Robert Babuška

Jonáš Kulhánek, Erik Derner, Torsten Sattler et al.

Novel view synthesis is a long-standing problem. In this work, we consider a variant of the problem where we are given only a few context views sparsely covering a scene or an object. The goal is to predict novel viewpoints in the scene, which requires learning priors. The current state of the art is based on Neural Radiance Field (NeRF), and while achieving impressive results, the methods suffer from long training times as they require evaluating millions of 3D point samples via a neural network for each image. We propose a 2D-only method that maps multiple context views and a query pose to a new image in a single pass of a neural network. Our model uses a two-stage architecture consisting of a codebook and a transformer model. The codebook is used to embed individual images into a smaller latent space, and the transformer solves the view synthesis task in this more compact space. To train our model efficiently, we introduce a novel branching attention mechanism that allows us to use the same model not only for neural rendering but also for camera pose estimation. Experimental results on real-world scenes show that our approach is competitive compared to NeRF-based methods while not reasoning explicitly in 3D, and it is faster to train.

Max Lodel, Bruno Brito, Álvaro Serra-Gómez et al.

Search missions require motion planning and navigation methods for information gathering that continuously replan based on new observations of the robot's surroundings. Current methods for information gathering, such as Monte Carlo Tree Search, are capable of reasoning over long horizons, but they are computationally expensive. An alternative for fast online execution is to train, offline, an information gathering policy, which indirectly reasons about the information value of new observations. However, these policies lack safety guarantees and do not account for the robot dynamics. To overcome these limitations we train an information-aware policy via deep reinforcement learning, that guides a receding-horizon trajectory optimization planner. In particular, the policy continuously recommends a reference viewpoint to the local planner, such that the resulting dynamically feasible and collision-free trajectories lead to observations that maximize the information gain and reduce the uncertainty about the environment. In simulation tests in previously unseen environments, our method consistently outperforms greedy next-best-view policies and achieves competitive performance compared to Monte Carlo Tree Search, in terms of information gains and coverage time, with a reduction in execution time by three orders of magnitude.

Andrea Simonetto, Tamas Keviczky, Robert Babuska

We consider the problem of maximizing the algebraic connectivity of the communication graph in a network of mobile robots by moving them into appropriate positions. We define the Laplacian of the graph as dependent on the pairwise distance between the robots and we approximate the problem as a sequence of Semi-Definite Programs (SDP). We propose a distributed solution consisting of local SDP's which use information only from nearby neighboring robots. We show that the resulting distributed optimization framework leads to feasible subproblems and through its repeated execution, the algebraic connectivity increases monotonically. Moreover, we describe how to adjust the communication load of the robots based on locally computable measures. Numerical simulations show the performance of the algorithm with respect to the centralized solution.

Jiri Sedlar, Karla Stepanova, Radoslav Skoviera et al.

This paper introduces a dataset for training and evaluating methods for 6D pose estimation of hand-held tools in task demonstrations captured by a standard RGB camera. Despite the significant progress of 6D pose estimation methods, their performance is usually limited for heavily occluded objects, which is a common case in imitation learning, where the object is typically partially occluded by the manipulating hand. Currently, there is a lack of datasets that would enable the development of robust 6D pose estimation methods for these conditions. To overcome this problem, we collect a new dataset (Imitrob) aimed at 6D pose estimation in imitation learning and other applications where a human holds a tool and performs a task. The dataset contains image sequences of nine different tools and twelve manipulation tasks with two camera viewpoints, four human subjects, and left/right hand. Each image is accompanied by an accurate ground truth measurement of the 6D object pose obtained by the HTC Vive motion tracking device. The use of the dataset is demonstrated by training and evaluating a recent 6D object pose estimation method (DOPE) in various setups.

Bas van der Heijden, Jelle Luijkx, Laura Ferranti et al.

Sim2real, that is, the transfer of learned control policies from simulation to real world, is an area of growing interest in robotics due to its potential to efficiently handle complex tasks. The sim2real approach faces challenges due to mismatches between simulation and reality. These discrepancies arise from inaccuracies in modeling physical phenomena and asynchronous control, among other factors. To this end, we introduce EAGERx, a framework with a unified software pipeline for both real and simulated robot learning. It can support various simulators and aids in integrating state, action and time-scale abstractions to facilitate learning. EAGERx's integrated delay simulation, domain randomization features, and proposed synchronization algorithm contribute to narrowing the sim2real gap. We demonstrate (in the context of robot learning and beyond) the efficacy of EAGERx in accommodating diverse robotic systems and maintaining consistent simulation behavior. EAGERx is open source and its code is available at https://eagerx.readthedocs.io.

