Video diffusion models provide a source of interaction representations for robot control, but transferring these representations requires reconciling variable camera inputs with heterogeneous action interfaces and closed-loop execution. We present X-World, a framework that transfers a video prior through a fixed-length token sequence to a shared action expert. A residual cross-view attention branch extends a pretrained video backbone to one, two, or three views while retaining its original self-attention path. A layer-aligned Q-Former aggregates backbone features, and dataset-specific modules map between native state and action interfaces and the shared action expert. Training separates video adaptation from action-only pretraining by freezing the video backbone in the latter stage, followed by joint target-domain post-training. The policy extracts video features with a single backbone pass and uses asynchronous action chunking for execution. On LIBERO, X-World reaches 98.5\% mean success; its LIBERO-trained checkpoint obtains 76.5\% on LIBERO-Plus without further adaptation. The seven-shift breakdown reveals gains in robot, language, lighting, and layout perturbations, alongside weaknesses under camera, background, and noise shifts relative to OpenVLA-OFT. On six dual-arm real-world tasks, it achieves 81.7\% mean success over 20 trials per task. Removing video adaptation or cross-view fusion produces the largest observed success drops among the tested removals.
https://arxiv.org/abs/2610.34105
Safe indoor operation requires autonomous tracking of objects that are not directly visible to the robot. Optical non-line-of-sight (NLoS) methods depend on ambient lighting and scene geometry or on weak multi-bounce returns that need long acquisitions. Millimeter-wave (mmWave) radar offers an attractive alternative: walls act as reflectors for mmWave signals, and frequency-modulated continuous-wave (FMCW) radars enable fast, practical measurement of range, angle, and velocity. However, the low resolution of these radars leads to spatially ambiguous observations. The Doppler information, although particularly sensitive to target motion, remains underexplored in indoor NLoS localization: existing methods emphasize spatial representations and either collapse or discard the Doppler dimension before learning. To leverage the complete Range-Azimuth-Doppler (RAD) information, we acquire the first indoor NLoS radar dataset that pairs sequential RAD measurements with synchronized position and velocity ground truth under controlled variations in motion: 576 sequences totaling 720,856 frames across 12 trajectories of a mobile robot moving along varying speeds, starting positions, and material configurations. We then formulate NLoS tracking as sequential position-velocity estimation rather than frame-wise localization: a shared 3-D encoder processes the full RAD representation of consecutive frames, separate recurrent branches estimate position and velocity, and post-inference refinement combines the two into a motion-consistent trajectory. Our method achieves 8.95cm position and 1.75cm/s velocity errors on held-out trajectories and generalizes to unseen scenarios involving a moving human target. Together, our dataset and tracker establish a benchmark for tracking hidden moving targets with a low-cost radar.
https://arxiv.org/abs/2610.34085
The simultaneous surveillance and containment (SSC) problem arises in multi-robot applications such as perimeter security and environmental monitoring, where robots must survey a region of interest and coordinate to enclose targets once they are detected. Surveillance favors spatial dispersion for coverage, whereas containment requires target-centric cohesion for enclosure. This conflict makes heuristic switching unstable, and the instability becomes more pronounced as larger robotic networks introduce more inter-agent and agent-target relations. End-to-end DRL reduces reliance on hand-crafted switching, but conventional single-stream policies often mix surveillance and containment cues in one shared feature space that could entangle dispersion-oriented and target-centric signals and weaken task transitions. In this paper, we propose the Dual-Stream Gated Network (DSGN), an architecture designed to address scale-amplified task-transition difficulties by separating surveillance and containment into specialized representation streams and coordinating them through a context-aware gating mechanism. A probabilistic prior further regularizes the gating process, reducing ambiguous intermediate decisions and supporting clearer behavioral transitions under large-scale interaction complexity. Evaluations show that DSGN maintains strong task efficacy and scalability under constant-density cross-scale settings. Additional ablation and phase-specific evaluations show that the proposed dynamic gating mechanism and probabilistic prior support effective task arbitration and reliable mode switching in both pure surveillance and task-switching scenarios. The source code is available at this https URL.
