Search arXiv⌕ Search

arXiv subjects

Dzmitry Tsetserukou

Publications and source records attributed to Dzmitry Tsetserukou.

At least 19 recordsLinked to original sources
arXiv2026

AgenticDiffusion: Multi-View Reasoning with View-Conditioned Diffusion Planning for Vision-Based UAV Navigation

Vision-based UAV navigation becomes challenging when navigation targets are distributed across complementary camera views and cannot be reliably observed from a single viewpoint. We propose AgenticDiffusion, an agentic multi-view UAV navigation framework that semantically coordinates first-person-view (FPV) and top-view observations for mission-level navigation. Given a natural-language instruction, AgenticDiffusion identifies the requested targets, selects the most appropriate camera view for each navigation task, determines the corresponding navigation goal, and invokes the appropriate view-conditioned diffusion planner for trajectory generation. The resulting trajectories are executed using Nonlinear Model Predictive Control (NMPC). AgenticDiffusion was evaluated in four real-world indoor scenarios, achieving an overall mission success rate of 80% across 40 physical-flight trials. In mixed-visibility scenarios, where the requested targets were distributed across FPV and top-view observations, coordinated multi-view navigation reduced average mission time by 50.8% relative to FPV-only navigation and by 26.8% relative to Top-only navigation. The semantic view-selection mechanism was also robust to lexical variation in target descriptions, achieving 100% accuracy across 66 test cases, compared with 63.64% for a confidence-based view-selection baseline. In a substantially larger Gazebo environment, AgenticDiffusion achieved a 90% mission success rate and completed the multi-stage mission, whereas the FPV-only and Top-only variants were unable to complete all requested navigation tasks.

cs.RO↗
arXiv2026

FlockDiffusion: Assignment-Conditioned Diffusion for Multi-Drone Task Allocation and Completion

Autonomous multi-drone navigation requires fleets to service distributed objectives in cluttered environments under tight computational budgets. Efficient coordination depends on task bundling, where each drone visits multiple objectives along its route. Separate solvers for cost estimation, assignment, and execution incur redundant graph search and produce long, abrupt paths. We propose FlockDiffusion, a learned framework combining a scene graph encoder, an explicit allocation head, an assignment conditioned diffusion transformer, and a closed form trajectory decoder. An autoregressive teacher provides offline supervision for parallel fleet trajectory generation. PyBullet ablations show that bundling increases task completion from 50% to 100%, while our complete teacher further reduces route cost by 8.4% relative to MAGNNET with bundling. In the optimized scalability benchmark, evaluated on 100 scenes per density with ten drones, FlockDiffusion achieves 6.2 to 7.6 times faster inference and approximately 37% shorter routes than the classical pipeline. As nominal task counts increase from 20 to 40, latency rises from 7.8 to 11.1 ms, compared with 48.0 to 75.8 ms for the baseline. In a separate evaluation across five Gazebo environments, FlockDiffusion achieves 100% planner coverage and reduces planned route cost by 15.4% relative to the baseline with bundling. These results demonstrate efficient planning under increasing task density in configurations that are demanding to reproduce with physical drone fleets.

cs.RO↗
arXiv2026

HapticWAM: Distilling Imagined Touch into a World-Action Model without Inference-Time Tactile Sensing

Contact-rich manipulation requires estimating forces, slip and contact geometry that can remain ambiguous in scene images. Optical tactile sensors provide both visual observations of the contact surface and mechanical measurements, yet learning from these signals raises two challenges: representing contact beyond appearance and transferring its benefits to a policy that does not require fingertip observations at deployment. We introduce HapticWAM, a world-action model that combines heterogeneous tactile encoding, structured contact prediction and teacher-student distillation. Its teacher encodes gel images together with deformation, shear, distributed forces, resultant wrench and derived contact state into a frozen video backbone. Rather than predicting tactile pixels alone, the model jointly generates actions and a contact package describing future events and mechanics. Anticipatory Contact Coupling uses the previously imagined package to condition attention, preserving a contact-related input when direct tactile observations are unavailable. Haptic-Imagination Distillation transfers both contact futures and action predictions to a student that retains the generative contact head but removes its fingertip input branches. On a real-world setup, across three contact-rich pick-and-place tasks, HapticWAM Student achieves a 77% per-task mean success rate (41 of 50 starts, 82% pooled), reaching 95% on one of the tasks, outperforming the evaluated teacher and baseline configurations.

