arXiv_RO
-
Generate, Track, Improve: Perceptive Multi-Skill Humanoid Locomotion with RL-Fine-Tuned Motion Generators
2026-09-25 17:38:23Zachary Olkin, William D. Compton, Aaron D. AmesAbstract
General purpose humanoids require locomotion controllers that are multi-skill, perceptive, dynamic, and robust enough to go anywhere humans can. In this work, we present a two layer locomotion architecture: (1) a perceptive flow matching motion generator plans whole body trajectories from raw depth images while a (2) perceptive tracking policy trained with control-guided RL follows these motions. Both policies are trained on a library of terrain consistent motion clips created with dynamically optimized human data which yields both accurate velocity tracking and terrain consistent references. Our central contribution is a simple yet effective off-policy RL fine tuning loop that improves the motion generator. A structured search method is used with the generator to gather data for advantage weighted regression. This off-policy loop is much more sample efficient than on-policy residual fine tuning and improves terrain consistency on unseen geometries and skill compositions. We find that successful terrain traversals increased by up to 25 percentage points and skill selection improved by up to 80 percentage points. By using raw depth images to perceive the environment no odometry or height maps are needed, and outdoor deployment is easy. With two cameras, the policy can see terrain coming from further away and adjust its velocity regardless of the commanded speed so it can traverse the terrain. A single policy pair enables a Unitree G1 humanoid to walk, run, stand, jump on and off of boxes, and traverse stairs in outdoor environments. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.31577
PDF
-
Learning to Leverage Compliance: A Policy-Admittance Learning Framework for Robotic Insertion
2026-09-25 15:58:13Chongren Wang, Minghe Li, Honghua Dai, Zhicheng Lin, Shiyang Wei, Xiaokui YueAbstract
Policy learning and compliant control offer a promising route to reliable autonomous assembly under pose errors and contact uncertainty. However, combining them does not ensure coordination: the policy may continue pushing against contact while the controller yields, producing sustained loading with limited progress. To address this problem, we propose LeCo (Leverage Compliance), a policy-admittance learning framework that guides a visual policy through execution-time interaction under fixed admittance. A multirate feedback mechanism aggregates high-rate contact-interaction records into policy-transition rewards. An integrated conflict cost then characterizes sustained policy-loading/controller-unloading opposition, while a directional high-force tail cost captures continued-loading events within a transition. Together with task completion, these costs encourage the policy to leverage compliance with less unproductive loading. We evaluate LeCo on four real connector-assembly tasks, obtaining an aggregate success rate of 94%. Across tasks, mean successful-trial resultant-force and torque peaks decrease by approximately 30% and 64% relative to the comparison baseline. Reward ablation further shows that adding conflict shaping reduces median successful-trial contact-conditioned conflict density by approximately 53%. These results support learning to leverage fixed compliance by turning multirate policy-admittance interaction into complementary reward signals for effective, lower-load insertion.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31439
PDF
-
ExoLaN: Physics-Consistent Context-Aware Dynamics Learning for Exoskeletons
2026-09-25 15:55:39Lucas Schulze, Maximilian Schwarz, Jona Hoppe, Jan Peters, Oleg ArenzAbstract
Task-agnostic assistive exoskeleton control based on human intention offers greater flexibility than conventional approaches that rely on predefined tasks or motion patterns. Human joint torque estimation enables task-agnostic assistance by characterizing user actions. Physics-consistent methods such as Deep Lagrangian Networks (DeLaN) have been applied to estimate the human torques in multi-user settings, but existing approaches cannot adapt to a specific user without retraining, and do not account for intermittent contacts during locomotion. We propose ExoLaN, a Context-Aware DeLaN for human-exoskeleton interaction that learns the full coupled system dynamics while adapting to changes in interaction context. ExoLaN combines temporal context with partial contact-force measurements from force-sensitive insoles to infer latent dynamics embeddings and estimate generalized contact torques. On seven unseen users performing 21 unseen tasks, ExoLaN reduces torque estimation MSE by 7% compared to a black-box baseline. Beyond inverse dynamics, ExoLaN serves as a unified model that also enables accurate forward prediction: training with a multi-step prediction loss reduces acceleration MSE by 59% and long-horizon position and velocity errors by 60% and 93%, respectively, compared with a single-step loss. Moreover, the learned latent context captures task information without explicit task labels, making it a promising signal for task-aware assistive control.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31434
