arXiv subjects

Xiaofeng Guo

Publications and source records attributed to Xiaofeng Guo.

At least 19 recordsLinked to original sources

arXiv2026

Learning Force-Reactive Humanoid Loco-Manipulation

Many everyday tasks require controlling contact force as well as motion. On a humanoid, this force must often be coordinated across both hands and the whole body, and cannot be specified by kinematic trajectories alone. Therefore, we present FLORE, a framework for learning force-reactive humanoid loco-manipulation. We collect robot-free demonstrations using two force-sensing UMI-style handheld grippers for hand motion and contact wrenches, and wearable trackers for body motion. A force-reactive diffusion policy takes vision, proprioception, and measured wrenches as input, then predicts actions and per-hand force commands. A hybrid compliance whole-body controller with force tracking executes these commands while maintaining balance: an integral of the force error measured by real force/torque (F/T) sensors lets each hand track force accurately along the commanded direction and remain compliant along the others. In simulation, the controller tracks per-hand force commands of varied magnitude and direction, with little loss in whole-body motion accuracy. Across three contact-rich tasks on the robot, the force-reactive policy succeeds in 80% of rollouts, compared with 26.7% for a position-only policy trained on the same demonstrations and executed by the same controller. For more details, please visit our website: https://louis-leee.github.io/FLoRe/.

cs.RO↗

arXiv2026

DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection

Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup and places the burden of coordinating many finger joints on the operator. Human demonstrations are easier to collect, but their motions must be estimated and retargeted to the robot, and they do not directly provide robot actions. In this paper, we introduce DexPort, a portable data-collection interface for high-DoF robot hands. It uses the same hand hardware for collection and deployment, avoiding a hand embodiment gap, and records both commanded joint targets and measured joint states. Our key observation is that a small set of skills can support a wide range of dexterous tasks. During collection, the operator moves the hand-held interface to specify the robot wrist motion and selects or adjusts skills that coordinate the finger motion. This removes the need to control each joint independently while retaining behaviors such as precise grasping and in-hand manipulation. We collect demonstrations across several real-world tasks and in unstructured environments without a robot arm. We then use behavior cloning to train visuomotor policies directly on the recorded wrist motions and hand commands, without skill labels. We evaluate across 4 tasks: pick-and-place with diverse objects, screwing with in-hand tool use, drawer stowage which requires simultaneous grasp and pulling, and a bimanual scanning task. We collect over 2,500 demonstrations with our portable device, in both laboratory and in-the-wild settings. Across our tasks, we see an improvement from 11% to 64% when using recorded robot commands instead of states, and an improvement from 36% to 78% for task success when using in-the-wild data.

cs.RO↗

arXiv2026

SWAP: Test-Time Steerable Humanoid Whole-Body Collision Avoidance

Humanoid robots operating in human-centric environments must coordinate the entire body to traverse tight, cluttered spaces while maintaining balance. Existing methods often struggle to jointly consider dynamic stability and collision avoidance from high-dimensional perceptual inputs. Moreover, for humanoids, safe behavior is inherently multimodal: the same obstacle may admit multiple valid traversals, which is difficult to represent with a single deterministic policy. To address these challenges, we propose SWAP (Steerable Whole-body Avoidance Policy), a hierarchical framework that separates collision-aware decision making from stabilization. A high-level, perception-conditioned diffusion policy generates multimodal, collision-aware motion proposals, while a low-level whole-body RL controller tracks these proposals and maintains dynamic balance. To efficiently train the high-level policy, we obtain scalable supervision via hindsight labeling: we roll out the low-level policy under randomized commands, place obstacles only in the space that each executed motion did not sweep, so the motion is collision-free by construction, and re-render the perception the robot would have seen. At deployment, Monte Carlo sampling with simple cost signals steers the diffusion model toward safe, task-aligned behaviors without heavy reward tuning. Experiments in simulation and on a real Unitree G1 humanoid show reliable avoidance with static and dynamic obstacles. Test-time steering further enables customization, improving targeted rewards (e.g., speed, orientation, or posture) by 34% on average while maintaining a high collision avoidance rate. Together, these results support a practical solution to humanoid whole-body collision avoidance with test-time steerability. Project website: https://iscoyizj.github.io/SWAP-steerable-humanoid-oa-website/

cs.RO↗

arXiv2026

PanTact: Teaching Whole-Body Dexterity with a Wearable Contact Interface

Humanoid robots have many degrees of freedom and contact surfaces, yet most loco-manipulation research restricts manipulation to the hands and avoids other body contacts with the environment. To extend manipulation beyond the hands, we present PanTact, a system that learns humanoid whole-body dexterity, the capability to manipulate with any suitable body surface, directly from robot-free human demonstrations. Our key idea is to use contact as manipulation-centric information that transfers across embodiments. Contact locations and timing specify the interactions needed to accomplish a task, while the robot chooses how to coordinate its body to realize them within its own physical constraints. Specifically, PanTact captures, learns, and executes whole-body contact via: 1) a wearable, robot-free data collection interface that augments egocentric vision and bimanual UMI grippers with whole-body modular contact patches to record body contact locations and states; 2) a visuomotor policy that mitigates the egocentric observation gap and predicts whole-body contact goals; and 3) contact-aware whole-body control formulations that realize active contact goals using suitable robot surfaces. We deploy PanTact on a Unitree G1 humanoid without additional body contact sensors, demonstrating whole-body dexterity involving body support, pushing, sweeping, and load-sharing. Website: https://pantact.github.io