cs.RO↗
arXiv2026

EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation

Visual traversability estimation is central to autonomous navigation, yet most approaches either rely on prompt-driven Vision-Language Model (VLM) or decouple traversability from trajectory planning, requiring separate planners with heavy mapping, manual tuning, and extended deployment time. We propose EmbodiedDiffusion, a diffusion-based framework that simultaneously predicts traversability maps and generates feasible trajectories from RGB images using planner-free synthetic supervision and embodiment conditioning for cross-platform transfer. The framework distills category-level traversability semantics from a VLM teacher into a lightweight student model during training, enabling prompt-free, real-time inference at deployment. A modular FiLM-based conditioning mechanism isolates embodiment-specific reasoning into a compact trainable subset of the network, allowing rapid adaptation to new robot platforms without retraining the visual backbone or the trajectory diffusion model. Across indoor environments with quadruped and aerial robots, EmbodiedDiffusion achieves 80-100% navigation success in the full-data regime with real-time inference (90 ms) and adapts to new platforms using only 10 min of visual data collection, demonstrating scalable, unified traversability reasoning and trajectory generation for heterogeneous robots.

cs.RO↗
arXiv2026

LoCal-RIO: Radar-Inertial Odometry with Loop-Closure IMU Bias Calibration

Millimeter-wave radar enables robust perception in visually degraded environments, yet radar-inertial estimation remains prone to drift: body-frame velocity measurements do not constrain heading and position, and the gyroscope bias, which governs heading drift, is poorly observable over the short horizons of sliding-window estimators. We propose a hierarchical radar-inertial factor graph that separates estimation into a fixed-lag navigation graph, which fuses IMU preintegration, radar velocities, ZUPT, and ground-plane constraints into smooth, low-latency odometry, and a keyframe mapping graph, which combines this odometry with submap registration and loop closures. Loop closures additionally calibrate the IMU: the part of a loop residual explained by a bias error is estimated through preintegration Jacobians chained over the loop interval and enters the navigation graph as a prior on the bias alone. Since this calibration is irreversible, it uses only loop closures accepted by the mapping graph and a cycle-consistency test. Extensive evaluations demonstrate high accuracy and drift-reduced estimation at real-time speeds.

cs.RO↗
arXiv2026

AgenticRL: Agentic Reinforcement Learning with Self-Refinement for Complex UAV Navigation

Deep reinforcement learning enables autonomous robots to learn complex navigation tasks, but still relies heavily on time consuming manual reward design and fine tuning. Existing automated reward generation and refinement methods reduce this effort, yet often lack task-level behavioral diagnosis for directing subsequent reward revisions. We introduce AgenticRL, a multimodal closed loop framework in which role-specialized agents generate executable rewards, diagnose failures of the resulting policies, formulate targeted refinement instructions, and regenerate improved rewards. Before training, a task grounding stage automatically selects a compatible action profile, together with its observation and reward interfaces. Each generated reward is used to train a policy using Proximal Policy Optimization (PPO), which is subsequently evaluated under randomized conditions. Task-level behavioral, geometric, and safety measurements are organized into a structured diagnosis packet and jointly analyzed with the current reward code, task specification, behavioral summary, and visual scene context. Unlike one-shot reward generation, human-guided refinement, or broad candidate search, AgenticRL uses automated diagnosis of the behavior induced by a reward to direct its next revision. We evaluate the framework across eight UAV tasks covering navigation, obstacle interaction, trajectory tracking, agile manoeuvres, and cluttered flight. Under the reported comparative evaluation, AgenticRL achieves success rates of 100% in racing and 88% in cluttered navigation, exceeding the strongest Eureka and Text2Reward baselines, respectively. Reward refinement increases mean simulation success from 37.2% to 96.4%, while the resulting policies achieve a collective real-world success rate of 90.0% and a sim-to-real accuracy of 93.4%.

