We study whether a language model can help design controllers whose behavior can be formally checked. In proof-carrying evolution (PCE), a search proposes controllers together with their certificates. Their mathematical forms are fixed; a proposer chooses their numerical parameters together. Certificate checks guide selection, and only a certified candidate can be returned. The deployed artifact is a control law and its certificate; the language model is used only during design. We compare four language models with classical search and synthesis on docking under a speed limit, pursuit of a maneuvering target, and attitude control on SO(3), using paired runs and shared proposal allowances. Certificates are checked in exact rational arithmetic during search on the linear problems. On SO(3), the search uses floating-point checks, followed by exact re-verification of every reported champion. The best run of each method also receives Lean 4 proofs of its stated control properties. On the linear problems, the strongest models beat the standard classical baselines on every run, but a classical optimizer that chooses certificates for the same objective closes most of that lead. Among the cited pursuit champions, the ranking does not survive a change from Euler to zero-order-hold dynamics. On SO(3), no model detectably outperforms CMA-ES when mixed with classical mutation. When models write every proposal, one tested model improves on CMA-ES and the other performs worse than its mixed variant. All search medians remain below the hand-tuned law. In a docking control with the objective and mutation operator held fixed, retaining certified candidates yields new certified designs in every run; removing this rule yields none.
https://arxiv.org/abs/2610.42043
Large-scale egocentric human videos provide rich and scalable manipulation experience for robot policy learning, yet substantial embodiment gaps in visual appearance, kinematic structure, and action spaces hinder effective knowledge transfer. Existing methods often decouple cross-embodiment knowledge alignment from robot policy learning, making it difficult for human manipulation knowledge to directly and fully contribute to robot action learning. To address this issue, we propose Nexus-VLA, a hybrid policy learning framework that enables cross-embodiment knowledge transfer through end-to-end human-robot joint training, allowing human manipulation experience to directly contribute to robot policy learning. We first introduce a hierarchical cross-embodiment semantic alignment paradigm that progressively establishes shared manipulation semantics from task intent to fine-grained interactions, enabling more complete use of the manipulation knowledge contained in human videos. Building on this hierarchy, we design a shared manipulation latent representation that jointly encodes multi-level shared knowledge into an internal representation directly used for continuous action generation, improving policy learning efficiency while effectively leveraging human knowledge. Across RoboCasa-GR1, OOD settings, and real-world robot experiments, Nexus-VLA achieves an 80.5% task success rate on RoboCasa-GR1 and demonstrates strong advantages in human-data utilization, learning efficiency, and cross-scenario generalization.
https://arxiv.org/abs/2610.42021
Robotic Manipulation Surfaces (RMS) reposition objects by deforming the surface on which they rest. A recent class of RMS suspends a continuous fabric sheet from a sparse grid of vertical linear actuators lowering the actuator density of such surfaces but how to design such surfaces so that objects can be controlled everywhere on it, and how to extend it beyond a single module so that objects can pass between modules and achieve parallel, remain open. This paper presents a separable catenary model of the suspended sheet that is fast to compute and provides both the surface shape for given actuator heights and the actuator heights for a desired local slope. The closed form inverse lets a simple PID controller position objects on the sheet, and the model relates fabric length, module span and actuator stroke to the reachable workspace, yielding a minimum fabric length bound and design charts for these surfaces. The approach is then extended to a multimodular platform in which neighbouring modules share actuators. On a $2 \times 2$ prototype, we demonstrate that centimetre-scale objects are transferred between modules and positioned within 0.03 m over a $1 m^2$ workspace with only nine actuators, enabling multi-object manipulation and opening the way to parallel manipulation.
https://arxiv.org/abs/2610.41982
Data-driven controllers have enabled lower-limb robotic exoskeletons to adapt assistance to the user across many tasks. A leading example is biological torque control, which estimates the user's own joint moment from onboard sensors and assists in proportion to that estimate. However, its estimators are trained on data recorded with the target device, so deploying the controller on new hardware requires collecting new data. Existing open-source efforts release hardware, software, or controllers separately, so this data collection must still be repeated on the assembled device. Here, we present an open-source knee exoskeleton, built from off-the-shelf components and widely available fabrication tools, with a biological torque controller derived entirely from simulation. A muscle-driven imitation policy reproduces squatting motions from an open biomechanics dataset, and the resulting knee moments are distilled into an estimator that uses only onboard sensors, so no training data are recorded on the device. In seven able-bodied participants, assistance reduced peak biological knee extension moment by 21.5% and peak vastus medialis activation by 26.7% during squatting, relative to squatting without the exoskeleton (p<0.05). Our results demonstrate that a biological torque controller derived from simulation can transfer to physical hardware without device-specific data collection. Because the hardware and training pipeline are released together, research groups can train and compare knee exoskeleton controllers on shared hardware without additional data collection overhead.
