This paper proposes a fully data-driven approach for optimal control of nonlinear control-affine systems represented by a stochastic diffusion. The focus is on the scenario where both the nonlinear dynamics and stage cost functions are unknown, while only a control penalty function and constraints are provided. To this end, we embed state probability densities into a reproducing kernel Hilbert space (RKHS) to leverage recent advances in operator regression, thereby identifying Markov transition operators associated with controlled diffusion processes. This operator learning approach integrates naturally with convex operator-theoretic Hamilton-Jacobi-Bellman recursions that scale linearly with state dimensionality, effectively solving a wide range of nonlinear optimal control problems. Numerical results demonstrate its ability to address diverse nonlinear control tasks, including the depth regulation of an autonomous underwater vehicle.

Marine debris poses an alarming threat to ocean environments. Conventional methods of sea and ocean cleaning rely heavily on manual collection, a process that has repeatedly demonstrated its inefficiency and extensive demand for resources. This paper presents the SeaClear system, a novel multi-robot platform designed to autonomously detect and collect marine debris, thereby offering a more efficient solution to this environmental challenge. An overview of the system is presented, followed by a detailed description of each robot’s capabilities. Leveraging artificial intelligence, the system employs the deep-learning-based computer vision algorithm You Only Look Once (YOLO) for the detection of underwater litter, addressing the challenges of poor visibility and hydrodynamic disturbances of underwater environments. Additionally, the paper explores the implemented navigation and control methodologies, which are an essential part of the workflow of the system. The performance of the designed system is validated via field tests conducted in a real-world underwater environment. Finally, directions for future work are proposed. • The infrastructure of a multi-robot system for autonomous underwater debris detection, mapping, and collection is presented. • The suitability of YOLO-based deep learning for real-time debris detection in shallow waters is validated. • The sensing and control scheme that enables the operation of the multi-robotic platform is presented. • The practical performance of the system is confirmed with field experiments to validate the feasibility of AI-driven underwater operations.

We propose a family of Gaussian processes (GP) for dynamical systems with linear time-invariant responses, which are nonlinear only in initial conditions. This linearity allows us to tractably quantify forecasting and representational uncertainty, simultaneously alleviating the challenge of computing the distribution of trajectories from a GP-based dynamical system and enabling a new probabilistic treatment of learning Koopman operator representations. Using a trajectory-based equivariance – which we refer to as Koopman equivariance – we obtain a GP model with enhanced generalization capabilities. To allow for large-scale regression, we equip our framework with variational inference based on suitable inducing points. Experiments demonstrate on-par and often better forecasting performance compared to kernel-based methods for learning dynamical systems.

Many machine learning approaches for decision making, such as reinforcement learning, rely on simulators or predictive models to forecast the time-evolution of quantities of interest, e.g., the state of an agent or the reward of a policy. Forecasts of such complex phenomena are commonly described by highly nonlinear dynamical systems, making their use in optimization-based decision-making challenging. Koopman operator theory offers a beneficial paradigm for addressing this problem by characterizing forecasts via linear time-invariant (LTI) ODEs, turning multi-step forecasts into sparse matrix multiplication. Though there exists a variety of learning approaches, they usually lack crucial learning-theoretic guarantees, making the behavior of the obtained models with increasing data and dimensionality unclear. We address the aforementioned by deriving a universal Koopman-invariant reproducing kernel Hilbert space (RKHS) that solely spans transformations into LTI dynamical systems. The resulting Koopman Kernel Regression (KKR) framework enables the use of statistical learning tools from function approximation for novel convergence results and generalization error bounds under weaker assumptions than existing work. Our experiments demonstrate superior forecasting performance compared to Koopman operator and sequential data predictors in RKHS.

Voronoi coverage control is a particular problem of importance in the area of multi-robot systems, which considers a network of multiple autonomous robots, tasked with optimally covering a large area. This is a common task for fleets of fixed-wing Unmanned Aerial Vehicles (UAVs), which are described in this work by a unicycle model with constant forward-speed constraints. We develop event-based control/communication algorithms to relax the resource requirements on wireless communication and control actuators, an important feature for battery-driven or otherwise energy-constrained systems. To overcome the drawback that the event-triggered algorithm requires continuous measurement of system states, we propose a self-triggered algorithm to estimate the next triggering time. Hardware experiments illustrate the theoretical results.