cs.RO↗
arXiv2026

SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs

A robot sent to a named gas leak must preserve gas identity, estimate the source, and navigate to the resulting goal. We present SmellDiffusion, a simulation pipeline that represents species-specific gas zones in an open-vocabulary olfactory scene graph and shares the selected goal between classical and diffusion planners. Its key components are a peak-local geometric gate for selective source correction and diffusion-based, gas-guided trajectory generation. Among 424 unique source-wind configurations in solved flow, 28 have a concentration peak displaced more than 0.5m from the source. A source-independent geometric gate, calibrated only on the training split and evaluated at the observed peak, detects 9 of 10 held-out displacements at 0.64 precision. Gating a precomputed forward-matching correction reduces mean error on the displaced cases from 1.468m to 0.592m (60%), using matching for only 14/204 cases. All-case mean error falls from 0.205m to 0.180m. All planners receive the same scene-graph source estimate as their goal. In a controlled comparison, best-of-ten diffusion achieves mean gas exposure comparable to gas-guided A* (0.0476 versus 0.0455). A single diffusion proposal takes 41.7ms, compared with 72.3ms for gas-guided A*, although best-of-ten sequential sampling increases total runtime. Plain A* also reaches the same goal and remains the fastest and shortest-path method. Six matched Gazebo runs give mean robot-to-source errors of 0.39m for A* and 0.31m for diffusion.

cs.RO↗
arXiv2026

AgenticSwarm: Semantic Perception and Adaptive Task Allocation for Heterogeneous Multi-UAV Missions

Multi UAV missions in complex environments require the system to understand both the surrounding scene and the intent of a human operator while maintaining feasible task allocation as mission conditions change. This paper presents AgenticSwarm, an agentic framework for semantic perception and adaptive task allocation in heterogeneous multi UAV missions. An agent interprets aerial imagery and natural language instructions to construct a grounded mission representation that links perceived objects and regions with task requirements, capability constraints, and mission dependencies. This information augments a constrained task allocation process in which obstacle aware path feasibility, energy consumption, and protected return home requirements are incorporated before assignment. During execution, changes such as UAV failure, battery degradation, or task modification trigger residual mission reconstruction from the current system state, while completed work and reconnaissance progress are retained. AgenticSwarm is evaluated across five diverse Gazebo environments and an indoor real test environment, demonstrating its ability to connect semantic reasoning with constrained allocation and adaptive multi UAV mission execution. Compared with a Grounding DINO+SAM~2.1 perception baseline, the SAM3-based pipeline improves class-aware recall by 25.2 percentage points (pp) and semantic label accuracy by 29.5 pp. Ablating residual mission replanning increases mean repeated work from 0% to 61.7% and post-event recovery time by 58.6%, highlighting the contribution of adaptive replanning to mission execution.

cs.RO↗
arXiv2026

ZeroTouch: Tactile-Supervised Visual Contact Estimation for Contact-Rich Manipulation

Reliable robotic grasping benefits from estimating the evolving physical interaction and selecting a grasp-dependent compression target. Tactile sensors provide direct interaction measurements but require dedicated hardware at deployment. We introduce ZeroTouch, a tactile-supervised framework that predicts dense contact deformation, the instantaneous six-axis wrench, and a grasp-dependent desired compression target from wrist RGB observations, gripper state, and local gravity direction. Tactile measurements are used only as privileged supervision during training and are not required at deployment. On the full validation set, the complete architecture reduces normal-force MAE from 2.017 N for a state-only baseline to 0.531 N. In physical evaluation with 20 trials per condition, ZeroTouch achieves 95% success on an unseen object, 80% in a seen-object/unseen-grasp condition, and 90% under a content/load shift. Under the same evaluation protocol, OpenVLA achieves 25%, 40%, and 55%, while SmolVLA achieves 10%, 25%, and 35%, respectively.

cs.RO↗
arXiv2026

AcousticDiffusion: Semantically Conditioned Audio-Guided Diffusion Policy for Search-and-Rescue Assistance

