Dzmitry Tsetserukou

Roohan Ahmed Khan, Yasheerah Yaqoot, Muhammad Ahsan Mustafa et al.

Deep reinforcement learning has shown strong potential for enabling autonomous robots to learn complex navigational tasks. However, its practical use still depends heavily on human designed reward functions and repeated manual fine tuning, which is time consuming and does not guarantee high success in the desired task. This paper presents AgenticRL, agent guided reinforcement learning framework that increases autonomy in reward design, policy refinement, and real world deployment for unmanned aerial vehicles (UAV) navigation tasks. AgenticRL uses a multimodal generative pre-trained tansformer (GPT) agent to interpret task information and visual scene observations, generate task specific reward functions, train policies using Proximal Policy Optimization (PPO) algorithm, and then act as a critic by evaluating the trained policy through diagnosis packets to generate feedback. Based on this feedback, the agent identifies failure modes and refines the reward function in a closed loop self improvement process. To further leverage the multimodal GPT agent during inference, AgenticRL uses real world images and natural language task information to automatically identify the active scenario and select the appropriate trained policy for execution. The framework is evaluated on multiple navigational tasks, including gate traversal, obstacle avoidance, wall barrier crossing with landing, trajectory following, and motion behavior learning. Experimental results show that the closed loop refinement process improves policy behavior compared with initial rewards by 71%. We also demonstrate sim-to-real transfer of the proposed framework, achieving a real world success rate of 91% and a sim-to-real accuracy of 94%.

Artem Lykov, Miguel Altamirano Cabrera, Mikhail Konenkov et al.

This paper presents the concept of Industry 6.0, introducing the world's first fully automated production system that autonomously handles the entire product design and manufacturing process based on user-provided natural language descriptions. By leveraging generative AI, the system automates critical aspects of production, including product blueprint design, component manufacturing, logistics, and assembly. A heterogeneous swarm of robots, each equipped with individual AI through integration with Large Language Models (LLMs), orchestrates the production process. The robotic system includes manipulator arms, delivery drones, and 3D printers capable of generating assembly blueprints. The system was evaluated using commercial and open-source LLMs, functioning through APIs and local deployment. A user study demonstrated that the system reduces the average production time to 119.10 minutes, significantly outperforming a team of expert human developers, who averaged 528.64 minutes (an improvement factor of 4.4). Furthermore, in the product blueprinting stage, the system surpassed human CAD operators by an unprecedented factor of 47, completing the task in 0.5 minutes compared to 23.5 minutes. This breakthrough represents a major leap towards fully autonomous manufacturing.

Faryal Batool, Muhammad Ahsan Mustafa, Fawad Mehboob et al.

Indoor UAV navigation requires efficient exploration, scene understanding, and reliable trajectory execution under limited field-of-view observations. Existing vision-based navigation frameworks typically rely on single-view observations, limiting their ability to reason about occlusions, target visibility, and global scene structure. In this work, we propose AgenticDiffusion, a multi-view UAV navigation framework that coordinates language-guided reasoning, open-vocabulary target grounding, vision-based diffusion planning, and NMPC within a unified aerial navigation pipeline. Given a natural language instruction and synchronized first-person-view (FPV) and top-view observations, the framework determines the most informative viewpoint for navigation and generates a mission plan prior to trajectory execution. The targets are localized using an open-vocabulary grounding model, after which viewpoint-specific diffusion planners generate navigation trajectories for UAV execution. Using complementary viewpoints, the proposed framework reduces repeated target exploration and improves navigation efficiency in cluttered indoor environments. The framework was validated in four real-world UAV navigation scenarios involving adaptive viewpoint selection, multi-stage mission execution, long-horizon navigation, and safe landing-site selection. The experimental results demonstrated an overall mission success rate of 80% in 40 real-world trials, while the diffusion planners achieved a trajectory generation success rate of 100%.

Oleg Voynov, Gleb Bobrovskikh, Pavel Karpyshev et al.

We present a new multi-sensor dataset for multi-view 3D surface reconstruction. It includes registered RGB and depth data from sensors of different resolutions and modalities: smartphones, Intel RealSense, Microsoft Kinect, industrial cameras, and structured-light scanner. The scenes are selected to emphasize a diverse set of material properties challenging for existing algorithms. We provide around 1.4 million images of 107 different scenes acquired from 100 viewing directions under 14 lighting conditions. We expect our dataset will be useful for evaluation and training of 3D reconstruction algorithms and for related tasks. The dataset is available at skoltech3d.appliedai.tech.

Jeffrin Sam, Nguyen Khang, Yara Mahmoud et al.

We present Action Agent, a two-stage framework that unifies agentic navigation video generation with flow-constrained diffusion control for multi-embodiment robot navigation. In Stage I, a large language model (LLM) acts as an orchestration module that selects video diffusion models, refines prompts through iterative validation, and accumulates cross-task memory to synthesize physically plausible first-person navigation videos from language and image inputs. This increases video generation success from 35% (single-shot) to 86% across 50 navigation tasks. In Stage II, we introduce FlowDiT, a Flow-Constrained Diffusion Transformer that converts optimized goal videos and language instructions into continuous velocity commands using action-space denoising diffusion. FlowDiT integrates DINOv2 visual features, learned optical flow for ego-motion representation, and CLIP language embeddings for semantic stopping. We pretrain on the RECON outdoor navigation dataset and fine-tune on 203 Unitree G1 humanoid episodes collected in Isaac Sim to calibrate velocity dynamics. A single 43M-parameter checkpoint achieves 73.2% navigation success in simulation and 64.7% task completion on a real Unitree G1 in unseen indoor environments under open-loop execution, while operating at 40--47 Hz. We evaluate Action Agent across three embodiments: a Unitree G1 humanoid (real hardware), a drone, and a wheeled mobile robot (Isaac Sim), demonstrating that decoupling trajectory imagination from execution yields a scalable and embodiment-aware paradigm for language-guided navigation.

Nadya Abdel Madjid, Murad Mebrahtu, Zakhar Yagudin et al.

Predicting future trajectories of surrounding traffic agents is critical for safe autonomous navigation and collision avoidance. Despite all advances in the trajectory forecasting realm, the prediction models remains vulnerable to uncertainty caused by occlusions, limited sensing range, and perception errors. Collaborative vehicle-to-vehicle (V2V) approaches help reduce this uncertainty by sharing complementary information. Existing collaborative trajectory prediction methods typically fuse feature maps at the perception stage to construct a holistic scene view. Further this holistic representation is decoded into the future trajectories. Such design incurs substantial communication overhead due to the exchange of high-dimensional feature representations and often assumes idealized bandwidth and synchronization, limiting practical deployment. We address these limitations by shifting collaboration from perception to the prediction module and introducing a late-fusion framework for shared forecasts. The framework is model-agnostic and treats collaborating vehicles as independent asynchronous agents. We evaluate the approach on the OPV2V, V2V4Real, and DeepAccident datasets, comparing individual and collaborative forecasting. Across all datasets, late fusion consistently reduces miss rate and improves trajectory success rate ($\mathrm{TSR}_{0.5}$), defined as the fraction of ground-truth agents with final displacement error below 0.5 m. On the real-world V2V4Real dataset, collaborative prediction improves the success rate by $1.69\%$ and $1.22\%$ for both intelligent vehicles, respectively, compared with individual forecasting.