Martin Vastl, Jonáš Kulhánek, Jiří Kubalík et al.

Many real-world problems can be naturally described by mathematical formulas. The task of finding formulas from a set of observed inputs and outputs is called symbolic regression. Recently, neural networks have been applied to symbolic regression, among which the transformer-based ones seem to be the most promising. After training the transformer on a large number of formulas (in the order of days), the actual inference, i.e., finding a formula for new, unseen data, is very fast (in the order of seconds). This is considerably faster than state-of-the-art evolutionary methods. The main drawback of transformers is that they generate formulas without numerical constants, which have to be optimized separately, so yielding suboptimal results. We propose a transformer-based approach called SymFormer, which predicts the formula by outputting the individual symbols and the corresponding constants simultaneously. This leads to better performance in terms of fitting the available data. In addition, the constants provided by SymFormer serve as a good starting point for subsequent tuning via gradient descent to further improve the performance. We show on a set of benchmarks that SymFormer outperforms two state-of-the-art methods while having faster inference.

Zhaoting Li, Rodrigo Pérez-Dattari, Robert Babuska et al.

Behavior cloning (BC) optimizes policies by treating human demonstrations as pointwise action labels. While effective with accurate action labels, this formulation is brittle in practice: when human-provided actions are imperfect, treating each label as an exact target can steer the policy away from the underlying desired behavior, particularly when expressive models are used (e.g., energy-based models). As a result, we propose a human-in-the-loop alternative that replaces pointwise supervision with set-valued action targets. We introduce Contrastive policy Learning from Interactive Corrections (CLIC). CLIC leverages human corrections to construct and refine sets of desired actions, and optimizes a policy to place probability mass over these sets rather than over a single action target. This formulation naturally accommodates both absolute and relative corrections and can represent complex multi-modal behaviors. Extensive simulation and real-robot experiments show that the proposed approach leads to effective policy learning across diverse settings: CLIC remains competitive with the state of the art under accurate data while being substantially more robust under noisy, relative, and partial feedback. Our implementation is publicly available at https://clic-webpage.github.io/.

Erik Derner, Kristina Batistič, Jan Zahálka et al.

As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary. The potential for exploitation by malicious actors, ranging from disinformation to data breaches and reputation damage, is substantial. This paper addresses a gap in current research by specifically focusing on security risks posed by LLMs within the prompt-based interaction scheme, which extends beyond the widely covered ethical and societal implications. Our work proposes a taxonomy of security risks along the user-model communication pipeline and categorizes the attacks by target and attack type alongside the commonly used confidentiality, integrity, and availability (CIA) triad. The taxonomy is reinforced with specific attack examples to showcase the real-world impact of these risks. Through this taxonomy, we aim to inform the development of robust and secure LLM applications, enhancing their safety and trustworthiness.

Jiří Kubalík, Erik Derner, Robert Babuška

Many real-world systems can be described by mathematical models that are human-comprehensible, easy to analyze and help explain the system's behavior. Symbolic regression is a method that can automatically generate such models from data. Historically, symbolic regression has been predominantly realized by genetic programming, a method that evolves populations of candidate solutions that are subsequently modified by genetic operators crossover and mutation. However, this approach suffers from several deficiencies: it does not scale well with the number of variables and samples in the training data - models tend to grow in size and complexity without an adequate accuracy gain, and it is hard to fine-tune the model coefficients using just genetic operators. Recently, neural networks have been applied to learn the whole analytic model, i.e., its structure and the coefficients, using gradient-based optimization algorithms. This paper proposes a novel neural network-based symbolic regression method that constructs physically plausible models based on even very small training data sets and prior knowledge about the system. The method employs an adaptive weighting scheme to effectively deal with multiple loss function terms and an epoch-wise learning process to reduce the chance of getting stuck in poor local optima. Furthermore, we propose a parameter-free method for choosing the model with the best interpolation and extrapolation performance out of all the models generated throughout the whole learning process. We experimentally evaluate the approach on four test systems: the TurtleBot 2 mobile robot, the magnetic manipulation system, the equivalent resistance of two resistors in parallel, and the longitudinal force of the anti-lock braking system. The results clearly show the potential of the method to find parsimonious models that comply with the prior knowledge provided.