https://arxiv.org/abs/2610.34084
Construction robots operating near workers require navigation that can anticipate human motion while remaining robust to dynamic and unstructured site conditions. However, existing social navigation methods depend on hand-crafted interaction rules, labeled demonstrations, or robot-specific control policies, limiting their scalability and transferability in construction environments. We propose a real-time, LiDAR-only framework that learns interaction-aware path corrections from unlabeled demonstrations. Constant-velocity extrapolation generates residual learning targets, while a GNN models relationships among the robot, pedestrians, and goal context. During deployment, an extended Kalman filter tracks LiDAR detections to construct dynamic graphs, and the GNN offsets planner-generated waypoints through a planner-agnostic interface. Within the bricklaying trial, the GNN reduced path irregularity by 39.2\% and increased minimum TTC. Across Dynablox sequences, it increased minimum TTC by 38.3\% while producing shorter, smoother paths than the baselines. Ablation studies supported a 1.0-s prediction interval and confirmed the benefits of target context, reflection augmentation, and feature normalization.
https://arxiv.org/abs/2610.34060
Swarm robotics enables scalable inspection through collective perception, where robots infer environmental properties from distributed observations. A common benchmark considers robots exploring black-white tiled environments and determining the majority tile type. While most work studies static environments, dynamic environments remain underexplored. We study collective perception in dynamic environments where the tile proportion and the spatial correlation of surface patterns may change over time. To enable implementation on resource-constrained robots, we integrate a lightweight change detection mechanism into a Bayesian collective decision-making framework that resets robot beliefs when distribution shifts are detected. The proposed detector requires constant memory and constant per-sample computation, unlike two recent competitive approaches that store the full sample stream, making it suitable for memory-constrained robots. We further introduce a method that detects spatially correlated sampling and adapts sampling intervals online to mitigate correlation effects. Our simulation results in Webots show competitive change detection delays, more consistent precision across communication settings, and improved decision accuracy under changing spatial correlations.
https://arxiv.org/abs/2610.34059
This paper proposes a command-aligned sampling distribution that incorporates navigation commands directly into the exploration process to improve the efficiency of sampling-based motion planning for quadcopters in three-dimensional environments. Inspired by the Language-Aided Subset Sampling Motion Planner, this paper extends command-aware subset sampling to aerial systems. Subset sampling is generalized to command-aligned regions, enabling structured 3D exploration while preserving probabilistic completeness. Natural language instructions are grounded into yaw-conditioned and altitude-aware geometric constraints using a prompt-based large language model for entity extraction and instruction validation. Extensive simulations in complex environments demonstrate that the proposed method generates collision-free, consistent trajectories while significantly reducing sampling effort compared to uniform RRT-based planners.
https://arxiv.org/abs/2610.34054
Robot tasks require grounding spatial language in physical scenes, but task success alone cannot establish whether spatial instructions are followed. We present BEHAVIOR-Spatial, a benchmark built on BEHAVIOR-1K that measures spatial question answering, point-based target grounding, and robot action to examine how VLM spatial understanding relates to VLA behavior. It comprises 3,256 spatial questions across 49 activities, 1,240 grounding queries across 14 manipulation tasks, and action evaluations covering those 14 tasks and 10 navigation tasks. Our manipulation protocol evaluates held-out configurations and instruction following when the requested target changes within a fixed training layout. The baseline achieves 41.6% on held-out configurations but only 16.1% under changed instructions. VLM adaptation and robot-data pretraining provide limited improvements, whereas oracle visual target cues raise these rates to 60.3% and 38.0%, respectively. Perception evaluations reveal policy-dependent correlations between VLM question-answering and grounding accuracy and VLA manipulation performance. Together, these findings motivate evaluating spatial instruction following alongside task completion and examining when spatial perception performance translates into robot behavior. Project website: this https URL.