This article investigates a fully distributed cooperation scheme for networked mobile manipulators. To achieve cooperative task allocation in a distributed way, an adaptation-based estimation law is established for each robotic agent to estimate the desired local trajectory. In addition, wrench synthesis is analyzed in detail to lay a solid foundation for tight cooperation tasks. Together with the estimated task, a set of distributed adaptive (DA) controllers is proposed to achieve motion synchronization of the mobile manipulator ensemble over a directed graph with a spanning tree irrespective of the kinematic and dynamic uncertainties in both the mobile manipulators and the tightly grasped object. The controlled synchronization alleviates the performance degradation caused by the estimation/tracking discrepancy during the transient phase. The proposed scheme requires no persistent excitation condition and avoids the use of noisy Cartesian-space velocities. Furthermore, it is independent from the object's center of mass by employing formation-based task allocation and a task-oriented strategy. These attractive attributes facilitate the practical application of the scheme. It is theoretically proven that convergence of the cooperative task tracking error is guaranteed. Simulation results, as well as manipulation experiments with three mobile manipulators involved, validate the efficacy and demonstrate the expected performance of the proposed scheme.

This paper describes a new methodological approach and robot system to trigger more prosocial human reactions towards a robot by transferring social-psychological principles from human-human interaction to human-robot interaction (HRI). The main idea is to trigger increased helpfulness by proactively creating similarity through dynamic emotional adaption of the robot to the mood of the human. This is achieved in an explicit and implicit way: Explicitly, by a similarity-statement of the robot of being in the same mood as the user, and implicitly by controlling the affective parameters of facial and verbal expressions of a robot head in an interaction scenario such that the current values of the human mood in the dimensions of pleasure, arousal, and dominance (PAD) are matched. In a first step, this is accomplished by an initial self-assessment by the human participant to be extended by automatic emotion recognition modules in a later stage. The effectiveness of the approach is confirmed by significant experimental results.

It is the aim of our research to explore how multimodal feedback can help a robot to carry out itinerary requests effectively and satisfactory for a human interaction partner. We conducted two studies to evaluate the feedback setup of the Interactive Urban Robot (IURO), which navigates through public space autonomously and finds its way by asking pedestrians for directions. In a Wizard-of-Oz (WOz) experiment with novice users, different feedback modalities and various combinations of them were tested against each other to ascertain the ideal setup of the robot. Subsequently, a cognitive walkthrough with HRI experts was performed to validate the results from the experiment. The results from both studies show that for itinerary requests verbal feedback is most prominent but other feedback modalities may support the conversation by providing reassurance or positive emotions.

In this paper, the impact of facial expressions on HRI is explored. To determine their influence on empathy of a human towards a robot and perceived subjective performance, an experimental setup is created, in which participants engage in a dialog with the robot head EDDIE. The web-based gaming application “Akinator” serves as a backbone for the dialog structure. In this game, the robot tries to guess a thought-of person chosen by the human by asking various questions about the person. In our experimental evaluation, the robot reacts in various ways to the human's facial expressions, either ignoring them, mirroring them, or displaying its own facial expression based on a psychological model for social awareness. In which way this robot behavior influences human perception of the interaction is investigated by a questionnaire. Our results support the hypothesis that the robot behavior during interaction heavily influences the extent of empathy by a human towards a robot and perceived subjective task-performance, with the adaptive modes clearly leading compared to the non-adaptive mode.

Every day human communication relies on a large number of different communication mechanisms like spoken language, facial expressions, body pose and gestures, allowing humans to pass large amounts of information in short time. In contrast, traditional human-machine communication is often unintuitive and requires specifically trained personal. In this paper, we present a real-time capable framework that recognizes traditional visual human communication signals in order to establish a more intuitive human-machine interaction. Humans rely on the interaction partner’s face for identification, which helps them to adapt to the interaction partner and utilize context information. Head gestures (head nodding and head shaking) are a convenient way to show agreement or disagreement. Facial expressions give evidence about the interaction partners’ emotional state and hand gestures are a fast way of passing simple commands. The recognition of all interaction queues is performed in parallel, enabled by a shared memory implementation.