Zakhar Yagudin, Murad Mebrahtu, Ren Jin et al.

High-speed autonomous racing presents extreme perception challenges, including large relative velocities and substantial domain shifts from conventional urban-driving datasets. Existing benchmarks do not adequately capture these high-dynamic conditions. We introduce EagleVision, a unified LiDAR-based multi-task benchmark for 3D detection and trajectory prediction in high-speed racing, providing newly annotated 3D bounding boxes for the Indy Autonomous Challenge dataset (14,893 frames) and the A2RL Real competition dataset (1,163 frames), together with 12,000 simulator-generated annotated frames, all standardized under a common evaluation protocol. Using a dataset-centric transfer framework, we quantify cross-domain generalization across urban, simulator, and real racing domains. Urban pretraining improves detection over scratch training (NDS 0.72 vs. 0.69), while intermediate pretraining on real racing data achieves the best transfer to A2RL (NDS 0.726), outperforming simulator-only adaptation. For trajectory prediction, Indy-trained models surpass in-domain A2RL training on A2RL test sequences (FDE 0.947 vs. 1.250), highlighting the role of motion-distribution coverage in cross-domain forecasting. EagleVision enables systematic study of perception generalization under extreme high-speed dynamics. The dataset and benchmark are publicly available at https://avlab.io/EagleVision

Ziang Guo, Xinhao Lin, Zakhar Yagudin et al.

Multi-modal end-to-end autonomous driving has shown promising advancements in recent work. By embedding more modalities into end-to-end networks, the system's understanding of both static and dynamic aspects of the driving environment is enhanced, thereby improving the safety of autonomous driving. In this paper, we introduce METDrive, an end-to-end system that leverages temporal guidance from the embedded time series features of ego states, including rotation angles, steering, throttle signals, and waypoint vectors. The geometric features derived from perception sensor data and the time series features of ego state data jointly guide the waypoint prediction with the proposed temporal guidance loss function. We evaluated METDrive on the CARLA leaderboard benchmarks, achieving a driving score of 70%, a route completion score of 94%, and an infraction score of 0.78.

Artem Nenashev, Mikhail Kurenkov, Andrei Potapov et al.

Visual localization is a critical task in mobile robotics, and researchers are continuously developing new approaches to enhance its efficiency. In this article, we propose a novel approach to improve the accuracy of visual localization using Structure from Motion (SfM) techniques. We highlight the limitations of global SfM, which suffers from high latency, and the challenges of local SfM, which requires large image databases for accurate reconstruction. To address these issues, we propose utilizing Neural Radiance Fields (NeRF), as opposed to image databases, to cut down on the space required for storage. We suggest that sampling reference images around the prior query position can lead to further improvements. We evaluate the accuracy of our proposed method against ground truth obtained using LIDAR and Advanced Lidar Odometry and Mapping in Real-time (A-LOAM), and compare its storage usage against local SfM with COLMAP in the conducted experiments. Our proposed method achieves an accuracy of 0.068 meters compared to the ground truth, which is slightly lower than the most advanced method COLMAP, which has an accuracy of 0.022 meters. However, the size of the database required for COLMAP is 400 megabytes, whereas the size of our NeRF model is only 160 megabytes. Finally, we perform an ablation study to assess the impact of using reference images from the NeRF reconstruction.

Maria Makarova, Qian Liu, Dzmitry Tsetserukou

Diffusion models have been successfully applied in areas such as image, video, and audio generation. Recent works show their promise for sequential decision-making and dexterous manipulation, leveraging their ability to model complex action distributions. However, challenges persist due to the data limitations and scenario-specific adaptation needs. In this paper, we address these challenges by proposing an optimized approach to training diffusion policies using large, pre-built datasets that are enhanced using Reinforcement Learning (RL). Our end-to-end pipeline leverages RL-based enhancement of the DexGraspNet dataset, lightweight diffusion policy training on a dexterous manipulation task for a five-fingered robotic hand, and a pose sampling algorithm for validation. The pipeline achieved a high success rate of 80% for three DexGraspNet objects. By eliminating manual data collection, our approach lowers barriers to adopting diffusion models in robotics, enhancing generalization and robustness for real-world applications.

Faryal Batool, Iana Zhura, Valerii Serpiva et al.

Reliable human--robot collaboration in emergency scenarios requires autonomous systems that can detect humans, infer navigation goals, and operate safely in dynamic environments. This paper presents HumanDiffusion, a lightweight image-conditioned diffusion planner that generates human-aware navigation trajectories directly from RGB imagery. The system combines YOLO-11--based human detection with diffusion-driven trajectory generation, enabling a quadrotor to approach a target person and deliver medical assistance without relying on prior maps or computationally intensive planning pipelines. Trajectories are predicted in pixel space, ensuring smooth motion and a consistent safety margin around humans. We evaluate HumanDiffusion in simulation and real-world indoor mock-disaster scenarios. On a 300-sample test set, the model achieves a mean squared error of 0.02 in pixel-space trajectory reconstruction. Real-world experiments demonstrate an overall mission success rate of 80% across accident-response and search-and-locate tasks with partial occlusions. These results indicate that human-conditioned diffusion planning offers a practical and robust solution for human-aware UAV navigation in time-critical assistance settings.

Iana Zhura, Yara Mahmoud, Jeffrin Sam et al.

Efficiently predicting motion plans directly from vision remains a fundamental challenge in robotics, where planning typically requires explicit goal specification and task-specific design. Recent vision-language-action (VLA) models infer actions directly from visual input but demand massive computational resources, extensive training data, and fail zero-shot in novel scenes. We present a unified image-space diffusion policy handling both meter-scale navigation and centimeter-scale manipulation via multi-scale feature modulation, with only 5 minutes of self-supervised data per task. Three key innovations drive the framework: (1) Multi-scale FiLM conditioning on task mode, depth scale, and spatial attention enables task-appropriate behavior in a single model; (2) trajectory-aligned depth prediction focuses metric 3D reasoning along generated waypoints; (3) self-supervised attention from AnyTraverse enables goal-directed inference without vision-language models and depth sensors. Operating purely from RGB input (2.0 GB memory, 10 Hz), the model achieves robust zero-shot generalization to novel scenes while remaining suitable for onboard deployment.