Navigating toward human callers is an important capability for rescue robots operating where visual contact is degraded or occluded. We present AcousticDiffusion, a semantically conditioned, audio-guided diffusion policy for human-directed navigation. A frozen pretrained audio recognizer processes 10.24 s windows, with speech gating and distress-aware prioritization converting recognition outputs into source-level navigation roles. Microphone-array direction-of-arrival measurements are recursively integrated into a robot-centric Bayesian bird's-eye-view belief field. Ego-motion compensation aligns successive observations, progressively constraining source position while preserving bearing-induced range uncertainty. The semantic belief, recent acoustic observations, audio features, and robot state condition a diffusion model that generates waypoint trajectories. On a synthetic-navigation validation set using recorded audio, AcousticDiffusion achieves a mean end-point bearing error of 11.20 degrees, with 91.78% of trajectories aligned within 30 degrees of the caller. Distractor rejection ranges from 89.20% to 98.99%, and the policy favors a HELP-designated caller over a competing speaker in 91.07% of windows. Deployed online on a ZSL-1 quadruped without additional retraining, it achieves a mean bearing error of 64.9 degrees, compared with 98.2 degrees for A* and 90.4 degrees for RRT, with a mean planner compute time of 6.07 ms. Despite imperfect acoustic localization, the reported mean final source distance is reduced from 3.96 m for the classical planners using ODAS-derived (Open embedded Audition System) guidance to 2.48 m, a 37.4% improvement. These results demonstrate the framework's ability to translate uncertain acoustic observations into closer approaches to human callers.

cs.RO↗
arXiv2026

GaussAnything: Semantic Intent-Driven Refinement of Evolving Gaussian Scenes for Standalone VR

Deploying reconstructed 3D environments on standalone VR headsets are constrained by limited compute and memory, and conventional level-of-detail policies optimize for visibility without accounting for the user's explicit inspection intent. We present GaussAnything, a native OpenXR system for intent-conditioned reallocation and progressive publication of evolving semantic Gaussian+SDF scenes. GaussAnything resolves class- or instance-level queries to persistent 3D objects and reallocates a fixed Gaussian resident budget toward the selected object while retaining global context, applying incremental, stable-identity updates coordinated with the TSDF-derived mesh through a source-epoch mechanism. Across eight scenes, an object query concentrates 88-90% of the fixed client budget onto the queried object without enlarging it, on-device rendering reproduces the host render to within a small margin (up to 36.7 dB), and the standalone client renders each stereo frame at a steady-state GPU cost of roughly 10 ms within the frame budget of standard standalone panels.

cs.GR↗
arXiv2026

CONTHER: Context-Aware Reinforcement Learning for Robotic Manipulation with Sparse Rewards

This paper investigates whether sequential context improves goal-conditioned Reinforcement Learning in sparse-reward manipulation tasks. While Hindsight Experience Replay (HER) addresses reward sparsity through goal relabeling, its operation on isolated transitions limits its ability to capture temporal dependencies inherent in joint-space control. We hypothesize that incorporating motion history can enhance policy learning and introduce CONTHER, which integrates a Transformer-based architecture with a modified HER replay buffer. The Transformer encodes sequences of prior states and goals to provide temporal awareness, while the buffer populates experience with artificially successful trajectories. Two architectural variants are analyzed to examine how contextual information should be integrated. In simulated point-reaching tasks with a UR3 manipulator, CONTHER achieves a 38.46% higher average success rate compared to baselines and outperforms the strongest baseline by 28.21%, with faster convergence and more stable learning. The framework is further evaluated on three dynamic tasks requiring complex trajectory following and obstacle avoidance, where temporal context is critical. By operating directly on joint velocities, the approach provides a foundation for transfer to physical systems. The primary contribution is a systematic investigation into fusing sequential context with goal relabeling, offering insights into how temporal awareness benefits policy learning.

cs.RO↗
arXiv2026

Output-Level Regularization Eliminates the Seed Lottery in Single-GPU VLA Fine-Tuning

Fine-tuning a vision-language-action model (VLA-JEPA) on a single GPU should be simple: load a pretrained checkpoint, run training, deploy. There is a hidden danger. Run the same fine-tuning code thirteen times -- same data, same architecture, different random seed -- and twelve runs produce a robot succeeding 91--94% of the time, while one run silently degrades to 65.2%: a 29 pp gap with no error message, no warning, and no way to predict which seed will fail. We call this the seed lottery. We trace the cause to output collapse: the action predictor quietly learns to produce nearly identical outputs regardless of what the robot sees. Existing weight-level methods (L2, EWC) are structurally blind to this collapse -- they penalize weight changes, but collapse occurs in directions weights can move freely without affecting outputs, a gap we formalize via the Jacobian null-space. Across 7 methods x up to 13 seeds x 3 LIBERO benchmarks, three output-level regularizers -- VICReg (n=12 seeds), Dropout (n=4), and a halved learning rate (n=5) -- each eliminate every catastrophic seed (0/21 combined collapses vs. 1/13 Baseline; F(12,11)=28.7, p<0.001), while weight-level methods (L2, EWC) preserve the lottery. The simplest fix is changing one number in your optimizer config.

