Search

The RoboCup Humanoid League holds annual soccer robot world championships towards the long-term objective of winning against the FIFA world champions by 2050. The participating teams continuously improve their systems. This paper presents the upgrades to our humanoid soccer system, leading our team NimbRo to win the Soccer Tournament in the Humanoid AdultSize League at RoboCup 2023 in Bordeaux, France. The mentioned upgrades consist of: an updated model architecture for visual perception, extended fused angles feedback mechanisms and an additional COM-ZMP controller for walking robustness, and parametric in-walk kicks through waveforms., Comment: Accepted for: RoboCup 2023: Robot World Cup XXVI, LNCS, Springer, to appear 2024 more...

In this paper, we present Toloka Visual Question Answering, a new crowdsourced dataset allowing comparing performance of machine learning systems against human level of expertise in the grounding visual question answering task. In this task, given an image and a textual question, one has to draw the bounding box around the object correctly responding to that question. Every image-question pair contains the response, with only one correct response per image. Our dataset contains 45,199 pairs of images and questions in English, provided with ground truth bounding boxes, split into train and two test subsets. Besides describing the dataset and releasing it under a CC BY license, we conducted a series of experiments on open source zero-shot baseline models and organized a multi-phase competition at WSDM Cup that attracted 48 participants worldwide. However, by the time of paper submission, no machine learning model outperformed the non-expert crowdsourcing baseline according to the intersection over union evaluation score., Comment: 16 pages; see https://toloka.ai/challenges/wsdm2023/ for more details more...

Many objects, such as tools and household items, can be used only if grasped in a very specific way - grasped functionally. Often, a direct functional grasp is not possible, though. We propose a method for learning a dexterous pre-grasp manipulation policy to achieve human-like functional grasps using deep reinforcement learning. We introduce a dense multi-component reward function that enables learning a single policy, capable of dexterous pre-grasp manipulation of novel instances of several known object categories with an anthropomorphic hand. The policy is learned purely by means of reinforcement learning from scratch, without any expert demonstrations. It implicitly learns to reposition and reorient objects of complex shapes to achieve given functional grasps. In addition, we explore two different ways to represent a desired grasp: explicit and more abstract, constraint-based. We show that our method consistently learns to successfully manipulate and achieve desired grasps on previously unseen object instances of known categories using both grasp representations. Training is completed on a single GPU in under three hours., Comment: To appear: IEEE Transactions on Automation Science and Engineering (T-ASE), 2025 more...

Beating the human world champions by 2050 is an ambitious goal of the Humanoid League that provides a strong incentive for RoboCup teams to further improve and develop their systems. In this paper, we present upgrades of our system which enabled our team NimbRo to win the Soccer Tournament, the Drop-in Games, and the Technical Challenges in the Humanoid AdultSize League of RoboCup 2022. Strong performance in these competitions resulted in the Best Humanoid award in the Humanoid League. The mentioned upgrades include: hardware upgrade of the vision module, balanced walking with Capture Steps, and the introduction of phase-based in-walk kicks. more...

Recent progress in generative models, especially in text-guided diffusion models, has enabled the production of aesthetically-pleasing imagery resembling the works of professional human artists. However, one has to carefully compose the textual description, called the prompt, and augment it with a set of clarifying keywords. Since aesthetics are challenging to evaluate computationally, human feedback is needed to determine the optimal prompt formulation and keyword combination. In this paper, we present a human-in-the-loop approach to learning the most useful combination of prompt keywords using a genetic algorithm. We also show how such an approach can improve the aesthetic appeal of images depicting the same descriptions., Comment: 13 pages (6 main pages), 7 figures, 4 tables, accepted at SIGIR '23 Short Paper Track more...