PDF
-
CognitiveReality: Robot-Agnostic Semantic Gaussian Mapping with an LLM Agent for Immersive Collaborative VR Teleoperation
2026-09-25 15:39:28Timofei Kozlov, Dmitrii Maliukov, Andrey Marchenko, Dmitrii Plotnikov, Miguel Altamirano Cabrera, Dzmitry TsetserukouAbstract
A photorealistic 3D view tells a teleoperator where a robot is, but not what the scene contains, how well each object has been observed, or how to turn pointing and speech into robot action. CognitiveReality turns a robot's RGB-D stream into a live, semantically indexed Gaussian-TSDF map shared by an operator in virtual reality and a tool-using language agent. One mapper binary serves any platform through configuration alone: it ingests poses from robot SLAM, joint kinematics, motion capture or an inline visual tracker, bridges localization outages with a shadow tracker and keyframe-anchored PnP, and maintains open-vocabulary instance identities with per-object quality at 2 Hz. Speech and controller rays are grounded against persistent scene objects through validated typed tools and operator-confirmed robot actions. In the controlled agent evaluation, the deployed local Qwen3-VL-8B router reaches 81.24\% tool exact match, while merge-aware replay correctly redirects 101 absorbed object identifiers. On robot data CognitiveReality exceeds a Gaussian-plus-SDF baseline by 2-8 dB; pose error through 5-40 s SLAM outages stays within 1-8 cm. Deployed live on two quadrupeds, the agent executed 26 of 30 navigation requests and 20 of 20 re-observation requests, raising object quality by 2-5 dB.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31418
PDF
-
dRVG: Quadtree-Guided, Resolution-Complete Online Motion Planning for Polygonal Robots in Unknown Environments
Abstract
We present the dynamic rotation-stacked visibility graph (dRVG), an online motion planner that guides polygonal robots to specified goals in initially unknown, static environ- ments. It merges local roadmaps from successive observations to plan collision-free translations and rotations without a uniform position grid. A spatial quadtree schedules sensing goals across regions to reduce repeated visits while retaining all orientation configurations for routing. Under exact sensing and geometric computation and star-shaped robot and envelope assumptions, dRVG with center scans is resolution-complete relative to full- map RVG at the same angular resolution. In experiments using footprint scans, dRVG solves all 140 cases across 20 difficult maps and seven angular resolutions within a 20 s planning budget, with a median planning time of 1.18 s at 360 orientation layers. Six microMVP demonstrations illustrate the complete online planning loop on a physical robot.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31412
PDF
-
Augmented Reality Interfaces for Human-Robot Collaboration: Development of a ROS 2-Based Sensor Streaming Framework and Validation via SLAM Algorithms
2026-09-25 15:25:03Alessandro Rubert, Stefano Ghidoni, Matteo TerreranAbstract
In recent years, Human-Robot Collaboration (HRC) has taken on a central role in Industry 4.0 and collaborative robotics, demanding communication channels that are increasingly bidirectional, intuitive, and efficient. In this context, Augmented Reality (AR) presents itself as a fundamental enabling technology, capable of both displaying information to the operator and gathering spatial data about the surrounding environment. This thesis presents the development of a sensor streaming framework that connects the Magic Leap 2 AR headset with the ROS 2 (Robot Operating System) ecosystem. Using the Unity development environment and the ROSTCP-Connector package, an on-board application for the headset was developed, capable of acquiring real-time data from the integrated sensors (pose tracking, cameras, and environmental sensors) and publishing it to dedicated ROS 2 topics. In order to test the accuracy, latency, and robustness of the generated data stream, the framework was validated using SLAM (Simultaneous Localization and Mapping) algorithms known in the literature. The experimental results demonstrate that the proposed architecture ensures stable data transmission, laying the groundwork for safe real-time interaction and shared spatial awareness, and opening up new perspectives for the control and supervision of robotic systems in complex HRC scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31396
