only acoustic input. In addition, we set a new state-of-the-art performance on the MOSI dataset (80.4% accuracy, 2% absolute improvement).

Di Fu, Pablo Barros, German I. Parisi et al.

The efficient integration of multisensory observations is a key property of the brain that yields the robust interaction with the environment. However, artificial multisensory perception remains an open issue especially in situations of sensory uncertainty and conflicts. In this work, we extend previous studies on audio-visual (AV) conflict resolution in complex environments. In particular, we focus on quantitatively assessing the contribution of semantic congruency during an AV spatial localization task. In addition to conflicts in the spatial domain (i.e. spatially misaligned stimuli), we consider gender-specific conflicts with male and female avatars. Our results suggest that while semantically related stimuli affect the magnitude of the visual bias (perceptually shifting the location of the sound towards a semantically congruent visual cue), humans still strongly rely on environmental statistics to solve AV conflicts. Together with previously reported results, this work contributes to a better understanding of how multisensory integration and conflict resolution can be modelled in artificial agents and robots operating in real-world environments.

Manfred Eppe, Sven Magg, Stefan Wermter

Deep reinforcement learning has recently gained a focus on problems where policy or value functions are independent of goals. Evidence exists that the sampling of goals has a strong effect on the learning performance, but there is a lack of general mechanisms that focus on optimizing the goal sampling process. In this work, we present a simple and general goal masking method that also allows us to estimate a goal's difficulty level and thus realize a curriculum learning approach for deep RL. Our results indicate that focusing on goals with a medium difficulty level is appropriate for deep deterministic policy gradient (DDPG) methods, while an "aim for the stars and reach the moon-strategy", where hard goals are sampled much more often than simple goals, leads to the best learning performance in cases where DDPG is combined with for hindsight experience replay (HER). We demonstrate that the approach significantly outperforms standard goal sampling for different robotic object manipulation problems.

Tobias Hinz, Nicolás Navarro-Guerrero, Sven Magg et al.

Most learning algorithms require the practitioner to manually set the values of many hyperparameters before the learning process can begin. However, with modern algorithms, the evaluation of a given hyperparameter setting can take a considerable amount of time and the search space is often very high-dimensional. We suggest using a lower-dimensional representation of the original data to quickly identify promising areas in the hyperparameter space. This information can then be used to initialize the optimization algorithm for the original, higher-dimensional data. We compare this approach with the standard procedure of optimizing the hyperparameters only on the original input. We perform experiments with various state-of-the-art hyperparameter optimization algorithms such as random search, the tree of parzen estimators (TPEs), sequential model-based algorithm configuration (SMAC), and a genetic algorithm (GA). Our experiments indicate that it is possible to speed up the optimization process by using lower-dimensional data representations at the beginning, while increasing the dimensionality of the input later in the optimization process. This is independent of the underlying optimization procedure, making the approach promising for many existing hyperparameter optimization algorithms.

Chandrakant Bothe, Sven Magg, Cornelius Weber et al.

Spoken language understanding is one of the key factors in a dialogue system, and a context in a conversation plays an important role to understand the current utterance. In this work, we demonstrate the importance of context within the dialogue for neural network models through an online web interface live demo. We developed two different neural models: a model that does not use context and a context-based model. The no-context model classifies dialogue acts at an utterance-level whereas the context-based model takes some preceding utterances into account. We make these trained neural models available as a live demo called Discourse-Wizard using a modular server architecture. The live demo provides an easy to use interface for conversational analysis and for discovering deep discourse structures in a conversation.

Chandrakant Bothe, Cornelius Weber, Sven Magg et al.

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within the conversation for most of the classes. Nevertheless, previous models of dialogue act classification work on the utterance-level and only very few consider context. We propose a novel context-based learning method to classify dialogue acts using a character-level language model utterance representation, and we notice significant improvement. We evaluate this method on the Switchboard Dialogue Act corpus, and our results show that the consideration of the preceding utterances as a context of the current utterance improves dialogue act detection.

Chandrakant Bothe, Sven Magg, Cornelius Weber et al.