Dmitrii Plotnikov, Iaroslav Kolomiets, Dmitrii Maliukov et al.

We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment. In our framework, executable Behavior Trees are repeatedly refined by a Large Language Model actor using structured natural-language feedback produced by a Vision-Language Model critic that observes the physical robot and execution traces. Unlike conventional reinforcement learning, policy updates in VRL occur directly at the symbolic planning level, without gradient-based optimization. This enables transparent reasoning, explicit causal feedback, and human-interpretable policy evolution. We validate the proposed framework on a real mobile robot performing a multi-stage manipulation and navigation task under execution uncertainty. Experimental results show that the framework supports explainable policy improvements, closed-loop adaptation to execution failures, and reliable deployment on physical robotic systems.

Amir Atef Habel, Roohan Ahmed Khan, Fawad Mehboob et al.

Wind disturbances remain a key barrier to reliable autonomous navigation for lightweight quadrotors, where the rapidly varying airflow can destabilize both planning and tracking. This paper introduces GustPilot, a hierarchical wind-resilient navigation stack in which a deep reinforcement learning (DRL) policy generates inertial-frame velocity reference for gate traversal. At the same time, a geometric Incremental Nonlinear Dynamic Inversion (INDI) controller provides low-level tracking with fast residual disturbance rejection. The INDI layer achieves this by providing incremental feedback on both specific linear acceleration and angular acceleration rate, using onboard sensor measurements to reject wind disturbances rapidly. Robustness is obtained through a two-level strategy, wind-aware planning learned via fan-jet domain randomization during training, and rapid execution-time disturbance rejection by the INDI tracking controller. We evaluate GustPilot in real flights on a 50g quad-copter platform against a DRL-PID baseline across four scenarios ranging from no-wind to fully dynamic conditions with a moving gate and a moving disturbance source. Despite being trained only in a minimal single-gate and single-fan setup, the policy generalizes to significantly more complex environments (up to six gates and four fans) without retraining. Across 80 experiments, DRL-INDI achieves a 94.7% versus 55.0% for DRL-PID as average Overall Success Rate (OSR), reduces tracking RMSE up to 50%, and sustains speeds up to 1.34 m/s under wind disturbances up to 3.5 m/s. These results demonstrate that combining DRL-based velocity planning with structured INDI disturbance rejection provides a practical and generalizable approach to wind-resilient autonomous flight navigation.

Konstantin Gubernatorov, Mikhail Sannikov, Ilya Mikhalchuk et al.

Tactile sensing is a crucial capability for Vision-Language-Action (VLA) architectures, as it enables dexterous and safe manipulation in contact-rich tasks. However, reliance on dedicated tactile hardware increases cost and reduces reproducibility across robotic platforms. We argue that tactile-aware manipulation can be learned offline and deployed without direct haptic feedback at inference. To this end, we present HapticVLA, which proceeds in two tightly coupled stages: Safety-Aware Reward-Weighted Flow Matching (SA-RWFM) and Tactile Distillation (TD). SA-RWFM trains a flow-matching action expert that incorporates precomputed, safety-aware tactile rewards penalizing excessive grasping force and suboptimal grasping trajectories. TD further transfers this tactile-aware capability into a conventional VLA: we distill a compact tactile token from the SA-RWFM teacher and train a student VLA to predict that token from vision and state modalities, enabling tactile-aware action generation at inference without requiring on-board tactile sensors. This design preserves contact-rich tactile-aware reasoning within VLA while removing the need for on-board tactile sensors during deployment. On real-world experiments, HapticVLA achieves a mean success rate of 86.7%, consistently outperforming baseline VLAs - including versions provided with direct tactile feedback during inference.

Vladimir Poliakov, Kenan Niu, Emmanuel Vander Poorten et al.

This work presents an RL-based agent for outpatient hysteroscopy training. Hysteroscopy is a gynecological procedure for examination of the uterine cavity. Recent advancements enabled performing this type of intervention in the outpatient setup without anaesthesia. While being beneficial to the patient, this approach introduces new challenges for clinicians, who should take additional measures to maintain the level of patient comfort and prevent tissue damage. Our prior work has presented a platform for hysteroscopic training with the focus on the passage of the cervical canal. With this work, we aim to extend the functionality of the platform by designing a subsystem that autonomously performs the task of the passage of the cervical canal. This feature can later be used as a virtual instructor to provide educational cues for trainees and assess their performance. The developed algorithm is based on the soft actor critic approach to smooth the learning curve of the agent and ensure uniform exploration of the workspace. The designed algorithm was tested against the performance of five clinicians. Overall, the algorithm demonstrated high efficiency and reliability, succeeding in 98% of trials and outperforming the expert group in three out of four measured metrics.

Ali Alridha Abdulkarim, Mikhail Litvinov, Dzmitry Tsetserukou

Millimeter-wave radar provides robust perception in visually degraded environments. However, radar-inertial state estimation is inherently susceptible to drift. Because radar yields only sparse, body-frame velocity measurements, it provides weak constraints on absolute orientation. Consequently, IMU biases remain poorly observable over the short time horizons typical of sliding-window filters. To address this fundamental observability challenge, we propose a tightly coupled, hierarchical radar-inertial factor graph framework. Our architecture decouples the estimation problem into a high-rate resetting graph and a persistent global graph. The resetting graph fuses IMU preintegration, radar velocities, and adaptive Zero-Velocity Updates (ZUPT) to generate the smooth, low-latency odometry required for real-time control. Concurrently, the persistent graph is a full-state factor graph maintaining the complete information of poses, velocities, and biases by fusing inertial data with keyframe-based geometric mapping and loop closures. Leveraging Incremental Smoothing and Mapping, the persistent graph can operate without explicit marginalization of variables, preserving their information while ensuring long-term bias observability. The cornerstone of our approach is a probabilistic tight-coupling mechanism: fully observable, optimized biases and their exact covariances are continuously injected from the persistent graph into the resetting graph's prior, effectively anchoring the high-rate estimator against integration drift. Extensive evaluations demonstrate our system achieves high accuracy with drift-reduced estimation at 27x real-time execution speeds. We release the implementation code and datasets upon the acceptance of the paper.

Faryal Batool, Yasheerah Yaqoot, Muhammad Ahsan Mustafa et al.