PDF
-
Modeling and Generative-AI-Based Design of Load-Adaptive Gravity Balancing Mechanisms
2026-09-25 15:18:54Ryotaro Kayawake, Kazuki Abe, Shota Miyake, Masahiro Watanabe, Kenjiro TadakumaAbstract
Load-adaptive gravity balancing mechanisms (LA-GBMs) can accommodate various loading conditions by passively changing their characteristics in response to payload variations. However, their design is difficult because both the desired mechanism motion and static equilibrium under variable payloads must be satisfied simultaneously. This study proposes a general design methodology for LA-GBMs that does not depend on specific mechanism architectures or mechanical elements. The necessary conditions for the potential fields of LA-GBMs are formulated, and two general forms are derived: an affine form representing the effect of payload mass and a factorized form representing state transitions associated with load adaptation and gravity balancing. These forms are then provided to generative AI as design requirements to generate candidate potential functions. The generated functions are analytically verified in terms of their conformity to the two general forms and the conditions required for valid LA-GBMs. Furthermore, the obtained potential functions are decomposed into individual terms, and an example of a method for constructing an LA-GBM by combining springs, counterweights, and function-generating linkage mechanisms is presented. By using potential functions as an intermediate representation, the proposed framework enables the generation of LA-GBM design candidates without prescribing a mechanism architecture in advance. Mechanical realizability and manufacturability of the generated potential fields remain important issues for future work.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31386
PDF
-
Transformer-based Monte Carlo Localization in Construction Meshes
2026-09-25 14:54:15Linus Kramer, William Talbot, Olga Vysotska, Marco HutterAbstract
To be able to perform inspection or digitization tasks, mobile robots on construction sites must be able to localize themselves reliably with respect to a global reference frame that is shared with a building map. Similar room layouts and low-texture surfaces pose a challenge for existing LiDAR- and vision-based localization methods. We approach this problem with a LiDAR-based global relocalization system that estimates the robot's pose relative to a building mesh and combines a PointNet++ encoder with a place recognition decoder, whose outputs serve as a learned observation model within a Monte Carlo Localization (MCL) framework. The pipeline is trained exclusively on synthetic LiDAR scans obtained by simulating the robot's sensors inside the building mesh. Our approach is robust in ambiguous environments due to an uncertainty-aware decoder that scales positional likelihoods and a resampling strategy that injects model hypotheses into the particle set, enabling recovery from potential particle depletion. Evaluations on real-world datasets show that our method outperforms both diffusion-based and ScanContext++ baselines while maintaining fast inference (18 ms per call), demonstrating the practicality of synthetic-data training for mesh-referenced global localization in construction robotics.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31357
PDF
-
Representation-Guided Generation and Integration of Executable Programs for Robot Manipulation
2026-09-25 14:41:24Ruixiao Yang, Mingxin Yu, Chuchu FanAbstract
Building a robotic manipulation system requires connecting perception, planning, and control through carefully designed representations and interfaces. VLM code generation offers a way to automate this construction, but independently generated components may operate on incompatible geometric and task-level information. We present Representation-guided Integration of VLM-generated Executable Task programs (RIVET), a framework for generating complete manipulation systems around a shared object-centric representation. The representation combines per-object 6D poses, which preserve the metric information required for action grounding, with a relation graph that exposes the task-level structure required for planning. Guided by this representation, a VLM generates cooperating perception, rendering, relation-inference, and planning programs, each combining task-specific computation with available packages where useful. The resulting programs are authored once for a manipulation domain and reused on unseen start and goal configurations without code regeneration. We evaluate RIVET on cube stacking, tangram rearrangement, and three-dimensional assembly in simulation and on a physical robot, where we achieve 83% overall success rate in the real world by reusing offline-generated systems. Our results demonstrate that representation-guided program generation can adapt a common manipulation framework to tasks with different geometric, relational, and sequential requirements.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31337