https://arxiv.org/abs/2610.41981
Automated endoscope guidance reduces the need for continuous manual camera control during minimally invasive surgery. However, the desired camera motion depends on the surgeon's immediate intentions and cannot always be inferred from the visual operative scene alone. We propose to automate the task using language-conditioned behavioral cloning; we define 6 clinically relevant guidance behaviors and collect 235 subtask demonstrations. In preliminary phantom experiments, our policy achieves 100% success on focus, overview, and stop, 80% on search-tip and follow-tip behaviors, and 50% on horizon leveling. These results demonstrate the feasibility of learning heterogeneous surgeon-requested camera behaviors with a single visuomotor policy, while the observed failure modes motivate future work on adding temporal context for more demanding guidance tasks.
https://arxiv.org/abs/2610.41978
Embodied surgical AI requires reliable multimodal data, yet surgical data collection remains costly, difficult to repeat, and strongly dependent on the hardware setup. We present Sensorium, an open-source Python library for recording, processing, annotating, and curating multimodal surgical data from configurable robot and sensor streams using the Robot Operating System (ROS) and ROS2 middleware. The library combines operator-facing data acquisition, configurable processing, semantic annotation, and episodic dataset generation. We evaluate Sensorium across 1516 recordings of phantom, ex vivo, and in vivo porcine experiments involving multiple surgical tasks and sensing configurations, and report preliminary usability feedback.
https://arxiv.org/abs/2610.41946
This paper extends an existing framework for the coordination of mobile agents in unknown worlds, by considering the possibility of dynamic instability. In the original problem, known as the Partially Observable Cooperative Guard Art Gallery Problem (POCGAGP) (arXiv:2512.09495), the multi-agent system must establish a communication network which completely covers an initially unknown constrained space. However, the POCGAGP fails to account for the unpredictability often seen in real-world deployment. To address this, the dynamic case (DPOCGAGP) introduces two settings which can influence the mobile network during deployment: Agent Loss and World Change, which represent dynamic changes to the world. Within this study, we present advancements to two state-of-the-art algorithms, the Centralized Agent-Directed Exploration for Network Coverage (CADENCE), and its decentralized analogue, DADENCE, to provide solutions in these cases. We then compare their performance against another state-of-the-art benchmark algorithm, and show that the adapted algorithms outperform across our benchmark test set, which comprises over 4500 test cases of varied size and structure.
https://arxiv.org/abs/2610.41936
How to reuse a pretrained locomotion policy for precise loco-manipulation is still an open problem. We propose an online method to learn the closed-loop dynamics under a frozen locomotion policy. The learned model predicts floating-base motion and improves loco-manipulation accuracy. However, unobserved latent conditions of the policy introduce heterogeneous responses, meaning that the same observed state will lead to different motions. Direct learning without accounting for this heterogeneity introduces bias and fluctuations into dynamics estimates, degrading floating-base prediction and end-effector tracking. To address this problem, a contaminated Gaussian model is proposed to approximate the effects of latent conditions. The model uses two Gaussian components to approximate predictable and unpredictable responses under the same observed state. Then, the contaminated Gaussian model is combined with a Gaussian process to construct an online learner using random Fourier features (RFFs). The learner estimates each response's probability of belonging to the predictable component and uses it to weight online updates, capturing predictable responses while reducing bias and fluctuations caused by heterogeneous observations. With consistent and unbiased dynamics estimates, model predictive control (MPC) predicts floating-base motion accurately and enables precise loco-manipulation. A finite-sample error bound is established to ensure uniform convergence in online learning. Simulation and hardware experiments demonstrate consistent end-effector tracking across different manipulator configurations and tasks, with errors of 0.01 m.