Recent approaches for dialogue act recognition have shown that context from preceding utterances is important to classify the subsequent one. It was shown that the performance improves rapidly when the context is taken into account. We propose an utterance-level attention-based bidirectional recurrent neural network (Utt-Att-BiRNN) model to analyze the importance of preceding utterances to classify the current one. In our setup, the BiRNN is given the input set of current and preceding utterances. Our model outperforms previous models that use only preceding utterances as context on the used corpus. Another contribution of the article is to discover the amount of information in each utterance to classify the subsequent one and to show that context-based learning not only improves the performance but also achieves higher confidence in the classification. We use character- and word-level features to represent the utterances. The results are presented for character and word feature representations and as an ensemble model of both representations. We found that when classifying short utterances, the closest preceding utterances contributes to a higher degree.

Egor Lakomkin, Mohammad Ali Zamani, Cornelius Weber et al.

Speech emotion recognition (SER) is an important aspect of effective human-robot collaboration and received a lot of attention from the research community. For example, many neural network-based architectures were proposed recently and pushed the performance to a new level. However, the applicability of such neural SER models trained only on in-domain data to noisy conditions is currently under-researched. In this work, we evaluate the robustness of state-of-the-art neural acoustic emotion recognition models in human-robot interaction scenarios. We hypothesize that a robot's ego noise, room conditions, and various acoustic events that can occur in a home environment can significantly affect the performance of a model. We conduct several experiments on the iCub robot platform and propose several novel ways to reduce the gap between the model's performance during training and testing in real-world conditions. Furthermore, we observe large improvements in the model performance on the robot and demonstrate the necessity of introducing several data augmentation techniques like overlaying background noise and loudness variations to improve the robustness of the neural approaches.

Egor Lakomkin, Mohammad Ali Zamani, Cornelius Weber et al.

Acoustically expressed emotions can make communication with a robot more efficient. Detecting emotions like anger could provide a clue for the robot indicating unsafe/undesired situations. Recently, several deep neural network-based models have been proposed which establish new state-of-the-art results in affective state evaluation. These models typically start processing at the end of each utterance, which not only requires a mechanism to detect the end of an utterance but also makes it difficult to use them in a real-time communication scenario, e.g. human-robot interaction. We propose the EmoRL model that triggers an emotion classification as soon as it gains enough confidence while listening to a person speaking. As a result, we minimize the need for segmenting the audio signal for classification and achieve lower latency as the audio signal is processed incrementally. The method is competitive with the accuracy of a strong baseline model, while allowing much earlier prediction.

Egor Lakomkin, Cornelius Weber, Sven Magg et al.

Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion perception resulting in low annotator agreement, and the uncertainty about which features are the most relevant and robust ones for classification. In this paper, we will tackle the latter problem. Inspired by the recent success of transfer learning methods we propose a set of architectures which utilize neural representations inferred by training on large speech databases for the acoustic emotion recognition task. Our experiments on the IEMOCAP dataset show ~10% relative improvements in the accuracy and F1-score over the baseline recurrent neural network which is trained end-to-end for emotion recognition.

German I. Parisi, Pablo Barros, Di Fu et al.

Crossmodal conflict resolution is crucial for robot sensorimotor coupling through the interaction with the environment, yielding swift and robust behaviour also in noisy conditions. In this paper, we propose a neurorobotic experiment in which an iCub robot exhibits human-like responses in a complex crossmodal environment. To better understand how humans deal with multisensory conflicts, we conducted a behavioural study exposing 33 subjects to congruent and incongruent dynamic audio-visual cues. In contrast to previous studies using simplified stimuli, we designed a scenario with four animated avatars and observed that the magnitude and extension of the visual bias are related to the semantics embedded in the scene, i.e., visual cues that are congruent with environmental statistics (moving lips and vocalization) induce the strongest bias. We implement a deep learning model that processes stereophonic sound, facial features, and body motion to trigger a discrete behavioural response. After training the model, we exposed the iCub to the same experimental conditions as the human subjects, showing that the robot can replicate similar responses in real time. Our interdisciplinary work provides important insights into how crossmodal conflict resolution can be modelled in robots and introduces future research directions for the efficient combination of sensory observations with internally generated knowledge and expectations.