PDF
-
See to Reach, Feel to Grasp: Learning A Blind Grasp Reflex for Anthropomorphic Robotic Hands
2026-09-25 14:27:54Alexander Alexiev, Tzu-Yuan Lin, Sang Min Kim, Ho Jae Lee, Yonghyeon Lee, Sangbae KimAbstract
In this work we study if a robotic hand using proprioception alone can grasp diverse objects with no visual observation. We present a modular dexterous grasping architecture that separates global arm motion from local contact control. An independently controlled arm guides the hand toward the object, while a reinforcement learning policy grasps and stabilizes it using only hand proprioceptive feedback. We call this \textit{a blind grasp reflex}: grasping without images, object poses, or geometric observations. A learned stable-grasp score determines when the object is securely held, allowing the arm to begin post-grasp manipulation. This separation makes grasping a reusable hand-level skill that can be combined with independently designed arm controllers for various manipulation tasks. Experiments in simulation and on hardware demonstrate robust blind grasping across diverse objects and seamless composition with a range of arm controllers. Moreover, despite never observing contact geometry, the learned grasp score closely aligns with an independent physics-based measure of grasp stability. The resulting approach follows a simple principle: see to reach, feel to grasp. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31323
PDF
-
NAC: Neural Action Codec for Vision-Language-Action Models
2026-09-25 13:44:37Ahad Jawaid, Yu XiangAbstract
Vision-language-action (VLA) models rely on discrete action tokenizers to bridge continuous robot control and autoregressive sequence modeling, yet existing tokenizers often trade off between compression, latency, and downstream performance. We revisit this design through the lens of neural audio codecs - convolutional encoder-decoder architectures with residual vector quantization that serve as the standard front end for audio foundation models. Motivated by their success, we introduce the Neural Action Codec (NAC), which treats short robot action trajectories as multi-channel 1D signals and compresses them using a multi-scale RVQGAN architecture. With adaptations to the action representation, compression rate, and reconstruction objective, audio-codec-style models can autoencode actions with high fidelity without substantial architectural changes. NAC provides a compact, ordered token space via offset codebooks, enabling standard autoregressive policies to operate over short, structured sequences. Meanwhile, a Vocos-style decoder with an ISTFT head and adversarial discriminators recovers action trajectories. Across LIBERO-10, RoboMimic, and a suite of real-world manipulation tasks, NAC achieves high reconstruction fidelity and higher average success rates than binning, FAST, and prior VQ-based tokenizers at comparable or better compression rates. These results demonstrate that repurposed neural audio codecs offer a strong, practical backbone for learned action tokenization in modern VLAs.
Abstract (translated)
URL
https://arxiv.org/abs/2606.21372
PDF
-
Cybflight: An Embedded Rust Autopilot for Aerial Robotics Research
2026-09-25 13:10:12Yifan Lin, Chao Qin, H S Helson Go, Hugh H. -T. LiuAbstract
Bringing an aerial robotics method from simulation to flight should not require rebuilding a mature autopilot or adding a companion computer. Cybflight is an open-source embedded Rust research autopilot whose typed, replaceable interfaces connect hardware access, perception, state estimation, trajectory planning, and control. This modular development and compile-time optimization workflow is demonstrated with replaceable Rust implementations of model predictive contour-tracking control (MPCTC) and incremental nonlinear dynamic inversion (INDI) running on one STM32H743 without a companion computer. Using this configuration, the vehicle reaches 12.38 m/s during indoor flight, while an outdoor flight using global navigation satellite system (GNSS) position updates reaches 31.4 m/s. These flights show that running demanding estimation and nonlinear control entirely on a flight-controller microcontroller need not come at the expense of a modular autopilot structure.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31232
PDF
-
Imp-ACT: Adaptive Impedance Control and Action Chunking with Transformers to Learn Contact-Rich Manipulation from Demonstrations
2026-09-25 13:04:37Luca Zanetti, Doganay Sirintuna, Idil Ozdamar, Pietro Balatti, Heng Zhang, Arash AjoudaniAbstract