https://arxiv.org/abs/2610.41892
LLM-based robotic agent systems can generate programs for robot control, yet their generalization to new tasks often depends on elaborate scaffolding. Expanding their skill repertoires alone offers limited guidance on how to assess new capabilities or identify what remains beyond their reach. We introduce META-Robot, a framework that couples self cognition with capability scaling by expanding the criteria through which an agent evaluates and develops its skills. At its core, action-level predicates make execution outcomes explicit and available for LLM reasoning. The agent uses these assessments to identify its own limitations, extend relevant evaluation criteria, and guide the structured expansion of its skills. Proprioceptive feedback further grounds this process in the robot's physical state, enriching the evidence available for self-cognition. Experiments in simulation and on real robots demonstrate stronger overall task performance, generalization to new tasks, continued expansion of skills and evaluation criteria, and effective use of non-visual proprioceptive signals.
https://arxiv.org/abs/2610.41868
Simulation benchmarks score robot policies by success rate, and every failed episode counts against the policy. Many of these failures are the simulator's fault, not the policy's; we find the cause and fix it. Testing a vision language action model and a world action model in simulation, we find that the policy often places the object and the simulator then ejects it, and that the benchmark's own scripted demonstrations fail the same way. We present SimuGuard, an auditing plugin for LIBERO, RoboTwin, RoboCasa and RoboDojo. It leaves the evaluation unchanged. At every physics step, it records the state and flags an object that starts moving at a contact faster than the robot's contact or gravity account for. It replays a recorded episode bit for bit, and it reruns the episode with one simulation parameter changed. With it we trace these episodes on RoboTwin to the collision detection of the physics engine: for geometry one to two centimeters apart, the engine reports a penetration of about two centimeters, and the solver throws the object out at several meters per second. The cause is one constant: the distance algorithm discards triangles below a fixed area threshold, which valid triangles fall below at the centimeter scale. With that constant changed and nothing else, episodes with an artifact fall from 12 in 100 to none, and the success rate on five container tasks rises from 89% to 98%. Success rates in simulation thus count failures that the simulator causes. Benchmarks on PhysX 5.3.1 or earlier should rerun in a repaired engine. Where the engine cannot change, they should report the success rate together with the range it spans when every flagged episode fails or passes: 75.8% to 98.5% around a reported 83.1% for LingBot-VA.
https://arxiv.org/abs/2610.41857
Multi-robot trajectory planning is a fundamental problem in multi-robot coordination but remains computationally challenging due to its nonconvex, multimodal, and high-dimensional nature. This work builds upon D4orm, a dynamics-aware diffusion-denoising framework, and develops a family of planning architectures for diverse operational requirements. Unlike conventional numerical optimization methods, D4orm employs sampling-based optimization to generate solution trajectories through massively parallel sampling, leveraging modern computing architectures such as GPUs. Its diffusion-denoising structure iteratively optimizes deformations to candidate control trajectories, providing an efficient and versatile paradigm for generating kinodynamically feasible and conflict-free trajectories. Using D4orm as the building block for advanced planners, we present a decoupled planner for improved scalability, an online receding-horizon planner with feedback control, and a distributed planner for resource-constrained settings. Evaluations with differential-drive and holonomic robots in 2D and 3D environments demonstrate that D4orm-based approaches find high-quality solutions faster and more reliably than other sampling-based optimization methods, such as MPPI, as well as a learned diffusion-model-based method. We further demonstrate zero-shot deployment on ten real quadrotors with obstacles, large-scale deconfliction with 100 simulated robots, and fully onboard distributed `lifelong' operation with six ground robots. Overall, these results establish diffusion denoising as a scalable and reliable framework for multi-robot coordination. Code and video: this https URL
https://arxiv.org/abs/2609.35651
Agentic robots must turn a high-level goal into actions while keeping the physical conditions needed for future steps valid. A completed action does not ensure that its effects will persist: a later disturbance can invalidate support that the remaining plan still assumes. We present LOGIV, a graph engineering framework for agentic robot execution that uses an explicit task graph to connect symbolic planning, observation-based verification, and embodied action. LOGIV compiles a validated plan into condition-support and resource-ordering edges, checks their physical validity during execution, and uses dependency tracing to determine what must be restored after a failure. Repair is constrained by retained unfinished actions, and the combined continuation is symbolically validated before execution resumes. The framework operates above existing Vision-Language-Action (VLA) and World Action Model (WAM) policies without adding trainable components. Across 20 dual-arm tasks from RoboTwin V2 and BiCoord with three execution backbones, LOGIV improves mean task success without injected disturbances by 10.67 and 15.33 percentage points, respectively. Under predefined perturbations, it achieves higher task completion and condition restoration than three adapted recovery baselines for every backbone on both benchmarks. On three real-robot tasks, successful trials increase from 12/30 to 17/30. These results support explicit, continuously checked task dependencies as a practical interface for reliable agentic robot execution.