Miroslav David, Karla Stepanova, Robert Babuska

Robotic surface-interaction tasks, such as spray painting or welding, require both accurate geometric planning and precise motion execution. While modern motion planners generate valid geometric paths, they often lack the expert motor patterns observed in human operators. Conversely, learning from demonstration often tightly couples task execution to the specific training geometry, limiting transferability. We propose a modular framework that decouples geometric motion planning from execution-level expertise. Expert behavior is represented as a vocabulary of interpretable, atomic motor rules, such as velocity scaling and orientation offsets, that systematically modify a geometrically planned reference path. We train a multimodal neural network to infer rule parameters jointly from kinematic trajectory data and CAD model geometry. We evaluate our approach through dynamic simulation on L-shaped and window-shaped objects, demonstrating on simulated data that the model successfully extracts velocity and orientation rules across both topologies.

Luuk van den Bent, Tomás Coleman, Robert Babuška

Currently, truss tomato weighing and packaging require significant manual work. The main obstacle to automation lies in the difficulty of developing a reliable robotic grasping system for already harvested trusses. We propose a method to grasp trusses that are stacked in a crate with considerable clutter, which is how they are commonly stored and transported after harvest. The method consists of a deep learning-based vision system to first identify the individual trusses in the crate and then determine a suitable grasping location on the stem. To this end, we have introduced a grasp pose ranking algorithm with online learning capabilities. After selecting the most promising grasp pose, the robot executes a pinch grasp without needing touch sensors or geometric models. Lab experiments with a robotic manipulator equipped with an eye-in-hand RGB-D camera showed a 100% clearance rate when tasked to pick all trusses from a pile. 93% of the trusses were successfully grasped on the first try, while the remaining 7% required more attempts.

Rodrigo Pérez-Dattari, Zhaoting Li, Robert Babuška et al.

Planning methods struggle with computational intractability in solving task-level problems in large-scale environments. This work explores leveraging the commonsense knowledge encoded in LLMs to empower planning techniques to deal with these complex scenarios. We achieve this by efficiently using LLMs to prune irrelevant components from the planning problem's state space, substantially simplifying its complexity. We demonstrate the efficacy of this system through extensive experiments within a household simulation environment, alongside real-world validation using a 7-DoF manipulator (video https://youtu.be/6ro2UOtOQS4).

Jiří Kubalík, Robert Babuška

Symbolic regression is a technique that can automatically derive analytic models from data. Traditionally, symbolic regression has been implemented primarily through genetic programming that evolves populations of candidate solutions sampled by genetic operators, crossover and mutation. More recently, neural networks have been employed to learn the entire analytical model, i.e., its structure and coefficients, using regularized gradient-based optimization. Although this approach tunes the model's coefficients better, it is prone to premature convergence to suboptimal model structures. Here, we propose a neuro-evolutionary symbolic regression method that combines the strengths of evolutionary-based search for optimal neural network (NN) topologies with gradient-based tuning of the network's parameters. Due to the inherent high computational demand of evolutionary algorithms, it is not feasible to learn the parameters of every candidate NN topology to full convergence. Thus, our method employs a memory-based strategy and population perturbations to enhance exploitation and reduce the risk of being trapped in suboptimal NNs. In this way, each NN topology can be trained using only a short sequence of backpropagation iterations. The proposed method was experimentally evaluated on three real-world test problems and has been shown to outperform other NN-based approaches regarding the quality of the models obtained.

Jacob E. Kooi, Robert Babuška

Landing a quadrotor on an inclined surface is a challenging maneuver. The final state of any inclined landing trajectory is not an equilibrium, which precludes the use of most conventional control methods. We propose a deep reinforcement learning approach to design an autonomous landing controller for inclined surfaces. Using the proximal policy optimization (PPO) algorithm with sparse rewards and a tailored curriculum learning approach, an inclined landing policy can be trained in simulation in less than 90 minutes on a standard laptop. The policy then directly runs on a real Crazyflie 2.1 quadrotor and successfully performs real inclined landings in a flying arena. A single policy evaluation takes approximately 2.5\,ms, which makes it suitable for a future embedded implementation on the quadrotor.