Flexible-joint manipulators are governed by complex nonlinear dynamics, defining a challenging control problem. In this work, we propose an approach to learn an outer-loop joint trajectory tracking controller with deep reinforcement learning. The controller represented by a stochastic policy is learned in under two hours directly on the real robot. This is achieved through bounded reference correction actions and use of a model-free off-policy learning method. In addition, an informed policy initialization is proposed, where the agent is pre-trained in a learned simulation. We test our approach on the 7 DOF manipulator of a Baxter robot. We demonstrate that the proposed method is capable of consistent learning across multiple runs when applied directly on the real robot. Our method yields a policy which significantly improves the trajectory tracking accuracy in comparison to the vendor-provided controller, generalizing to an unseen payload., Comment: Accepted final version. IEEE International Conference on Robotics and Automation (ICRA), Philadelphia, USA, May 2022 more...

The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020 posed diverse challenges for unmanned aerial vehicles (UAVs). We present our four tailored UAVs, specifically developed for individual aerial-robot tasks of MBZIRC, including custom hardware- and software components. In Challenge 1, a target UAV is pursued using a high-efficiency, onboard object detection pipeline to capture a ball from the target UAV. A second UAV uses a similar detection method to find and pop balloons scattered throughout the arena. For Challenge 2, we demonstrate a larger UAV capable of autonomous aerial manipulation: Bricks are found and tracked from camera images. Subsequently, they are approached, picked, transported, and placed on a wall. Finally, in Challenge 3, our UAV autonomously finds fires using LiDAR and thermal cameras. It extinguishes the fires with an onboard fire extinguisher. While every robot features task-specific subsystems, all UAVs rely on a standard software stack developed for this particular and future competitions. We present our mostly open-source software solutions, including tools for system configuration, monitoring, robust wireless communication, high-level control, and agile trajectory generation. For solving the MBZIRC 2020 tasks, we advanced the state of the art in multiple research areas like machine vision and trajectory generation. We present our scientific contributions that constitute the foundation for our algorithms and systems and analyze the results from the MBZIRC competition 2020 in Abu Dhabi, where our systems reached second place in the Grand Challenge. Furthermore, we discuss lessons learned from our participation in this complex robotic challenge., Comment: Accepted for Field Robotics, to appear 2022 more...

Flexible-joint manipulators are frequently used for increased safety during human-robot collaboration and shared workspace tasks. However, joint flexibility significantly reduces the accuracy of motion, especially at high velocities and with inexpensive actuators. In this paper, we present a learning-based approach to identify the unknown dynamics of a flexible-joint manipulator and improve the trajectory tracking at high velocities. We propose a two-stage model which is composed of a one-step forward dynamics future predictor and an inverse dynamics estimator. The second part is based on linear time-invariant dynamical operators to approximate the feed-forward joint position and velocity commands. We train the model end-to-end on real-world data and evaluate it on the Baxter robot. Our experiments indicate that augmenting the input with one-step future state prediction improves the performance, compared to the same model without prediction. We compare joint position, joint velocity and end-effector position tracking accuracy against the classical baseline controller and several simpler models. more...

Today, comprehensive evaluation of large-scale machine learning models is possible thanks to the open datasets produced using crowdsourcing, such as SQuAD, MS COCO, ImageNet, SuperGLUE, etc. These datasets capture objective responses, assuming the single correct answer, which does not allow to capture the subjective human perception. In turn, pairwise comparison tasks, in which one has to choose between only two options, allow taking peoples' preferences into account for very challenging artificial intelligence tasks, such as information retrieval and recommender system evaluation. Unfortunately, the available datasets are either small or proprietary, slowing down progress in gathering better feedback from human users. In this paper, we present IMDB-WIKI-SbS, a new large-scale dataset for evaluating pairwise comparisons. It contains 9,150 images appearing in 250,249 pairs annotated on a crowdsourcing platform. Our dataset has balanced distributions of age and gender using the well-known IMDB-WIKI dataset as ground truth. We describe how our dataset is built and then compare several baseline methods, indicating its suitability for model evaluation., Comment: Accepted to NeurIPS Data-Centric AI Workshop more...