cs.RO↗
arXiv2026

UltraArUco: A Lightweight Multilingual Library And Framework With Low-Latency Real-Time Marker-Based Tracking System For Mobile AR Interaction

UltraArUco is a lightweight multilingual library and framework for low latency, realtime marker-based tracking in mobile augmented reality. Unlike standard OpenCV-based implementations, UltraArUco introduces an optimized multilingual wrapper that reduces per-frame latency in six times, while maintaining high accuracy. Distributed Wi-Fi architecture provides portability, connects a mobile device (camera input) with a PC-based visual application, enabling responsive interactions. The framework is validated through an interactive piano simulation, where static ArUco markers on keys enable occlusion based note triggering, and hand-mounted markers provide spatial gesture recognition. UltraArUco's system requirements make it highly suitable for resource-constrained mobile AR applications, demonstrating a viable AR music application without specialized equipment.

cs.HC↗
arXiv2026

CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain

Reconstructing dense 3D scenes from sparse LiDAR point clouds (LiDAR scene completion) is a fundamental challenge in autonomous driving, where diffusion models offer a promising solution. However, existing approaches rely on object-level autoencoders that collapse into unstable global representations at outdoor scale, and suffer from ground truth data corrupted by odometry drift that systematically degrades supervision quality. Furthermore, multi-step diffusion inference incurs prohibitive latency for real-time deployment. We present CloudDiffusion, addressing these issues with three independent components. First, a multi-token Gaussian VAE with cross-attention pooling provides stable scene-scale LiDAR compression as a standalone reconstruction module, avoiding the global-pooling and codebook-collapse failure modes of prior point-cloud autoencoders. Second, an anchor-based ICP ground truth refinement pipeline eliminates drift-induced noise from training supervision, reducing our single-step x0 diffusion teacher's squared Chamfer distance by approximately 16x on SemanticKITTI seq. 08 (0.396 to 0.024 m^2) with no model change (partly aided by the denser, more compact refined references). Third, the same teacher completes scenes in a single x0 step, operating directly in coordinate space, not in the VAE latent. It runs in near real time at 209ms/frame, 65-138x lower inference latency than iterative diffusion baselines. Our results indicate that data quality dominates model design in this regime, and suggest that multi-token latent spaces could serve as a stable first stage for future latent diffusion-based scene completion.

cs.CV↗
arXiv2026

GeminiPainter's sequence-formed pipeline comprised of perception, cognition, planning, and action stages

We present an autonomous robotic portrait-generation system combining real-time face detection, AI-based sketch generation, and robotic drawing. The system captures video frames, extracts facial regions, converts them into minimalist single-line sketches using the Gemini Vision API, optimizes stroke order through graph-based path planning, and executes smooth trajectories on a 6-DoF collaborative manipulator. This perception-cognition-action pipeline integrates computer vision, neural artistic abstraction, motion optimization, and robot control. User ratings on a 5-point scale were high for sketch quality 4.33, perceived execution 4.53, and user experience 4.65, indicating recognizable, appealing, and engaging robotic portraits.

cs.RO↗
arXiv2026

SpaceVLA: Spatially Grounded VLA for Robotic Manipulation with User-Authored Grasp and Place Anchors

Vision-language-action (VLA) models follow language commands but often lack explicit spatial intent for manipulation. We present Visual Intent Anchors, an XR pipeline that lets users specify grasp and placement regions and renders them as image-space overlays for VLA control. We collect 200 Unity pick-and-place demonstrations and fine-tune OpenVLA-7B with LoRA on temporally subsampled annotated observations. The policy predicts tokenized 7-DoF incremental actions from marked RGB observations and language. We evaluate the policy in closed-loop Unity trials, achieving a grasp success rate of 91.25% and mean grasp and placement errors of 0.5 cm and 0.7 cm, respectively.

cs.HC↗
arXiv2026

HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing

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.

cs.RO↗