Safe swarm navigation in cluttered indoor environment requires long-horizon planning, reactive obstacle avoidance, and adaptive compliance. We propose ImpedanceDiffusion, a hierarchical framework that leverages image-conditioned diffusion-based global path planning with Artificial Potential Field (APF) tracking and semantic-aware variable impedance control for aerial drone swarms. The diffusion model generates geometric global trajectories directly from RGB images without explicit map construction. These trajectories are tracked by an APF-based reactive layer, while a VLM-RAG module performs semantic obstacle classification with 90% retrieval accuracy to adapt impedance parameters for mixed obstacle environments during execution. Two diffusion planners are evaluated: (i) a top-view long-horizon planner using single-pass inference and (ii) a first-person-view (FPV) short-horizon planner deployed via a two-stage inference pipeline. Both planners achieve a 100% trajectory generation rate across twenty static and dynamic experimental configurations and are validated via zero-shot sim-to-real deployment on Crazyflie 2.1 drones through the hierarchical APF-impedance control stack. The top-view planner produces smoother trajectories that yield conservative tracking speeds of 1.0-1.2 m/s near hard obstacles and 0.6-1.0 m/s near soft obstacles. In contrast, the FPV planner generates trajectories with greater local clearance and typically higher speeds, reaching 1.4-2.0 m/s near hard obstacles and up to 1.6 m/s near soft obstacles. Across 20 experimental configurations (100 total runs), the framework achieved a 92% success rate while maintaining stable impedance-based formation control with bounded oscillations and no in-flight collisions, demonstrating reliable and adaptive swarm navigation in cluttered indoor environments.

Fawad Mehboob, Monijesu James, Amir Habel et al.

As aerial platforms evolve from passive observers to active manipulators, the challenge shifts toward designing intuitive interfaces that allow non-expert users to command these systems naturally. This work introduces a novel concept of autonomous aerial manipulation system capable of interpreting high-level natural language commands to retrieve objects and deliver them to a human user. The system is intended to integrate a MediaPipe based on Grounding DINO and a Vision-Language-Action (VLA) model with a custom-built drone equipped with a 1-DOF gripper and an Intel RealSense RGB-D camera. VLA performs semantic reasoning to interpret the intent of a user prompt and generates a prioritized task queue for grasping of relevant objects in the scene. Grounding DINO and dynamic A* planning algorithm are used to navigate and safely relocate the object. To ensure safe and natural interaction during the handover phase, the system employs a human-centric controller driven by MediaPipe. This module provides real-time human pose estimation, allowing the drone to employ visual servoing to maintain a stable, distinct position directly in front of the user, facilitating a comfortable handover. We demonstrate the system's efficacy through real-world experiments for localization and navigation, which resulted in a 0.164m, 0.070m, and 0.084m of max, mean euclidean, and root-mean squared errors, respectively, highlighting the feasibility of VLA for aerial manipulation operations.

Valerii Serpiva, Jeffrin Sam, Chidera Simon et al.

We present DreamToNav, a novel autonomous robot framework that uses generative video models to enable intuitive, human-in-the-loop control. Instead of relying on rigid waypoint navigation, users provide natural language prompts (e.g. ``Follow the person carefully''), which the system translates into executable motion. Our pipeline first employs Qwen 2.5-VL-7B-Instruct to refine vague user instructions into precise visual descriptions. These descriptions condition NVIDIA Cosmos 2.5, a state-of-the-art video foundation model, to synthesize a physically consistent video sequence of the robot performing the task. From this synthetic video, we extract a valid kinematic path using visual pose estimation, robot detection and trajectory recovery. By treating video generation as a planning engine, DreamToNav allows robots to visually "dream" complex behaviors before executing them, providing a unified framework for obstacle avoidance and goal-directed navigation without task-specific engineering. We evaluate the approach on both a wheeled mobile robot and a quadruped robot in indoor navigation tasks. DreamToNav achieves a success rate of 76.7%, with final goal errors typically within 0.05-0.10 m and trajectory tracking errors below 0.15 m. These results demonstrate that trajectories extracted from generative video predictions can be reliably executed on physical robots across different locomotion platforms.

Miguel Altamirano Cabrera, Jonathan Tirado, Aleksey Fedoseev et al.

The shape of deformable objects can change drastically during grasping by robotic grippers, causing an ambiguous perception of their alignment and hence resulting in errors in robot positioning and telemanipulation. Rendering clear tactile patterns is fundamental to increasing users' precision and dexterity through tactile haptic feedback during telemanipulation. Therefore, different methods have to be studied to decode the sensors' data into haptic stimuli. This work presents a telemanipulation system for plastic pipettes that consists of a Force Dimension Omega.7 haptic interface endowed with two electro-stimulation arrays and two tactile sensor arrays embedded in the 2-finger Robotiq gripper. We propose a novel approach based on convolutional neural networks (CNN) to detect the tilt of deformable objects. The CNN generates a tactile pattern based on recognized tilt data to render further electro-tactile stimuli provided to the user during the telemanipulation. The study has shown that using the CNN algorithm, tilt recognition by users increased from 23.13\% with the downsized data to 57.9%, and the success rate during teleoperation increased from 53.12% using the downsized data to 92.18% using the tactile patterns generated by the CNN.

Alexander Petrovsky, Yomna Youssef, Kirill Myasoedov et al.

This paper focuses on Passable Obstacles Aware (POA) planner - a novel navigation method for two-wheeled robots in a highly cluttered environment. The navigation algorithm detects and classifies objects to distinguish two types of obstacles - passable and unpassable. Our algorithm allows two-wheeled robots to find a path through passable obstacles. Such a solution helps the robot working in areas inaccessible to standard path planners and find optimal trajectories in scenarios with a high number of objects in the robot's vicinity. The POA planner can be embedded into other planning algorithms and enables them to build a path through obstacles. Our method decreases path length and the total travel time to the final destination up to 43% and 39%, respectively, comparing to standard path planners such as GVD, A*, and RRT*

Ziang Guo, Min Chen, Xuefeng Zhang et al.

End-to-end (E2E) autonomous driving presents a promising approach for translating perceptual inputs directly into driving actions. However, prohibitive annotation costs and temporal data quality degradation hinder long-term real-world deployment. While combining imitation learning (IL) and reinforcement learning (RL) is a common strategy for policy improvement, conventional RL training relies on delayed, event-based rewards-policies learn only from catastrophic outcomes such as collisions, leading to premature convergence to suboptimal behaviors. To address these limitations, we introduce GSDrive, a framework that exploits 3D Gaussian Splatting (3DGS) for differentiable, physics-based reward shaping in E2E driving policy improvement. Our method incorporates a flow matching-based trajectory predictor within the 3DGS simulator, enabling multi-mode trajectory probing where candidate trajectories are rolled out to assess prospective rewards. This establishes a bidirectional knowledge exchange between IL and RL by grounding reward functions in physically simulated interaction signals, offering immediate dense feedback instead of sparse catastrophic events. Evaluated on the reconstructed nuScenes dataset, our method surpasses existing simulation-based RL driving approaches in closed-loop experiments. Code is available at https://github.com/ZionGo6/GSDrive.