https://arxiv.org/abs/2610.34051
Dynamic and continuously evolving environments present significant challenges for robotic mapping and scene understanding, particularly on construction sites where moving agents, temporary obstacles, and persistent structural changes coexist. While dynamic and long-term SLAM methods can detect motion and environmental changes, their outputs are predominantly metric representations that provide limited structure for higher-level spatial and temporal reasoning. This paper presents a LiDAR-based real-time temporal construction scene graph (T-ConSG) that jointly represents free-space regions, static objects, dynamic objects, and environmental events with spatial-relational and event-participation edges. The proposed framework incrementally constructs the graph from LiDAR-derived geometric evidence, maintaining persistent free-space and static-object information while tracking dynamic objects. Changes in accumulated spatial evidence are further represented as explicit installation and removal events, allowing the graph to capture both transient dynamics and persistent environmental evolution. We demonstrate the proposed representation through three complementary application studies: dynamics-aware navigation in a bricklaying testbed, construction progress monitoring on the ConSLAM dataset, and online change detection in a simulated construction environment. The results demonstrate that the proposed T-ConSG provides a unified representation for organizing spatial and temporal information and supports robotic reasoning across environments containing both short-term dynamics and persistent changes.
https://arxiv.org/abs/2610.34041
Construction robots must label building elements they can only partly see. We show that when occlusion at test time removes whole regions of a scene, rather than parts of an object as in training, point-cloud segmentation networks do not simply miss the hidden elements: they relabel them, and the errors collapse onto a single sink class. With fixed synthetic layouts the column absorbs up to 70% of all test points; with randomized layouts the sink moves to the stair, predicted at 4.5-5.4x its true share across three training seeds. Baseline mIoU falls to 0.15-0.27 (fixed) and 0.36-0.72 (randomized), and up to 269 whole objects vanish in a single test set. Appending 14 hand-computed geometric features per point (GPE) restores mIoU to 0.54-0.92 and removes 64-100% of whole-object losses in every run, for PointNet++ and a PTv3-style transformer in both layout regimes; on real S3DIS scans it removes every whole-wall loss (10 to 0). In an as-built column check computed from the predictions, GPE raises the share of correctly checked views from 17-58% to 71-92%. Feature permutation on fixed, randomized and real scenes explains the pattern: each class relies on whichever cue is stable in its training data, position for height-banded slabs and beams, intrinsic shape for walls and stairs once their position varies. Occlusion augmentation is a strong alternative on mIoU, but in every setting it loses more whole objects than GPE (e.g., 25-35 vs. 0).
https://arxiv.org/abs/2610.34040
WiFi Channel State Information (CSI) enables fine-grained sensing of spatial relationships between wireless devices. The WiFi Sensor for Robotics (WSR) toolbox demonstrated that WiFi-CSI measurements collected during robot motion, combined with odometry, can be used to synthesize virtual antenna arrays, enabling motion-induced bearing estimation in multi-robot experiments. However, deploying the WSR approach has remained challenging due to its limited integration with standard robotics tools and reliance on deprecated WiFi-CSI acquisition hardware. This work presents an open-source simulation framework that integrates the WSR sensing pipeline within the robotic simulator Gazebo. The framework generates synthetic WiFi-CSI measurements with realistic physical signal properties and leverages realistic robot motion required for motion-induced sensing and downstream localization. It further supports processing both simulated and real WiFi-CSI data for direct comparison and validation. Our aim is to make WSR-style sensing accessible as a modular sensing modality for robotic research. We validate our framework by comparing simulated and real-world experiments using TurtleBot3 robots, and demonstrate its use for bearing estimation and robot localization. This work lowers the barrier to entry for WiFi-CSI-based sensing in multi-robot systems and provides a foundation for integrating WiFi-CSI sensing with multi-modal perception for localization and coordination. All code and experimental details are publicly available at this https URL
https://arxiv.org/abs/2610.34034
Robots that learn from people often see several valid ways to do the same task: pass an obstacle on the left or on the right, open the microwave or move the kettle first. A policy that re-decides at every step can waver between these ways mid-task. We ask when the action head (the part of a policy that turns the state into actions) matters, and how it should make this choice. On a controlled task, heads that sample one way succeed far more often than a head that averages the ways when the demonstrations contain several ways and the state gives no hint which to take (+0.72 success with two ways); this trend was not reproduced on the other tasks we ran. We then present ElevateHead, a head that decides once at a learned decision point, commits to that choice for the episode, and exposes the choice as an input a user can set. We designed it by diagnosis: each version was frozen and tested on tasks it had not seen, and the next version changed only what a measured failure pointed to; predictions were registered before each run. The first four versions each fell below BeT on at least one held-out task. The fifth completed all four subtasks of the held-out Franka Kitchen task in 45.2% of episodes against 29.3% for BeT, the strongest baseline across our tasks (+0.160, 95% CI [+0.129, +0.188]); when a mode was forced, the first completed subtask matched it in 95% of successful episodes. Diagnosis also located where commitment breaks: varied start positions (repaired on the controlled task: commitment 0.22 to 0.81, success 0.74 to 0.91) and varied object placement (partly repaired: in an exploratory variant, commitment 0.03 to 0.59 on aligning with no detectable change in success). On held-out block stacking, version 4 was comparable to BeT and did not exceed it. A real-robot test with predictions fixed in advance is planned for a follow-up version of this paper.