This paper presents Crowd-Kit, a general-purpose computational quality control toolkit for crowdsourcing. Crowd-Kit provides efficient and convenient implementations of popular quality control algorithms in Python, including methods for truth inference, deep learning from crowds, and data quality estimation. Our toolkit supports multiple modalities of answers and provides dataset loaders and example notebooks for faster prototyping. We extensively evaluated our toolkit on several datasets of different natures, enabling benchmarking computational quality control methods in a uniform, systematic, and reproducible way using the same codebase. We release our code and data under the Apache License 2.0 at https://github.com/Toloka/crowd-kit., Comment: published at JOSS more...

Domain-specific data is the crux of the successful transfer of machine learning systems from benchmarks to real life. In simple problems such as image classification, crowdsourcing has become one of the standard tools for cheap and time-efficient data collection: thanks in large part to advances in research on aggregation methods. However, the applicability of crowdsourcing to more complex tasks (e.g., speech recognition) remains limited due to the lack of principled aggregation methods for these modalities. The main obstacle towards designing aggregation methods for more advanced applications is the absence of training data, and in this work, we focus on bridging this gap in speech recognition. For this, we collect and release CrowdSpeech -- the first publicly available large-scale dataset of crowdsourced audio transcriptions. Evaluation of existing and novel aggregation methods on our data shows room for improvement, suggesting that our work may entail the design of better algorithms. At a higher level, we also contribute to the more general challenge of developing the methodology for reliable data collection via crowdsourcing. In that, we design a principled pipeline for constructing datasets of crowdsourced audio transcriptions in any novel domain. We show its applicability on an under-resourced language by constructing VoxDIY -- a counterpart of CrowdSpeech for the Russian language. We also release the code that allows a full replication of our data collection pipeline and share various insights on best practices of data collection via crowdsourcing. more...

Every day, burning buildings threaten the lives of occupants and first responders trying to save them. Quick action is of essence, but some areas might not be accessible or too dangerous to enter. Robotic systems have become a promising addition to firefighting, but at this stage, they are mostly manually controlled, which is error-prone and requires specially trained personal. We present two systems for autonomous firefighting from air and ground we developed for the Mohamed Bin Zayed International Robotics Challenge (MBZIRC) 2020. The systems use LiDAR for reliable localization within narrow, potentially GNSS-restricted environments while maneuvering close to obstacles. Measurements from LiDAR and thermal cameras are fused to track fires, while relative navigation ensures successful extinguishing. We analyze and discuss our successful participation during the MBZIRC 2020, present further experiments, and provide insights into our lessons learned from the competition., Comment: 8 pages, accepted for ICUAS 2021 more...

Processing information on 3D objects requires methods stable to rigid-body transformations, in particular rotations, of the input data. In image processing tasks, convolutional neural networks achieve this property using rotation-equivariant operations. However, contrary to images, graphs generally have irregular topology. This makes it challenging to define a rotation-equivariant convolution operation on these structures. In this work, we propose Spherical Graph Convolutional Network (S-GCN) that processes 3D models of proteins represented as molecular graphs. In a protein molecule, individual amino acids have common topological elements. This allows us to unambiguously associate each amino acid with a local coordinate system and construct rotation-equivariant spherical filters that operate on angular information between graph nodes. Within the framework of the protein model quality assessment problem, we demonstrate that the proposed spherical convolution method significantly improves the quality of model assessment compared to the standard message-passing approach. It is also comparable to state-of-the-art methods, as we demonstrate on Critical Assessment of Structure Prediction (CASP) benchmarks. The proposed technique operates only on geometric features of protein 3D models. This makes it universal and applicable to any other geometric-learning task where the graph structure allows constructing local coordinate systems. more...

For several years, high development and production costs of humanoid robots restricted researchers interested in working in the field. To overcome this problem, several research groups have opted to work with simulated or smaller robots, whose acquisition costs are significantly lower. However, due to scale differences and imperfect simulation replicability, results may not be directly reproducible on real, adult-sized robots. In this paper, we present the NimbRo-OP2X, a capable and affordable adult-sized humanoid platform aiming to significantly lower the entry barrier for humanoid robot research. With a height of 135 cm and weight of only 19 kg, the robot can interact in an unmodified, human environment without special safety equipment. Modularity in hardware and software allow this platform enough flexibility to operate in different scenarios and applications with minimal effort. The robot is equipped with an on-board computer with GPU, which enables the implementation of state-of-the-art approaches for object detection and human perception demanded by areas such as manipulation and human-robot interaction. Finally, the capabilities of the NimbRo-OP2X, especially in terms of locomotion stability and visual perception, are evaluated. This includes the performance at RoboCup 2018, where NimbRo-OP2X won all possible awards in the AdultSize class. more...