Ziang Guo, Stepan Perminov, Mikhail Konenkov et al.

Many established vision perception systems for autonomous driving scenarios ignore the influence of light conditions, one of the key elements for driving safety. To address this problem, we present HawkDrive, a novel perception system with hardware and software solutions. Hardware that utilizes stereo vision perception, which has been demonstrated to be a more reliable way of estimating depth information than monocular vision, is partnered with the edge computing device Nvidia Jetson Xavier AGX. Our software for low light enhancement, depth estimation, and semantic segmentation tasks, is a transformer-based neural network. Our software stack, which enables fast inference and noise reduction, is packaged into system modules in Robot Operating System 2 (ROS2). Our experimental results have shown that the proposed end-to-end system is effective in improving the depth estimation and semantic segmentation performance. Our dataset and codes will be released at https://github.com/ZionGo6/HawkDrive.

Danil Belov, Artem Erkhov, Elizaveta Pestova et al.

The aim of this work is to enable quadrupedal robots to mount skateboards using Reverse Curriculum Reinforcement Learning. Although prior work has demonstrated skateboarding for quadrupeds that are already positioned on the board, the initial mounting phase still poses a significant challenge. A goal-oriented methodology was adopted, beginning with the terminal phases of the task and progressively increasing the complexity of the problem definition to approximate the desired objective. The learning process was initiated with the skateboard rigidly fixed within the global coordinate frame and the robot positioned directly above it. Through gradual relaxation of these initial conditions, the learned policy demonstrated robustness to variations in skateboard position and orientation, ultimately exhibiting a successful transfer to scenarios involving a mobile skateboard. The code, trained models, and reproducible examples are available at the following link: https://github.com/dancher00/quadruped-skateboard-mounting

Ziang Guo, Zakhar Yagudin, Selamawit Asfaw et al.

Camera, LiDAR and radar are common perception sensors for autonomous driving tasks. Robust prediction of 3D object detection is optimally based on the fusion of these sensors. To exploit their abilities wisely remains a challenge because each of these sensors has its own characteristics. In this paper, we propose FADet, a multi-sensor 3D detection network, which specifically studies the characteristics of different sensors based on our local featured attention modules. For camera images, we propose dual-attention-based sub-module. For LiDAR point clouds, triple-attention-based sub-module is utilized while mixed-attention-based sub-module is applied for features of radar points. With local featured attention sub-modules, our FADet has effective detection results in long-tail and complex scenes from camera, LiDAR and radar input. On NuScenes validation dataset, FADet achieves state-of-the-art performance on LiDAR-camera object detection tasks with 71.8% NDS and 69.0% mAP, at the same time, on radar-camera object detection tasks with 51.7% NDS and 40.3% mAP. Code will be released at https://github.com/ZionGo6/FADet.

Dinar Sharafutdinov, Mark Griguletskii, Pavel Kopanev et al.

SLAM is one of the most fundamental areas of research in robotics and computer vision. State of the art solutions has advanced significantly in terms of accuracy and stability. Unfortunately, not all the approaches are available as open-source solutions and free to use. The results of some of them are difficult to reproduce, and there is a lack of comparison on common datasets. In our work, we make a comparative analysis of state of the art open-source methods. We assess the algorithms based on accuracy, computational performance, robustness, and fault tolerance. Moreover, we present a comparison of datasets as well as an analysis of algorithms from a practical point of view. The findings of the work raise several crucial questions for SLAM researchers.

Oleg Sautenkov, Yasheerah Yaqoot, Artem Lykov et al.

The UAV-VLA (Visual-Language-Action) system is a tool designed to facilitate communication with aerial robots. By integrating satellite imagery processing with the Visual Language Model (VLM) and the powerful capabilities of GPT, UAV-VLA enables users to generate general flight paths-and-action plans through simple text requests. This system leverages the rich contextual information provided by satellite images, allowing for enhanced decision-making and mission planning. The combination of visual analysis by VLM and natural language processing by GPT can provide the user with the path-and-action set, making aerial operations more efficient and accessible. The newly developed method showed the difference in the length of the created trajectory in 22% and the mean error in finding the objects of interest on a map in 34.22 m by Euclidean distance in the K-Nearest Neighbors (KNN) approach.

Mikhail Konenkov, Artem Lykov, Daria Trinitatova et al.

The advent of immersive Virtual Reality applications has transformed various domains, yet their integration with advanced artificial intelligence technologies like Visual Language Models remains underexplored. This study introduces a pioneering approach utilizing VLMs within VR environments to enhance user interaction and task efficiency. Leveraging the Unity engine and a custom-developed VLM, our system facilitates real-time, intuitive user interactions through natural language processing, without relying on visual text instructions. The incorporation of speech-to-text and text-to-speech technologies allows for seamless communication between the user and the VLM, enabling the system to guide users through complex tasks effectively. Preliminary experimental results indicate that utilizing VLMs not only reduces task completion times but also improves user comfort and task engagement compared to traditional VR interaction methods.

Valerii Serpiva, Artem Lykov, Artyom Myshlyaev et al.

RaceVLA presents an innovative approach for autonomous racing drone navigation by leveraging Visual-Language-Action (VLA) to emulate human-like behavior. This research explores the integration of advanced algorithms that enable drones to adapt their navigation strategies based on real-time environmental feedback, mimicking the decision-making processes of human pilots. The model, fine-tuned on a collected racing drone dataset, demonstrates strong generalization despite the complexity of drone racing environments. RaceVLA outperforms OpenVLA in motion (75.0 vs 60.0) and semantic generalization (45.5 vs 36.3), benefiting from the dynamic camera and simplified motion tasks. However, visual (79.6 vs 87.0) and physical (50.0 vs 76.7) generalization were slightly reduced due to the challenges of maneuvering in dynamic environments with varying object sizes. RaceVLA also outperforms RT-2 across all axes - visual (79.6 vs 52.0), motion (75.0 vs 55.0), physical (50.0 vs 26.7), and semantic (45.5 vs 38.8), demonstrating its robustness for real-time adjustments in complex environments. Experiments revealed an average velocity of 1.04 m/s, with a maximum speed of 2.02 m/s, and consistent maneuverability, demonstrating RaceVLA's ability to handle high-speed scenarios effectively. These findings highlight the potential of RaceVLA for high-performance navigation in competitive racing contexts. The RaceVLA codebase, pretrained weights, and dataset are available at this http URL: https://racevla.github.io/

Ziang Guo, Konstantin Gubernatorov, Selamawit Asfaw et al.