Contact-rich manipulation requires robots to balance accurate motion tracking with compliant interaction, yet most visual-action policies leave compliance fixed at the controller level. We present Imp-ACT, a methodologically grounded and practical approach to incorporating direction-dependent Cartesian stiffness modulation directly into demonstration collection, without manual stiffness selection or offline target reconstruction. During teleoperation, a self-tuning impedance controller adapts stiffness along the instantaneous direction of motion while maintaining compliance in orthogonal directions. The adapted stiffness is applied and recorded alongside visual observations and motion commands, capturing motion and compliance under the same dynamics. We implement this pipeline using Action Chunking with Transformer (ACT) to predict end-effector pose, gripper action, and motion-direction stiffness from visual, proprioceptive, and wrench observations. The performance of Imp-ACT is evaluated on wiping and plug insertion using both success rate and quantitative measures of contact behavior. Compared with fixed low- and high-stiffness baselines, Imp-ACT achieves comparable or higher success while maintaining low interaction forces. In wiping, it reduces contact-force vibration by approximately $29\times$ relative to the compliant baseline and $180\times$ relative to the stiff baseline. In plug insertion, it reduces forces orthogonal to the insertion direction by $43\%$ relative to the better fixed-stiffness baseline. These results highlight the benefit of maintaining sufficient stiffness along the direction needed for task execution while preserving compliance in other directions to limit contact forces and accommodate environmental constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31225
PDF
-
CoralPlan: Observation Skill Selection and Execution for Underwater Robotic Inspection
2026-09-25 12:53:55Yuer Gao, Yu Zhao, Yi CaiAbstract
Underwater robotic inspection depends on acquiring views that reveal task-relevant structure. For a structurally complex coral colony, recognising the target is only the starting point: the robot must select and execute a viewing motion suited to the inspection task. We present CoralPlan, a vision-language system that selects an observation skill from a current camera image and task text supplied by an episode manifest. A shared motion interface executes orbit, patch, or survey as target-relative trajectories; the remaining plan fields provide operator guidance. Observation completion requires target keeping and primitive-specific coverage, while joint success also requires selection to match the recorded reference. We evaluate this interface in 144 simulated episodes and 36 matched simulation-hardware pairs. In a clear-water pool with external target-reference poses, hardware observation completion reaches 77.8% and joint success reaches 63.9%. The experiments identify both reference-mismatched completions and incomplete observations after a matching skill selection. These results connect observation-skill choice to measurable underwater execution outcomes and identify where task-directed acquisition succeeds or fails.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31211
PDF
-
Onboard Wind-Preview Model Predictive Control Using Pitot-Static Sensing for Multirotor UAVs
2026-09-25 12:16:35Bas Meere, Eline Wisse, Laurens Vousten, Sander Doodeman, Elena Torta, Paula Chanfreut, Duarte AntunesAbstract
Effective wind gust rejection and stable hovering are critical for the outdoor operation of autonomous drones. However, existing gust rejection methods are primarily reactive, inferring the disturbance from the resulting motion or measuring it at the airframe. Either way, the wind has already begun to act before it can be compensated. In this work, we anticipate the gust instead by measuring the wind ahead of the drone with a low-cost, low-weight pitot-static sensor mounted on a boom. The resulting wind preview is incorporated into a nonlinear model predictive controller (MPC), which optimizes the drone motion while anticipating wind disturbances. A longer boom offers more preview time but adds inertia and degrades flight performance. We characterize this trade-off in simulation and show that the optimal preview distance is not a fixed property of the platform, but shifts with the wind speed and with how quickly the drone can respond. Indoor hardware experiments confirm the trend and show that the proposed controller substantially improves hover performance against a PX4 baseline and an otherwise identical wind-unaware MPC. Outdoor experiments show that the error along the wind direction is reduced by 54 percent with respect to the baseline, demonstrating that a single wind-aligned sensor can significantly improve hovering performance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31185