https://arxiv.org/abs/2610.40016
Inserting an unseen part requires sub-millimetre precision and the correct orientation of keyed features. Current zero-shot agentic manipulation methods built on vision-language models (VLMs) produce spatial outputs that are far too coarse for this. We propose to let a VLM build a sketch model of the task, i.e., a few geometric primitives and two mate frames, which a VLM agent measures with geometric tools in multi-view depth and which a standard planner and compliant controller execute. Because a sketch describes the parts independently of their placement, the robot needs to build it only once per task. A sketch memory stores each agent run and transfers the stored sketch to later placements by point-cloud registration, so that the VLM is called only for unfamiliar parts. After grasping the part, the robot inspects both mating faces at close range and corrects the sketch by shape matching. On 69 simulated insertion episodes, our method inserts 88% of the parts at the assembled pose in a strict kinematic test, while ReKep and MOKA with the same VLM insert none. On new placements of eight tasks, reusing one stored run inserts as many parts as calling the agent in each episode, and it produces the sketch in 3.4 s instead of about 90 s.
https://arxiv.org/abs/2610.41844
Recent developments in both high-thrust (HT) and low-thrust (LT) propulsion technologies broaden design options for on-orbit servicing (OOS) missions. However, incorporating LT transfers into OOS mission planning requires accounting for the trade-off between prescribed transfer duration and propellant consumption. Multi-servicing, multi-transfer OOS mission planning is inherently sequential and requires adaptive planning tools that account for propulsion-dependent transfer durations and mass-dependent propellant consumption. Thus, transfer dynamics must be integrated into mission planning and scheduling to increase flexibility and adaptability. In addition, the planning is often done with imperfect information about the system's state and stochastic service demands. This paper focuses on modeling orbital transfers, particularly LT transfers, within a Partially Observable Markov Decision Process (POMDP) framework for OOS mission planning. To enable offline policy computation, the transfer model must provide explicit state transitions and rewards for all admissible actions. The state space is therefore augmented with the servicing vehicle's remaining propellant to enable consistent mass updates. HT transfers are modeled using a precomputed transfer matrix that maps each transfer to the time of flight and propellant consumed. LT transfers are represented using an analytical GEO phasing model with prescribed transfer-duration alternatives. For each alternative, the model calculates propellant consumption and maneuver feasibility as functions of the required phase change and the current servicing-vehicle mass. The proposed modeling approach is evaluated on simplified OOS planning scenarios using circular phasing with HT and LT propulsion. The resulting POMDPs are solved using the Successive Approximations of the Reachable Space under Optimal Policies (SARSOP) algorithm, and the policies obtained under HT and LT are compared. This comparison provides a quantitative assessment of the feasibility and operational impact of LT options, particularly regarding the potential role of advanced electric propulsion in future servicing architectures.
https://arxiv.org/abs/2610.41839
Recent years have seen multiple impressive results in visual-inertial odometry (VIO) techniques, by which accurate state estimation can be achieved via the extended Kalman filter (EKF) or nonlinear optimization. However, these approaches are rarely open source, and they tend to fail in real experiments due to the temporary lack of feature points and fast motion. Therefore, in this study, we used encoders to overcome the temporary failure of purely vision-based simultaneous localization and mapping (SLAM). Here, we propose a generative measurement model for encoders and derive an expression for the maximum a posteriori (MAP) estimate and necessary Jacobians for optimization. We use our theory to present a novel tightly coupled visual-inertial encoder RGB-Depth (RGB-D) SLAM system. Tests on our system on an in-house dataset confirmed that our modeling effort led to accurate (with a root mean squared error (RMSE) of approximately 2-7 cm) and robust state estimation in real time. The source code and our dataset containing the encoder information have been published for verification.
https://arxiv.org/abs/2610.41768
This paper leverages the higher-order kinematic derivatives of serial robots to achieve efficient, aspect-preserving real-time inverse kinematics. First, a family of higher-order solvers is derived, with a necessary orientation-error correction map, yielding the QuIK4 and QuIK5 methods with fourth- and fifth-order convergence. Second, an aspect-preserving step limiter extrapolates the Jacobian determinant along the step to predict and avoid singularities, shortening steps only when they head toward a singularity rather than when the current iterate is ill-conditioned. Third, a Hermite-interpolation certifier verifies the aspect of each answer, and a certified restart algorithm recovers failures from proven same-aspect seeds. The proposed methods are shown to outperform prior methods, reducing failures by up to four orders of magnitude and nearly eliminating aspect switching at tracking-level errors. A C++ library is released with ROS 2 integration.