In autonomous driving, dynamic environment and corner cases pose significant challenges to the robustness of ego vehicle's decision-making. To address these challenges, commencing with the representation of state-action mapping in the end-to-end autonomous driving paradigm, we introduce a novel pipeline, VDT-Auto. Leveraging the advancement of the state understanding of Visual Language Model (VLM), incorporating with diffusion Transformer-based action generation, our VDT-Auto parses the environment geometrically and contextually for the conditioning of the diffusion process. Geometrically, we use a bird's-eye view (BEV) encoder to extract feature grids from the surrounding images. Contextually, the structured output of our fine-tuned VLM is processed into textual embeddings and noisy paths. During our diffusion process, the added noise for the forward process is sampled from the noisy path output of the fine-tuned VLM, while the extracted BEV feature grids and embedded texts condition the reverse process of our diffusion Transformers. Our VDT-Auto achieved 0.52m on average L2 errors and 21% on average collision rate in the nuScenes open-loop planning evaluation. Moreover, the real-world demonstration exhibited prominent generalizability of our VDT-Auto. The code and dataset will be released after acceptance.

Oleg Sautenkov, Yasheerah Yaqoot, Muhammad Ahsan Mustafa et al.

We present UAV-CodeAgents, a scalable multi-agent framework for autonomous UAV mission generation, built on large language and vision-language models (LLMs/VLMs). The system leverages the ReAct (Reason + Act) paradigm to interpret satellite imagery, ground high-level natural language instructions, and collaboratively generate UAV trajectories with minimal human supervision. A core component is a vision-grounded, pixel-pointing mechanism that enables precise localization of semantic targets on aerial maps. To support real-time adaptability, we introduce a reactive thinking loop, allowing agents to iteratively reflect on observations, revise mission goals, and coordinate dynamically in evolving environments. UAV-CodeAgents is evaluated on large-scale mission scenarios involving industrial and environmental fire detection. Our results show that a lower decoding temperature (0.5) yields higher planning reliability and reduced execution time, with an average mission creation time of 96.96 seconds and a success rate of 93%. We further fine-tune Qwen2.5VL-7B on 9,000 annotated satellite images, achieving strong spatial grounding across diverse visual categories. To foster reproducibility and future research, we will release the full codebase and a novel benchmark dataset for vision-language-based UAV planning.

Marcelino Julio Fernando, Miguel Altamirano Cabrera, Jeffrin Sam et al.

Bimanual mobile manipulation requires a seamless integration between high-level semantic reasoning and safe, compliant physical interaction - a challenge that end-to-end models approach opaquely and classical controllers lack the context to address. This paper presents GenerativeMPC, a hierarchical cyber-physical framework that explicitly bridges semantic scene understanding with physical control parameters for bimanual mobile manipulators. The system utilizes a Vision-Language Model with Retrieval-Augmented Generation (VLM-RAG) to translate visual and linguistic context into grounded control constraints, specifically outputting dynamic velocity limits and safety margins for a Whole-Body Model Predictive Controller (MPC). Simultaneously, the VLM-RAG module modulates virtual stiffness and damping gains for a unified impedance-admittance controller, enabling context-aware compliance during human-robot interaction. Our framework leverages an experience-driven vector database to ensure consistent parameter grounding without retraining. Experimental results in MuJoCo, IsaacSim, and on a physical bimanual platform confirm a 60% speed reduction near humans and safe, socially-aware navigation and manipulation through semantic-to-physical parameter grounding. This work advances the field of human-centric cybernetics by grounding large-scale cognitive models into predictable, high-frequency physical control loops.

Lavanya Ratnabala, Aleksey Fedoseev, Robinroy Peter et al.

This paper addresses the challenge of decentralized task allocation within heterogeneous multi-agent systems operating under communication constraints. We introduce a novel framework that integrates graph neural networks (GNNs) with a centralized training and decentralized execution (CTDE) paradigm, further enhanced by a tailored Proximal Policy Optimization (PPO) algorithm for multi-agent deep reinforcement learning (MARL). Our approach enables unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) to dynamically allocate tasks efficiently without necessitating central coordination in a 3D grid environment. The framework minimizes total travel time while simultaneously avoiding conflicts in task assignments. For the cost calculation and routing, we employ reservation-based A* and R* path planners. Experimental results revealed that our method achieves a high 92.5% conflict-free success rate, with only a 7.49% performance gap compared to the centralized Hungarian method, while outperforming the heuristic decentralized baseline based on greedy approach. Additionally, the framework exhibits scalability with up to 20 agents with allocation processing of 2.8 s and robustness in responding to dynamically generated tasks, underscoring its potential for real-world applications in complex multi-agent scenarios.

Artem Bazhenov, Vladimir Berman, Sergei Satsevich et al.

This paper introduces DogSurf - a newapproach of using quadruped robots to help visually impaired people navigate in real world. The presented method allows the quadruped robot to detect slippery surfaces, and to use audio and haptic feedback to inform the user when to stop. A state-of-the-art GRU-based neural network architecture with mean accuracy of 99.925% was proposed for the task of multiclass surface classification for quadruped robots. A dataset was collected on a Unitree Go1 Edu robot. The dataset and code have been posted to the public domain.

Elizaveta Semenyakina, Ivan Snegirev, Mariya Lezina et al.

Dexterous robotic manipulation requires more than geometrically valid grasps: it demands physically grounded contact strategies that account for the spatially non-uniform mechanical properties of the object. However, existing grasp planners typically treat the surface as structurally homogeneous, even though contact in a weak region can damage the object despite a geometrically perfect grasp. We present a pipeline for grasp selection and force regulation in a five-fingered robotic hand, based on a map of locally admissible contact loads. From an operator command, the system identifies the target object, reconstructs its 3D geometry using SAM3D, and imports the model into Isaac Sim. A physics-informed geometric analysis then computes a force map that encodes the maximum lateral contact force admissible at each surface location without deformation. Grasp candidates are filtered by geometric validity and task-goal consistency. When multiple candidates are comparable under classical metrics, they are re-ranked using a force-map-aware criterion that favors grasps with contacts in mechanically admissible regions. An impedance controller scales the stiffness of each finger according to the locally admissible force at the contact point, enabling safe and reliable grasp execution. Validation on paper, plastic, and glass cups shows that the proposed approach consistently selects structurally stronger contact regions and keeps grip forces within safe bounds. In this way, the work reframes dexterous manipulation from a purely geometric problem into a physically grounded joint planning problem of grasp selection and grip execution for future humanoid systems.

Konstantin Gubernatorov, Artem Voronov, Roman Voronov et al.