PDF
-
Evaluating the Impact of Adaptive Extended Reality on Human-Robot Interaction Across the Reality-Virtuality Continuum
2026-09-25 11:27:38Carl Tornberg, Alicia Torck, Lotfi El Hafi, Tadahiro TaniguchiAbstract
As populations in developed countries age and labor shortages intensify, Cybernetic Avatars (CAs) are proposed to extend human capabilities through robotic embodiments, requiring effective Human-Robot Interaction (HRI) frameworks. Extended Reality (XR), an umbrella term for Augmented Reality (AR), Augmented Virtuality (AV), and Virtual Reality (VR), offers such interfaces, but prior research typically fixes the XR modality without evaluating its effect on task outcomes. This study examines whether the XR modality impacts HRI performance and whether an adaptive interface adjusting the level of virtuality along the Reality-Virtuality Continuum (RVC) at runtime improves it. A custom XR application interfaced with a mobile manipulator supports immersive control and runtime modality switching. In a within-participant multi-room pick-and-place experiment comparing fixed AR, AV, and VR with dynamic RVC through task metrics, the NASA-TLX, and the System Usability Scale (SUS), this study demonstrates that 1) the fixed reality modality affects HRI results, and 2) dynamically changing the modality along the RVC improves them. AR yielded significantly lower mental demand, effort, and frustration than AV and VR, while the dynamic RVC condition achieved the highest throughput and lowest workload, highlighting the value of adaptive XR interfaces for human-robot symbiosis. The implementation is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31138
PDF
-
INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement
2026-09-25 11:27:27Aron Distelzweig, Andreas Look, Faris Janjo\v{s}, Steffen Hagedorn, Luigi Palmieri, Joschka BoedeckerAbstract
Driving in dense urban traffic is interactive: whether a merge or an unprotected turn succeeds depends on how surrounding agents respond to the ego vehicle. Conventional planners predict first and plan second and, therefore, cannot account for this dependency. Methods that integrate prediction and planning either train both jointly, which introduces task interference, or keep them separate and are restricted to a predefined set of proposals. We present INTERACT: Interactive Planning for Autonomous Driving via Anchor-Conditioned Prediction and Trust-Region Refinement. Our key insight is that surrounding agents react to the intent a trajectory expresses rather than to its exact realization, so a single reactive prediction stays valid across an entire family of plans. INTERACT therefore decomposes interactive planning into prediction across driving intents and optimization within each intent. We derive a small set of diverse intents, which we call anchors, from map geometry, query a dedicated ego-conditioned prediction model once per anchor, and refine every anchor with the Cross-Entropy Method under a trust-region penalty that keeps the refined plan close enough to its anchor for the conditioned reaction to still apply. Prediction thus remains a separate model, avoiding task interference, while conditioning on anchors preserves the dependency. Because each anchor is refined continuously, the final plan is not restricted to the anchor set, yet INTERACT requires only one predictor query per anchor rather than one per candidate plan, with all anchors processed in parallel. On the nuPlan and interPlan closed-loop benchmarks, INTERACT sets a new state of the art, with the largest gains precisely in the interactive scenarios that motivate the method. The code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31137
PDF
-
Comparative Evaluation of an XR Pen-based Control Interface for Semi-Autonomous Mobile Robot Navigation in Service Environments
2026-09-25 11:07:24Alicia Torc, Carl Tornberg, Eric Piette, Renaud Ronsse, Benoit Macq, Gustavo Alfonso Garcia Ricardez, Lotfi El Hafi, Tadahiro TaniguchiAbstract
Service robots remain difficult to deploy in domestic environments, partly because fully autonomous operation is not yet reliable in unpredictable surroundings, and partly because conventional control methods remain inaccessible to novice users. Extended Reality (XR) enables operators to visualize robot information overlaid onto the real world and to interact with augmented elements. Yet, common XR control methods, such as motion controllers and hand gestures, are still perceived as unintuitive. This paper presents a control interface that uses a commercial XR pen to command a semi-autonomous mobile robot in Augmented Reality (AR): the operator points at a position in the room, selects it, and drags an augmented arrow to set the