https://arxiv.org/abs/2610.34031
Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test-time scaling offers an efficient alternative by sampling multiple action candidates and selecting the one most likely to lead to task success at inference time. Existing classification-based verifiers learn from trajectory-level outcomes but treat all visited states equally, even though their value for candidate discrimination can vary across a trajectory. At many states, plausible actions are similar and provide limited discrimination signal, while only a sparse set of decision-critical states admits meaningfully different actions that can substantially affect downstream outcomes. To address this, we propose DiVeR, which estimates decision criticality from the dispersion of sampled action representations. DiVeR then uses this signal to reweight verifier learning toward states where action selection is most consequential, without requiring step-level annotations or additional environment interaction. Across LIBERO, RoboCasa, and real-world experiments on a Franka Research 3 robot, DiVeR consistently improves task success through more effective verifier-guided action selection, while adding negligible verifier inference overhead.
https://arxiv.org/abs/2610.04933
Long-horizon manipulation often depends on object properties that cannot be reliably inferred from appearance alone. Physical interaction can reveal these properties, but it can also change the world in ways that invalidate subsequent actions. We present a task and motion planning (TAMP) framework that integrates task-directed interactive information-gathering with interleaved planning and execution. Building on PDDLStream, our framework plans optimistically with these interactive actions, verifies their outcomes during execution, and adapts the remaining plan by retaining still-applicable actions and replanning only the connections needed to continue execution. We evaluate the framework in simulation and on a real robot across tasks that require determining whether an object is movable, a pen has ink, a drawer can be opened, or a container is empty. These experiments demonstrate how interaction-driven state updates and recovery replanning support continued execution under uncertain outcomes and external disturbances.
https://arxiv.org/abs/2610.33959
Bimanual robotic control requires simultaneous management of distinct functional demands under motor noise, energetic costs, and communication delays. We investigate how learning responsibility should be organised across modular controllers and the two arms in a simulated musculoskeletal system with two communicating recurrent controllers. Using a 2 x 2 design, we compare differential versus shared controller objectives and fixed versus balanced hand-task assignments. Task-aligned functional specialisation was strongest when differential objectives were combined with a fixed assignment aligned with contralateral control routing. This condition achieved the highest canonical-task performance and control efficiency, reaching 81.33% bimanual success. Its advantage over shared objectives increased with motor noise but narrowed under stronger energy penalties. Stronger specialisation also reduced hand-role flexibility: reversing the hand roles decreased bimanual success by 80.46 percentage points under Differential-Fixed training, compared with 1.51 percentage points under Shared-Balanced training. These results show that controller objectives and hand-task experience jointly determine functional organisation. Stronger role-specific specialisation favours performance and efficiency when roles remain stable, whereas more distributed training favours interchangeability when roles change.