Taeke de Haan, Padmaja Kulkarni, Robert Babuska

We propose a geometry-based grasping method for vine tomatoes. It relies on a computer-vision pipeline to identify the required geometric features of the tomatoes and of the truss stem. The grasping method then uses a geometric model of the robotic hand and the truss to determine a suitable grasping location on the stem. This approach allows for grasping tomato trusses without requiring delicate contact sensors or complex mechanistic models and under minimal risk of damaging the tomatoes. Lab experiments were conducted to validate the proposed methods, using an RGB-D camera and a low-cost robotic manipulator. The success rate was 83% to 92%, depending on the type of truss.

Osama Mazhar, Robert Babuska, Jens Kober

Deep neural networks designed for vision tasks are often prone to failure when they encounter environmental conditions not covered by the training data. Single-modal strategies are insufficient when the sensor fails to acquire information due to malfunction or its design limitations. Multi-sensor configurations are known to provide redundancy, increase reliability, and are crucial in achieving robustness against asymmetric sensor failures. To address the issue of changing lighting conditions and asymmetric sensor degradation in object detection, we develop a multi-modal 2D object detector, and propose deterministic and stochastic sensor-aware feature fusion strategies. The proposed fusion mechanisms are driven by the estimated sensor measurement reliability values/weights. Reliable object detection in harsh lighting conditions is essential for applications such as self-driving vehicles and human-robot interaction. We also propose a new "r-blended" hybrid depth modality for RGB-D sensors. Through extensive experimentation, we show that the proposed strategies outperform the existing state-of-the-art methods on the FLIR-Thermal dataset, and obtain promising results on the SUNRGB-D dataset. We additionally record a new RGB-Infra indoor dataset, namely L515-Indoors, and demonstrate that the proposed object detection methodologies are highly effective for a variety of lighting conditions.

Bas van der Heijden, Laura Ferranti, Jens Kober et al.

This paper presents DeepKoCo, a novel model-based agent that learns a latent Koopman representation from images. This representation allows DeepKoCo to plan efficiently using linear control methods, such as linear model predictive control. Compared to traditional agents, DeepKoCo learns task-relevant dynamics, thanks to the use of a tailored lossy autoencoder network that allows DeepKoCo to learn latent dynamics that reconstruct and predict only observed costs, rather than all observed dynamics. As our results show, DeepKoCo achieves similar final performance as traditional model-free methods on complex control tasks while being considerably more robust to distractor dynamics, making the proposed agent more amenable for real-life applications.

Jonáš Kulhánek, Erik Derner, Robert Babuška

Visual navigation is essential for many applications in robotics, from manipulation, through mobile robotics to automated driving. Deep reinforcement learning (DRL) provides an elegant map-free approach integrating image processing, localization, and planning in one module, which can be trained and therefore optimized for a given environment. However, to date, DRL-based visual navigation was validated exclusively in simulation, where the simulator provides information that is not available in the real world, e.g., the robot's position or image segmentation masks. This precludes the use of the learned policy on a real robot. Therefore, we propose a novel approach that enables a direct deployment of the trained policy on real robots. We have designed visual auxiliary tasks, a tailored reward scheme, and a new powerful simulator to facilitate domain randomization. The policy is fine-tuned on images collected from real-world environments. We have evaluated the method on a mobile robot in a real office environment. The training took ~30 hours on a single GPU. In 30 navigation experiments, the robot reached a 0.3-meter neighborhood of the goal in more than 86.7% of cases. This result makes the proposed method directly applicable to tasks like mobile manipulation.

Jiří Kubalík, Erik Derner, Jan Žegklitz et al.

Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value function and policy mappings. Commonly used numerical approximators, such as neural networks or basis function expansions, have two main drawbacks: they are black-box models offering little insight into the mappings learned, and they require extensive trial and error tuning of their hyper-parameters. In this paper, we propose a new approach to constructing smooth value functions in the form of analytic expressions by using symbolic regression. We introduce three off-line methods for finding value functions based on a state-transition model: symbolic value iteration, symbolic policy iteration, and a direct solution of the Bellman equation. The methods are illustrated on four nonlinear control problems: velocity control under friction, one-link and two-link pendulum swing-up, and magnetic manipulation. The results show that the value functions yield well-performing policies and are compact, mathematically tractable, and easy to plug into other algorithms. This makes them potentially suitable for further analysis of the closed-loop system. A comparison with an alternative approach using neural networks shows that our method outperforms the neural network-based one.

Radoslav Skoviera, Karla Stepanova, Michael Tesar et al.

In this paper, we consider the problem of learning object manipulation tasks from human demonstration using RGB or RGB-D cameras. We highlight the key challenges in capturing sufficiently good data with no tracking devices - starting from sensor selection and accurate 6DoF pose estimation to natural language processing. In particular, we focus on two showcases: gluing task with a glue gun and simple block-stacking with variable blocks. Furthermore, we discuss how a linguistic description of the task could help to improve the accuracy of task description. We also present the whole architecture of our transfer of the imitated task to the simulated and real robot environment.

Frederik Ruelens, Bert Claessens, Salman Quaiyum et al.

Electric water heaters have the ability to store energy in their water buffer without impacting the comfort of the end user. This feature makes them a prime candidate for residential demand response. However, the stochastic and nonlinear dynamics of electric water heaters, makes it challenging to harness their flexibility. Driven by this challenge, this paper formulates the underlying sequential decision-making problem as a Markov decision process and uses techniques from reinforcement learning. Specifically, we apply an auto-encoder network to find a compact feature representation of the sensor measurements, which helps to mitigate the curse of dimensionality. A wellknown batch reinforcement learning technique, fitted Q-iteration, is used to find a control policy, given this feature representation. In a simulation-based experiment using an electric water heater with 50 temperature sensors, the proposed method was able to achieve good policies much faster than when using the full state information. In a lab experiment, we apply fitted Q-iteration to an electric water heater with eight temperature sensors. Further reducing the state vector did not improve the results of fitted Q-iteration. The results of the lab experiment, spanning 40 days, indicate that compared to a thermostat controller, the presented approach was able to reduce the total cost of energy consumption of the electric water heater by 15%.

Frederik Ruelens, Bert Claessens, Stijn Vandael et al.

Driven by recent advances in batch Reinforcement Learning (RL), this paper contributes to the application of batch RL to demand response. In contrast to conventional model-based approaches, batch RL techniques do not require a system identification step, which makes them more suitable for a large-scale implementation. This paper extends fitted Q-iteration, a standard batch RL technique, to the situation where a forecast of the exogenous data is provided. In general, batch RL techniques do not rely on expert knowledge on the system dynamics or the solution. However, if some expert knowledge is provided, it can be incorporated by using our novel policy adjustment method. Finally, we tackle the challenge of finding an open-loop schedule required to participate in the day-ahead market. We propose a model-free Monte-Carlo estimator method that uses a metric to construct artificial trajectories and we illustrate this method by finding the day-ahead schedule of a heat-pump thermostat. Our experiments show that batch RL techniques provide a valuable alternative to model-based controllers and that they can be used to construct both closed-loop and open-loop policies.

Sofie Haesaert, Robert Babuska, Alessandro Abate

This article deals with stochastic processes endowed with the Markov (memoryless) property and evolving over general (uncountable) state spaces. The models further depend on a non-deterministic quantity in the form of a control input, which can be selected to affect the probabilistic dynamics. We address the computation of maximal reach-avoid specifications, together with the synthesis of the corresponding optimal controllers. The reach-avoid specification deals with assessing the likelihood that any finite-horizon trajectory of the model enters a given goal set, while avoiding a given set of undesired states. This article newly provides an approximate computational scheme for the reach-avoid specification based on the Fitted Value Iteration algorithm, which hinges on random sample extractions, and gives a-priori computable formal probabilistic bounds on the error made by the approximation algorithm: as such, the output of the numerical scheme is quantitatively assessed and thus meaningful for safety-critical applications. Furthermore, we provide tighter probabilistic error bounds that are sample-based. The overall computational scheme is put in relationship with alternative approximation algorithms in the literature, and finally its performance is practically assessed over a benchmark case study.