desired orientation of the robot at this destination. Two additional interfaces, based on the XR motion controllers and hand gestures, were developed within the same framework. To assess the performance and users' perception of these interfaces, and of the XR pen in particular, a study with 10 participants compared four control methods, i.e., the XR pen, the XR motion controllers, hand gestures, and a computer-based baseline RViz, in navigation tasks performed in a home-like environment. Results show that the XR pen significantly outperforms the other methods in task selection time with the most consistent selections, and that the XR motion controllers obtain the best perceived workload and usability scores, ahead of the computer-based baseline, supporting XR-based control as an intuitive alternative for novice users. However, technical limitations in the integration of the recently released XR pen currently hold back its user experience.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31117
PDF
-
DualManip: Agentic Dynamic Manipulation via Dual-Path Semantic Reasoning and Geometric Adaptation
2026-09-25 10:57:02Chengxi Li, Yan Di, Yingyue Li, Ruida Zhang, Mingyang Li, Xiangyang JiAbstract
Vision-language models (VLMs) enable open-vocabulary reasoning for robot manipulation, but their high inference latency limits responsiveness in dynamic scenes. Many scene changes, however, alter object geometry without invalidating task intent. We present DualManip, a dual-path framework that decouples infrequent semantic reasoning from responsive geometric adaptation. The semantic path decomposes the task and grounds task-relevant interactions, followed by a constraint-solving module for pose optimization. During execution, the geometric path continuously updates template-to-observation correspondences from live RGB-D observations via a shape-adaptive network. These correspondences transfer task-relevant grasp contacts across observations, enabling online grasp reconstruction under object motion and non-rigid deformation. The Information Interaction Module bridges the two paths by initializing task-relevant grasps from semantic grounding, validating geometric updates, and triggering semantic replanning upon update failures. Real-world evaluation spans six manipulation tasks covering non-rigid deformation, articulated reconfiguration, rigid motion, and high-precision assembly across three settings: static, single-change, and continuous dynamic. DualManip demonstrates superior manipulation robustness, particularly under continuous scene changes, while achieving geometric adaptation approximately 46$\times$ faster than agentic verification and semantic replanning. Our project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31112
PDF
-
AuthGuard-R: Safety-Compliant Mission Hijacking and Dual-Gate Defense for LLM-Controlled Robots
2026-09-25 10:56:22Saidattu Chepuri, Vikas SrivastavaAbstract
Large language models are increasingly used as high-level planners for mobile robots, robot manipulators, and autonomous vehicles. Recent studies show that these systems can be influenced through malicious text, speech, visual instructions, retrieved documents, and poisoned sensory context. Most defenses ask whether a proposed action is physically safe. This paper studies a different problem: an action may be physically safe and still violate the mission authorized by the user. An attacker may redirect a delivery robot, replace an approved object, extend a robot's operating region, activate an unnecessary sensor, or delay a mission without creating an immediate physical hazard. We call this attack \emph{safety-compliant mission hijacking}. We propose MissionPAIR, an adaptive attack framework that searches for executable plans that pass a safety gate while violating an authenticated mission. We also propose AuthGuard-R, a deterministic authorization layer that binds every executable action to a signed mission, robot identity, object and region scope, current state, time, and input provenance. AuthGuard-R operates with an independent safety gate, giving a dual-gate architecture. We formalize mission policies over robot traces, define security games, and prove authorization soundness, mission non-escalation, replay resistance, robot binding, provenance separation, threshold-approval security, audit-log tamper evidence, and trace-level composition. We report a preliminary cross-model evaluation with Claude Haiku~4.5 and the open-source Qwen2.5~7B planner. Across 240 live attack trials, the planners followed an injected mission deviation in 109 trials; AuthGuard-R rejected all 109 resulting unauthorized actions. A separate hand-constructed suite of eleven protocol- and policy-level attacks was also blocked completely.
Abstract (translated)
URL
https://arxiv.org/abs/2609.31110
PDF