We introduce a facial mimicry system, which combines facial expression analysis and synthesis on a robot, utilizing the facial action coding system. The activation of action units on a user's face is automatically extracted from a video stream and mapped to the robot, thus mirroring the facial expression. As a novel approach, a user study quantifies the congruence of the initial human facial expression with the robotic facial expression. The evaluation shows that the robotic facial expression is perceived to be close to the human facial expression, from which it is derived. This is a fundamental aspect for a mimicry system, providing a basis for future research on empathy and emotional closed loop control.

This video presents the Autonomous City Explorer (ACE) project. Its goal was to create a robot capable of navigating unknown urban environments without the use of GPS data or prior map knowledge. The robot had to find its way solely by interacting with pedestrians and building a topological representation of its surroundings. This video outlines the necessary ingredients for successful low-level navigation on sidewalks, information retrieval from pedestrians as well as the construction of a semantic representation of an urban environment. A system architecture for outdoor localization, traversability assessment, path planning, behavior selection and topological abstraction in urban environments is presented.

In the autonomous city explorer (ACE) project a mobile robot is developed, which is capable of finding its way to a given destination in an unknown urban environment. An exemplary mission is to find the way from our institute to the Marienplatz, a public place in the center of Munich, without any prior knowledge or GPS information. Inspired by the behavior of humans in unknown environments, ACE must find its way by asking pedestrians. The route is about 1.5 kilometers far and includes heavily traveled roads and crowded public places. In order to navigate safely in an unknown urban environment, some challenges arise for the vision system. Robust human detection, tracking and the estimation of human body poses is essential for natural interaction with pedestrians. Furthermore, the robot needs to be able to detect sidewalk and crossroads. A visual odometry system is used to support the conventional navigation. Outdoor experiments were conducted twice successfully. After about 5 hours and interacting with 25 and 38 persons respectively, ACE arrived the Marienplatz. This paper describes both, an architecture of the vision system used for ACE and the algorithms used to deal with the described challenges.

Emotional expressions are considered to be important for robotic and virtual agents to improve nonverbal communication in human-machine-interaction. In this paper we focus on a subset of emotional expressions, namely the smile and it's variations. The proposed concept for generating artificial smile sequences is based on the system-theoretic psychological model of smiling, which is based on the Zurich Model of Social Motivation. The model and seven different types of smiles are introduced and it is presented how to integrate this model in a virtual agent. The evaluation of the generated facial expressions shows that the seven types of smiles are distinguishable from each other and can be classified according to given categories.

Inspired by the expectation-based perception of humans, a surprise-driven active vision system is proposed. This vision system not only considers spatial saliency of objects in the environment, but also investigates temporal novelty in the neighborhood. Surprise is defined as the difference of the saliency probability distributions of two consecutive input images, which is measured using Kullback-Leibler divergence. The high-speed gaze shift capability of the camera platform and the parallel computation with the aid of GPUs enable a real-time tracking of the surprising event.

This paper focuses on the development of EDDIE, a flexible low-cost emotion-display with 23 degrees of freedom. Actuators are assigned to particular action units of the facial action coding system (FACS). Emotion states represented by the circumplex model of affect are mapped to individual action units. Thereby, continuous, dynamic, and realistic emotion state transitions are achieved. EDDIE is largely developed and manufactured in a rapid-prototyping process. Miniature off-the-shelf mechatronics components are used providing high functionality at low-cost. Evaluations conducted in a user-study show that emotions can be recognized very well. Further experiments show that additional features adapted from animals have significant but small influence on the display of the human emotion 'disgust'

EDDIE, a novel mechatronical emotion-display designed for dynamic non-verbal human-robot interaction is presented. A special feature are dynamic and realistic emotional state transitions. Therefore, the emotional state-space based on the circumplex model of affect is directly mapped to joint space. The display is largely developed and manufactured in a rapid-prototyping process. Only miniature off-the-shelf mechatronic components are used providing high functionality at low cost.

This paper focuses on the development of EDDIE, a flexible low-cost emotion-display with 23 degrees of freedom. Actuators are assigned to particular action units of the facial action coding system (FACS). Emotion states represented by the circumplex model of affect are mapped to individual action units. Thereby, continuous, dynamic, and realistic emotion state transitions are achieved. EDDIE is largely developed and manufactured in a rapid-prototyping process. Miniature off-the-shelf mechatronics are used providing high functionality while extremely low-cost. Evaluations are conducted based on a user-study