A computer simulation of dynamics of an optical discharge produced in the volume of a transparent dielectric (fused silica) by a focused femtosecond laser pulse was carried out taking into account the possibility of developing small-scale ionization-field instability. The presence of small foreign inclusions in the fused silica was taken into account with the model of a nanodispersed heterogeneous medium by using Maxwell Garnett formulas. The results of the calculations made it possible to reveal the previously unknown physical mechanism that determines the periodicity of the ordered plasma-field structure that is formed in each single breakdown pulse and is the root cause of the ordered volume nanograting formation in dielectric material exposed to a series of repeated pulse. Two main points are decisive in this mechanism: (i) the formation of a thin overcritical plasma layer at the breakdown wave front counter-propagated to the incident laser pulse and (ii) the excitation of the "internal surface plasmon" at this front, resulting in a rapid amplification of the corresponding spatial harmonic of random seed perturbations in the plasma and formation of a contrast structure with a period equal to the wavelength of the surface plasmon (0.7 of the wavelength in dielectric). more...

Individual and team capabilities are challenged every year by rule changes and the increasing performance of the soccer teams at RoboCup Humanoid League. For RoboCup 2019 in the AdultSize class, the number of players (2 vs. 2 games) and the field dimensions were increased, which demanded for team coordination and robust visual perception and localization modules. In this paper, we present the latest developments that lead team NimbRo to win the soccer tournament, drop-in games, technical challenges and the Best Humanoid Award of the RoboCup Humanoid League 2019 in Sydney. These developments include a deep learning vision system, in-walk kicks, step-based push-recovery, and team play strategies. more...

In human-made scenarios, robots need to be able to fully operate objects in their surroundings, i.e., objects are required to be functionally grasped rather than only picked. This imposes very strict constraints on the object pose such that a direct grasp can be performed. Inspired by the anthropomorphic nature of humanoid robots, we propose an approach that first grasps an object with one hand, obtaining full control over its pose, and performs the functional grasp with the second hand subsequently. Thus, we develop a fully autonomous pipeline for dual-arm functional regrasping of novel familiar objects, i.e., objects never seen before that belong to a known object category, e.g., spray bottles. This process involves semantic segmentation, object pose estimation, non-rigid mesh registration, grasp sampling, handover pose generation and in-hand pose refinement. The latter is used to compensate for the unpredictable object movement during the first grasp. The approach is applied to a human-like upper body. To the best knowledge of the authors, this is the first system that exhibits autonomous bimanual functional regrasping capabilities. We demonstrate that our system yields reliable success rates and can be applied on-line to real-world tasks using only one off-the-shelf RGB-D sensor., Comment: Accepted for IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), Toronto, Canada, 2019 more...

Mobile manipulation robots have high potential to support rescue forces in disaster-response missions. Despite the difficulties imposed by real-world scenarios, robots are promising to perform mission tasks from a safe distance. In the CENTAURO project, we developed a disaster-response system which consists of the highly flexible Centauro robot and suitable control interfaces including an immersive tele-presence suit and support-operator controls on different levels of autonomy. In this article, we give an overview of the final CENTAURO system. In particular, we explain several high-level design decisions and how those were derived from requirements and extensive experience of Kerntechnische Hilfsdienst GmbH, Karlsruhe, Germany (KHG). We focus on components which were recently integrated and report about a systematic evaluation which demonstrated system capabilities and revealed valuable insights., Comment: Accepted for IEEE Robotics and Automation Magazine (RAM), to appear December 2019 more...