https://arxiv.org/abs/2610.33947
Predicting the short-term future trajectory of a person from RGB-D cameras is a key capability for mobile robots navigating in dynamic and human populated environment. The key challenge to deploying learned predictors on real robots is the train-deploy pipeline gap. Training data are often prepared with an idealized, smoothed ground truth, whereas at inference, the model is fed noisy estimates from pose detectors and depth sensors. The model is therefore evaluated on an input distribution it never encountered during training. Most existing models rely on recurrent neural networks (RNNs) or transformers, which either struggle to capture short-term temporal dependencies or suffer from computational cost. We present TrajMamba, a lightweight, bidirectional state space model for short-term human trajectory prediction using an RGB-D camera. The model uses a single shared processing path for both training and deployment, aligning human pose extraction, depth back projection, and smoothing processes. It encodes a short window of persons's hip center velocities with stacked bidirectional Mamba blocks and decodes future velocities with a GRU head. On the ETH/UCY benchmark, TrajMamba reaches an average ADE of 0.29 m FDE of 0.51 m. With 262K parameters, it runs in real time on modest hardware and is deployed on a TIAGo robot with an onboard NVIDIA Jetson Orin.
https://arxiv.org/abs/2610.33916
When a team of drones explores a building together, each drone tells the others which frontier it is going to and shares the map it has built. This avoids duplicated effort, but it also means that the team trusts every identity from which it receives messages. In a Sybil attack, one compromised drone creates fake identities, and these fake teammates claim frontiers and send fabricated scans, so the real drones leave parts of the building unexplored and end up with walls in their maps that do not exist. We study five such attackers, including one that seals off the openings between floors, and five levels of defence that need no security infrastructure, only the drones' own sensors and maps: an audit of received map data against what a drone sees itself, a check that a body is present where an identity claims to be, trust only for identities whose body has been seen, a quarantine for identities that no drone has observed, and a rule that binds each observed body to one identity. Tests in simulation cover 70 maps of seven kinds, from offices and tunnels to three-storey buildings and caves. Without a defence, one compromised drone leaves on average up to 25% of a map unexplored (45% in offices), and the floor-sealing attacker cuts the explored part of a three-storey building to 82.3%, or 34.6% on the worst map. The quarantine brings exploration back to the level of an unattacked team in every setting, and in most settings it also brings the false data back to that level. The exceptions are two colluding attackers, fakes placed next to real drones, three of the ten caves and a team of 16 drones, and binding bodies to identities fixes the last three. Over 2,350 missions, an honest drone was revoked by a teammate only twice.
https://arxiv.org/abs/2610.33906
Long-horizon manipulation requires actions whose validity depends on earlier interactions, yet visual progress can conceal missing task prerequisites. We propose RoboLongR, an offline-to-online framework that learns history-dependent rewards to guide policy adaptation to new tasks. Its central objective is causal consistency: aligning rewarded progress with prerequisites supported by execution history. Stage-shuffle supervision encourages execution-order sensitivity, recurrent memory preserves evidence of earlier interactions, and two-round training refines trajectory segments using predicted progress. The resulting rewards guide stage-conditioned policy refinement from behavior cloning to online reinforcement learning. Sparse terminal feedback connects policy experience to reward learning by triggering correction for repeated high-scoring failures. Pretrained on demonstrations from 88 RLBench tasks and Open-X data, RoboLongR achieves 31.8% average success on 18 long-horizon tasks excluded from reward pretraining, exceeding the strongest evaluated baseline by 9.2 percentage points. Across four real-robot tasks, it achieves 57.5% success, a 32.5-percentage-point improvement over the comparison method. Reward-level controls probe sensitivity to synthetic order perturbations, while ablations examine the contributions of individual components to policy improvement.