We address natural language pick-and-place in unseen, unpredictable indoor environments with AnywhereVLA, a modular framework for mobile manipulation. A user text prompt serves as an entry point and is parsed into a structured task graph that conditions classical SLAM with LiDAR and cameras, metric semantic mapping, and a task-aware frontier exploration policy. An approach planner then selects visibility and reachability aware pre grasp base poses. For interaction, a compact SmolVLA manipulation head is fine tuned on platform pick and place trajectories for the SO-101 by TheRobotStudio, grounding local visual context and sub-goals into grasp and place proposals. The full system runs fully onboard on consumer-level hardware, with Jetson Orin NX for perception and VLA and an Intel NUC for SLAM, exploration, and control, sustaining real-time operation. We evaluated AnywhereVLA in a multi-room lab under static scenes and normal human motion. In this setting, the system achieves a $46\%$ overall task success rate while maintaining throughput on embedded compute. By combining a classical stack with a fine-tuned VLA manipulation, the system inherits the reliability of geometry-based navigation with the agility and task generalization of language-conditioned manipulation.

Viktor Rakhmatulin, Miguel Altamirano Cabrera, Fikre Hagos et al.

Modern industry still relies on manual manufacturing operations and safe human-robot interaction is of great interest nowadays. Speed and Separation Monitoring (SSM) allows close and efficient collaborative scenarios by maintaining a protective separation distance during robot operation. The paper focuses on a novel approach to strengthen the SSM safety requirements by introducing haptic feedback to a robotic cell worker. Tactile stimuli provide early warning of dangerous movements and proximity to the robot, based on the human reaction time and instantaneous velocities of robot and operator. A preliminary experiment was performed to identify the reaction time of participants when they are exposed to tactile stimuli in a collaborative environment with controlled conditions. In a second experiment, we evaluated our approach into a study case where human worker and cobot performed collaborative planetary gear assembly. Results show that the applied approach increased the average minimum distance between the robot's end-effector and hand by 44% compared to the operator relying only on the visual feedback. Moreover, the participants without the haptic support have failed several times to maintain the protective separation distance.

Polina Ponomareva, Daria Trinitatova, Aleksey Fedoseev et al.

The teleoperation of robotic systems in medical applications requires stable and convenient visual feedback for the operator. The most accessible approach to delivering visual information from the remote area is using cameras to transmit a video stream from the environment. However, such systems are sensitive to the camera resolution, limited viewpoints, and cluttered environment bringing additional mental demands to the human operator. The paper proposes a novel system of teleoperation based on an augmented virtual environment (VE). The region-based convolutional neural network (R-CNN) is applied to detect the laboratory instrument and estimate its position in the remote environment to display further its digital twin in the VE, which is necessary for dexterous telemanipulation. The experimental results revealed that the developed system allows users to operate the robot smoother, which leads to a decrease in task execution time when manipulating test tubes. In addition, the participants evaluated the developed system as less mentally demanding (by 11%) and requiring less effort (by 16%) to accomplish the task than the camera-based teleoperation approach and highly assessed their performance in the augmented VE. The proposed technology can be potentially applied for conducting laboratory tests in remote areas when operating with infectious and poisonous reagents.

Saian Protasov, Pavel Karpyshev, Ivan Kalinov et al.

Mobile autonomous robots include numerous sensors for environment perception. Cameras are an essential tool for robot's localization, navigation, and obstacle avoidance. To process a large flow of data from the sensors, it is necessary to optimize algorithms, or to utilize substantial computational power. In our work, we propose an algorithm for optimizing a neural network for object detection using preliminary binary frame classification. An autonomous outdoor mobile robot with 6 rolling-shutter cameras on the perimeter providing a 360-degree field of view was used as the experimental setup. The obtained experimental results revealed that the proposed optimization accelerates the inference time of the neural network in the cases with up to 5 out of 6 cameras containing target objects.

Ivan Kalinov, Daria Trinitatova, Dzmitry Tsetserukou

WareVR is a novel human-robot interface based on a virtual reality (VR) application to interact with a heterogeneous robotic system for automated inventory management. We have created an interface to supervise an autonomous robot remotely from a secluded workstation in a warehouse that could benefit during the current pandemic COVID-19 since the stocktaking is a necessary and regular process in warehouses, which involves a group of people. The proposed interface allows regular warehouse workers without experience in robotics to control the heterogeneous robotic system consisting of an unmanned ground vehicle (UGV) and unmanned aerial vehicle (UAV). WareVR provides visualization of the robotic system in a digital twin of the warehouse, which is accompanied by a real-time video stream from the real environment through an on-board UAV camera. Using the WareVR interface, the operator can conduct different levels of stocktaking, monitor the inventory process remotely, and teleoperate the drone for a more detailed inspection. Besides, the developed interface includes remote control of the UAV for intuitive and straightforward human interaction with the autonomous robot for stocktaking. The effectiveness of the VR-based interface was evaluated through the user study in a "visual inspection" scenario.

Evgeny Tsykunov, Aleksey Fedoseev, Ekaterina Dorzhieva et al.

DroneStick is a novel hands-free method for smooth interaction between a human and a robotic system via one of its agents, without training and any additional handheld or wearable device or infrastructure. A flying joystick (DroneStick), being a part of a multi-robot system, is composed of a flying drone and coiled wire with a vibration motor. By pulling on the coiled wire, the operator commands certain motions of the follower robotic system. The DroneStick system does not require the user to carry any equipment before or after performing the required interaction. DroneStick provides useful feedback to the operator in the form of force transferred through the wire, translation/rotation of the flying joystick, and motor vibrations at the fingertips. Feedback allows users to interact with different forms of robotic systems intuitively. A potential application can enhance an automated `last mile' delivery when a recipient needs to guide a delivery drone/robot gently to a spot where a parcel has to be dropped.

Miguel Altamirano Cabrera, Juan Heredia, Jonathan Tirado et al.

Complex tasks require human collaboration since robots do not have enough dexterity. However, robots are still used as instruments and not as collaborative systems. We are introducing a framework to ensure safety in a human-robot collaborative environment. The system is composed of a haptic feedback display, low-cost wearable mocap, and a new collision avoidance algorithm based on the Artificial Potential Fields (APF). Wearable optical motion capturing system enables tracking the human hand position with high accuracy and low latency on large working areas. This study evaluates whether haptic feedback improves safety in human-robot collaboration. Three experiments were carried out to evaluate the performance of the proposed system. The first one evaluated human responses to the haptic device during interaction with the Robot Tool Center Point (TCP). The second experiment analyzed human-robot behavior during an imminent collision. The third experiment evaluated the system in a collaborative activity in a shared working environment. This study had shown that when haptic feedback in the control loop was included, the safe distance (minimum robot-obstacle distance) increased by 4.1 cm from 12.39 cm to 16.55 cm, and the robot's path, when the collision avoidance algorithm was activated, was reduced by 81%.