https://arxiv.org/abs/2610.41752
Architectural spaces are increasingly gaining robotic capabilities. Architectural robots such as robotic partitions, ceilings, furniture, facades, and other spatial components can autonomously move and reconfigure in response to occupants' needs and activities. Yet, when architectural robots start shaping the spatial conditions in which people continuously live, work, and interact, we may begin to experience the architectural space itself as robotic. What does this shift mean for how we inhabit such spaces? Drawing on our previous studies, I reflect on how architectural robots interact with people not only through their motions, but also through the spatial configurations that persist after those motions stop; how their actions may benefit some occupants while disadvantaging others; and how multiple robots may together make a whole architectural space appear to act. I argue that as computation gains the capacity to physically reconfigure our environments, interaction extends beyond the moment of computational action into the spatial conditions that people continue to inhabit. Understanding robotic architecture therefore requires us to look beyond short-term human-robot interaction and toward how people inhabit, negotiate, and maintain control over spaces that can autonomously reconfigure.
https://arxiv.org/abs/2610.41724
Flexible robot links challenge the rigid-body assumption, making joint measurements alone insufficient for accurate manipulation. This paper introduces a flexibility-aware manipulation framework that connects structural dynamics directly to sensing, kinematics, and control. Instead of prescribing a dense inertial measurement unit (IMU) network, the dominant vibration modes of each flexible link are first identified from response-convergence and excitation-bandwidth criteria. Under a full-rank modal observability condition, $m$ retained modes require only $m$ independent slope measurements and one reference IMU, defining the minimum observable IMU configuration. The resulting measurements are used to reconstruct the continuous link deformation, which is then incorporated into flexibility-aware forward kinematics and a deformation-informed partial differential equation-based controller. Experiments on hydraulic single- and double-link manipulators evaluate the framework. On the long-reach double-link platform, the proposed kinematics achieves end-effector root mean square errors of $0.0107$~m, $0.0194$~m, and $0.0102$~rad while using fewer sensors than the piecewise-rigid method. Closed-loop reaching experiments further demonstrate real-time integration of IMU-estimated joint states and reconstructed deformation into the proposed controller. The results show that dominant modal information can determine sensing requirements and enable real-time flexibility-aware robotic manipulation.
https://arxiv.org/abs/2610.41702
Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation. We organize existing approaches along two complementary dimensions: six fundamental memory requirements, spanning world-state persistence, task progress, belief maintenance, and experiential learning; and eight architectural categories, including recurrent states, fast weights, visual and symbolic representations, spatial memory, and experience-based systems. We analyze their capabilities and limitations, and examine how existing benchmarks evaluate memory-dependent behavior, distinguishing genuine use of historical information from general task performance. Finally, we identify open challenges in selecting relevant experiences, maintaining consistent beliefs in changing environments, and consolidating knowledge across episodes. Our analysis provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.
https://arxiv.org/abs/2610.41688
Wearable force-augmentation technologies, including exoskeletons and soft exosuits, are being developed for occupational and rehabilitation settings to enhance performance by reducing the muscular demands of movements. Yet enhanced performance also requires users to perceive the environment accurately, adapt to changing conditions, and decide whether actions are worth their physical cost. We used an elbow-assisting exosuit to investigate the physiological, perceptual and cognitive consequences of force augmentation during lifting. We assessed weight perception, adaptation in a volatile environment, and effort-based decision-making with and without assistance. While assistance reduced muscle activity, its behavioural outcomes did not simply reflect this biomechanical change. Assistance reduced perceived weight, but this effect was strongly shaped by participants' initial experience. Assistance also selectively reduced adaptation to changing environmental contingencies. Finally, reducing the muscular demands of lifting did not translate straightforwardly into how demanding the action felt or whether participants chose to perform it: differences in effort-based decisions were shaped by initial experience rather than simply tracking reductions in muscle activity or perceived fatigue. Together, we show that the perceptual and cognitive consequences of force augmentation cannot be inferred from its biomechanical benefits alone. Effective augmentation therefore requires perceptual and cognitive outcomes to be evaluated alongside physical performance.
https://arxiv.org/abs/2610.41679