https://arxiv.org/abs/2610.33863
Distributed Cyber-Physical Systems (CPS) and Edge AI networks increasingly depend on public-key authentication and key-establishment mechanisms that are vulnerable to cryptographically relevant Quantum Computers (QC). Shor's algorithm threatens widely deployed asymmetric primitives, while Grover's algorithm reduces the effective security margins of symmetric and hash-based mechanisms. Although Post-Quantum Cryptography (PQC) provides a migration path, its larger public keys, ciphertexts, and signatures introduce additional computation, memory, communication, storage, and packet-fragmentation costs that can constrain dynamic multi-agent systems. In this article, we introduce rotational secrecy, an architectural objective that limits temporal key exposure through authenticated transitions between cryptographic epochs. We present Private Authentication for Rotational Secrecy (PARS), a reference mechanism that coordinates policy-triggered key establishment, rotation, and reconciliation among authorized Physical AI agents. For deployments that need distributed agreement on security state, we further develop the PARS-Enabled Edge Security Ledger (PARS-ESL), an optional permissioned architecture maintained by authorized validators or capable edge gateways. PARS-ESL does not store high-volume operational transactions. Instead, it records authenticated state for key epochs, group membership, revocation, algorithm-suite policies, challenge validation, and recovery checkpoints. As a result, resource-constrained agents can take part as lightweight clients, and low-latency operational traffic stays outside the ledger consensus path, protected by the currently active symmetric epoch keys. Our results show that ledger-assisted post-quantum key-epoch management is feasible for selected Edge AI and CPS security-control workloads under the stated trust, compromise, connectivity, and resource assumptions.
https://arxiv.org/abs/2610.33862
Language is a natural way to command robots, but converting a single instruction into a long-horizon, contact-rich hand-object interaction remains challenging: synthesized references are noisy, human-to-robot retargeting introduces embodiment bias, and fixed-reference tracking lets small errors snowball. We address this with AdaDexTrack, a modulator-in-the-loop framework for language-conditioned manipulation tracking. A distilled generalist tracker serves as the skill carrier, while a tightly aligned modulator performs three feedback corrections: reference modulation (continual adjustment of what to track), object-latent modulation (online adaptation of the object representation to recruit suitable skills), and positional-target modulation (small state-dependent refinements for execution). The tracker is learned via large-scale specialist to generalist distillation on a corpus of language-conditioned hand-object trajectories; the modulator is trained with RL under the same task objective, ensuring tight coupling. Across large-scale evaluations, AdaDexTrack consistently outperforms prior SOTA on unseen-trajectory and unseen-object sets in both average tracking error and success rate, demonstrating robustness and generalization. We further show zero-shot sim-to-real transfer on real hardware, where adding the modulator yields substantial gains over a tracker-only variant. AdaDexTrack reframes language-conditioned dexterous manipulation as modulated tracking, replacing the open-loop, fixed-reference tracking with in-loop modulation that adjusts the reference, object latent, and positional target, yielding drift-resistant execution from noisy text references.
https://arxiv.org/abs/2610.33852
Video world models (VWMs) are rapidly emerging as scalable neural simulators for robotic manipulation. However, most benchmarks only evaluate them as open-world video generators, using Vision-Language Models (VLMs) that lack strict 3D spatial and kinematic reasoning. To bridge this gap, we introduce RoboWorM, a comprehensive, deployment-aware benchmark that leverages known hardware priors such as robot kinematic trees and fixed camera configurations, to systematically examine structural and spatiotemporal fidelity. RoboWorM curates 1,605 episodes across single-arm, bimanual, and humanoid morphologies, spanning both Markovian and long-horizon non-Markovian tasks under single- and multi-view setups. To explicitly measure physical consistency, we propose two deterministic, VLM-free metrics: KIVA for intra-view kinematic stability, and RIGIS for multi-view geometric consistency. By exploiting intrinsic robotic invariants, KIVA improves hallucination detection alignment with human annotations by 25.8% relative to the strongest frontier VLMs, while RIGIS achieves a 130% higher Spearman correlation with human preferences. Furthermore, since real-world deployment requires low inference latency, we utilize RoboWorM to conduct the first large-scale audit of the quality-efficiency trade-off. Evaluating 9 state-of-the-art acceleration techniques across 3 leading world models (over 29,000 generated rollouts), we demonstrate how these acceleration methods can retain superficial visual quality while silently compromising deployment-critical physical constraints. Using our metrics, we achieve 2.3$\times$ maximum inference speed-up with minimal quality loss.
https://arxiv.org/abs/2610.33807