Nikita Mikhailovskiy, Alexander Sedunin, Stepan Perminov et al.

The paper focuses on the development of an autonomous disinfection robot UltraBot to reduce COVID-19 transmission along with other harmful bacteria and viruses. The motivation behind the research is to develop such a robot that is capable of performing disinfection tasks without the use of harmful sprays and chemicals that can leave residues and require airing the room afterward for a long time. UltraBot technology has the potential to offer the most optimal autonomous disinfection performance along with taking care of people, keeping them from getting under the UV-C radiation. The paper highlights UltraBot's mechanical and electrical design as well as disinfection performance. The conducted experiments demonstrate the effectiveness of robot disinfection ability and actual disinfection area per each side with UV-C lamp array. The disinfection effectiveness results show actual performance for the multi-pass technique that provides 1-log reduction with combined direct UV-C exposure and ozone-based air purification after two robot passes at a speed of 0.14 m/s. This technique has the same performance as ten minutes static disinfection. Finally, we have calculated the non-trivial form of the robot disinfection zone by two consecutive experiment to produce optimal path planning and to provide full disinfection in selected areas.

Stepan Perminov, Nikita Mikhailovskiy, Alexander Sedunin et al.

The paper focuses on the development of the autonomous robot UltraBot to reduce COVID-19 transmission and other harmful bacteria and viruses. The motivation behind the research is to develop such a robot that is capable of performing disinfection tasks without the use of harmful sprays and chemicals that can leave residues, require airing the room afterward for a long time, and can cause the corrosion of the metal structures. UltraBot technology has the potential to offer the most optimal autonomous disinfection performance along with taking care of people, keeping them from getting under UV-C radiation. The paper highlights UltraBot's mechanical and electrical structures as well as low-level and high-level control systems. The conducted experiments demonstrate the effectiveness of the robot localization module and optimal trajectories for UV-C disinfection. The results of UV-C disinfection performance revealed a decrease of the total bacterial count (TBC) by 94% on the distance of 2.8 meters from the robot after 10 minutes of UV-C irradiation.

Valery Ilin, Ivan Kalinov, Pavel Karpyshev et al.

In the proposed study, we describe the possibility of automated dataset collection using an articulated robot. The proposed technology reduces the number of pixel errors on a polygonal dataset and the time spent on manual labeling of 2D objects. The paper describes a novel automatic dataset collection and annotation system, and compares the results of automated and manual dataset labeling. Our approach increases the speed of data labeling 240-fold, and improves the accuracy compared to manual labeling 13-fold. We also present a comparison of metrics for training a neural network on a manually annotated and an automatically collected dataset.

Ekaterina Karmanova, Valerii Serpiva, Stepan Perminov et al.

Reinforcement learning (RL) methods have been actively applied in the field of robotics, allowing the system itself to find a solution for a task otherwise requiring a complex decision-making algorithm. In this paper, we present a novel RL-based Tic-tac-toe scenario, i.e. SwarmPlay, where each playing component is presented by an individual drone that has its own mobility and swarm intelligence to win against a human player. Thus, the combination of challenging swarm strategy and human-drone collaboration aims to make the games with machines tangible and interactive. Although some research on AI for board games already exists, e.g., chess, the SwarmPlay technology has the potential to offer much more engagement and interaction with the user as it proposes a multi-agent swarm instead of a single interactive robot. We explore user's evaluation of RL-based swarm behavior in comparison with the game theory-based behavior. The preliminary user study revealed that participants were highly engaged in the game with drones (70% put a maximum score on the Likert scale) and found it less artificial compared to the regular computer-based systems (80%). The affection of the user's game perception from its outcome was analyzed and put under discussion. User study revealed that SwarmPlay has the potential to be implemented in a wider range of games, significantly improving human-drone interactivity.

Ekaterina Karmanova, Valerii Serpiva, Stepan Perminov et al.

We present a new paradigm of games, i.e. SwarmPlay, where each playing component is presented by an individual drone that has its own mobility and swarm intelligence to win against a human player. The motivation behind the research is to make the games with machines tangible and interactive. Although some research on the robotic players for board games already exists, e.g., chess, the SwarmPlay technology has the potential to offer much more engagement and interaction with a human as it proposes a multi-agent swarm instead of a single interactive robot. The proposed system consists of a robotic swarm, a workstation, a computer vision (CV), and Game Theory-based algorithms. A novel game algorithm was developed to provide a natural game experience to the user. The preliminary user study revealed that participants were highly engaged in the game with drones (69% put a maximum score on the Likert scale) and found it less artificial compared to the regular computer-based systems (77% put maximum score). The affection of the user's game perception from its outcome was analyzed and put under discussion. User study revealed that SwarmPlay has the potential to be implemented in a wider range of games, significantly improving human-drone interactivity.

Valerii Serpiva, Ekaterina Karmanova, Aleksey Fedoseev et al.

We propose a novel human-swarm interaction system, allowing the user to directly control a swarm of drones in a complex environment through trajectory drawing with a hand gesture interface based on the DNN-based gesture recognition. The developed CV-based system allows the user to control the swarm behavior without additional devices through human gestures and motions in real-time, providing convenient tools to change the swarm's shape and formation. The two types of interaction were proposed and implemented to adjust the swarm hierarchy: trajectory drawing and free-form trajectory generation control. The experimental results revealed a high accuracy of the gesture recognition system (99.75%), allowing the user to achieve relatively high precision of the trajectory drawing (mean error of 5.6 cm in comparison to 3.1 cm by mouse drawing) over the three evaluated trajectory patterns. The proposed system can be potentially applied in complex environment exploration, spray painting using drones, and interactive drone shows, allowing users to create their own art objects by drone swarms.

Iaroslav Okunevich, Daria Trinitatova, Pavel Kopanev et al.

DeltaCharger is a novel charging robot with an Inverted Delta structure for 3D positioning of electrodes to achieve robust and safe transferring energy between two mobile robots. The embedded high-fidelity tactile sensors allow to estimate the angular, vertical and horizontal misalignments between electrodes on the charger mechanism and electrodes on the target robot using pressure data on the contact surfaces. This is crucial for preventing a short circuit. In this paper, the mechanism of the developed prototype and evaluation study of different machine learning models for misalignment prediction are presented. The experimental results showed that the proposed system can measure the angle, vertical and horizontal values of misalignment from pressure data with an accuracy of 95.46%, 98.2%, and 86.9%, respectively, using a Convolutional Neural Network (CNN). DeltaCharger can potentially bring a new level of charging systems and improve the prevalence of mobile autonomous robots.