Over the past few years, the Humanoid League rules have changed towards more realistic and challenging game environments, which encourage teams to advance their robot soccer performances. In this paper, we present the software and hardware designs that led our team NimbRo to win the competitions in the AdultSize league -- including the soccer tournament, the drop-in games, and the technical challenges at RoboCup 2018 in Montreal. Altogether, this resulted in NimbRo winning the Best Humanoid Award. In particular, we describe our deep-learning approaches for visual perception and our new fully 3D printed robot NimbRo-OP2X., Comment: Accepted for RoboCup 2018: Robot World Cup XXII, LNCS, Springer, to appear 2019 more...

Solving mobile manipulation tasks in inaccessible and dangerous environments is an important application of robots to support humans. Example domains are construction and maintenance of manned and unmanned stations on the moon and other planets. Suitable platforms require flexible and robust hardware, a locomotion approach that allows for navigating a wide variety of terrains, dexterous manipulation capabilities, and respective user interfaces. We present the CENTAURO system which has been designed for these requirements and consists of the Centauro robot and a set of advanced operator interfaces with complementary strength enabling the system to solve a wide range of realistic mobile manipulation tasks. The robot possesses a centaur-like body plan and is driven by torque-controlled compliant actuators. Four articulated legs ending in steerable wheels allow for omnidirectional driving as well as for making steps. An anthropomorphic upper body with two arms ending in five-finger hands enables human-like manipulation. The robot perceives its environment through a suite of multimodal sensors. The resulting platform complexity goes beyond the complexity of most known systems which puts the focus on a suitable operator interface. An operator can control the robot through a telepresence suit, which allows for flexibly solving a large variety of mobile manipulation tasks. Locomotion and manipulation functionalities on different levels of autonomy support the operation. The proposed user interfaces enable solving a wide variety of tasks without previous task-specific training. The integrated system is evaluated in numerous teleoperated experiments that are described along with lessons learned., Comment: Published in: Journal of Field Robotics (JFR), Wiley, 2019 more...

The spatiotemporal evolution of the field and plasma in the optical breakdown induced in the volume of transparent dielectric (fused silica) by the focused fs laser pulse is studied under condition of the so-called plasma-resonance-induced ionization instability that results in the deep small-scale periodic modulation of the breakdown plasma parameters in the direction of the laser polarization. In the framework of the model used, the optical electric field was calculated with allowance for the effects influencing both its long-scale structure (the beam focusing accounted for in the given-ray-tube approximation, phase and group delays, and back reflection) and the small-scale one (quasi-static enhancement in the plasma resonance regions). The plasma density evolution is described by the rate equation taking into account the photoionization, avalanche ionization, and ambipolar diffusion. Based on the fulfilled numerical calculations, we have described the main types of the breakdown wave originating in the focal region and have found the laser pulse intensity range where the instability evolving from very small seed perturbations leads to the formation of the contrast subwavelength periodic structure containing the number of the narrow zones with overcritical plasma density and enhanced energy deposition. The latter allows us to consider this structure as underlying the nanograting formation observed experimentally in the fused silica irradiated by series of repeated fs pulses., Comment: 11 pages, 4 figures more...

Autonomous dual-arm manipulation is an essential skill to deploy robots in unstructured scenarios. However, this is a challenging undertaking, particularly in terms of perception and planning. Unstructured scenarios are full of objects with different shapes and appearances that have to be grasped in a very specific manner so they can be functionally used. In this paper we present an integrated approach to perform dual-arm pick tasks autonomously. Our method consists of semantic segmentation, object pose estimation, deformable model registration, grasp planning and arm trajectory optimization. The entire pipeline can be executed on-board and is suitable for on-line grasping scenarios. For this, our approach makes use of accumulated knowledge expressed as convolutional neural network models and low-dimensional latent shape spaces. For manipulating objects, we propose a stochastic trajectory optimization that includes a kinematic chain closure constraint. Evaluation in simulation and on the real robot corroborates the feasibility and applicability of the proposed methods on a task of picking up unknown watering cans and drills using both arms., Comment: Accepted for IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), Beijing, China, 2018 more...