cs.RO↗

arXiv2026

Precise SE(3) End-Effector Tracking in Whole-Body Humanoid Control

Precise end-effector tracking during humanoid whole-body motion is challenging due to floating-base oscillations, gravity, dynamic coupling, and locomotion-induced disturbances. We propose ResGAC, a whole-body humanoid controller for precise end-effector pose tracking that combines geometric admittance control (GAC) with residual reinforcement learning. GAC provides structured $\SE$ task-space feedback and generates nominal arm joint-position targets, while residual RL compensates for unmodeled dynamics and coordinates locomotion and balance in the shared joint-position action space. The left-invariant geometric formulation allows the same GAC law to be used across manipulation reference frames. This enables the use of a ground-attached heading frame that preserves planar locomotion while removing pelvis roll, pitch, and heave from the manipulation reference, thereby reducing reference-induced end-effector motion during locomotion. ResGAC is validated on a real Unitree G1 humanoid. Across four standing end-effector tracking benchmarks, ResGAC consistently outperforms representative baselines, including SONIC, achieving lower translational and rotational errors. Real-world experiments further demonstrate reduced propagation of pelvis motion to the desired end-effector pose using the proposed ground-attached heading frame. ResGAC achieves $90\%$ success in a standing peg-in-hole task compared with $50\%$ for SONIC, and accurate world-frame $\SE$ end-effector pose tracking during lower-body motion. Experimental videos are included in the supplementary material and are also available on the project website: https://resgac.github.io/ResGAC-website/.

cs.RO↗

arXiv2026

AM-Bench: A Modular Simulation Suite and Benchmark for Aerial Manipulation Policy Learning

Standardized benchmarks have played a central role in advancing robot manipulation learning, yet most focus on ground-supported manipulation systems, which limits their applicability to dynamics-critical domains such as aerial manipulation (AM). AM presents distinct system-level challenges, including environmental disturbances, coupled dynamics between the manipulator and floating base, and constrained degrees of freedom. Consequently, task performance depends jointly on robot embodiment, low-level control, and high-level policy design. We introduce AM-Bench, a modular simulation suite and benchmark for multirotor-based AM policy learning. AM-Bench includes representative embodiments spanning underactuated, fully actuated, and overactuated systems, 12 tasks across contact, transport, and constrained interaction, configurable aerodynamic disturbances and actuator saturation, standard low-level controllers, and baseline policy-learning algorithms. Unlike prior manipulation benchmarks that primarily emphasize end-to-end policy performance, AM-Bench enables system-level evaluation of how embodiment, control, disturbances, and policy choices interact. We demonstrate its diagnostic value through three simulation studies spanning high-level policies, policy--control interfaces, and embodiments, together with real-world validation of modeled effects and a hardware test of the learning pipeline.

cs.RO↗

arXiv2026

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies

We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstrations collected with a handheld gripper (UMI) to train generalizable visuomotor policies. A central challenge in transferring these policies to constrained robotic embodiments-such as aerial manipulators-is the mismatch in control and robot dynamics, which often leads to out-of-distribution behaviors and poor execution. To address this, we propose Embodiment-Aware Diffusion Policy (EADP), which couples a high-level UMI policy with a low-level embodiment-specific controller at inference time. By integrating gradient feedback from the controller's tracking cost into the diffusion sampling process, our method steers trajectory generation towards dynamically feasible modes tailored to the deployment embodiment. This enables plug-and-play, embodiment-aware trajectory adaptation at test time. We validate our approach on multiple long-horizon and high-precision aerial manipulation tasks, showing improved success rates, efficiency, and robustness under disturbances compared to unguided diffusion baselines. Finally, we demonstrate deployment in previously unseen environments, using UMI demonstrations collected in the wild, highlighting a practical pathway for scaling generalizable manipulation skills across diverse-and even highly constrained-embodiments. All code, data, checkpoints, and result videos can be found at umi-on-air.github.io.

cs.RO↗

arXiv2025

DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment

Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-stage pipeline: a compact seed set of human-sung recordings is constructed by pairing fixed melodies with diverse LLM-generated lyrics, and melody-specific models are trained to synthesize over 500 hours of high-quality Chinese singing data. Building on this corpus, we propose DiTSinger, a Diffusion Transformer with RoPE and qk-norm, systematically scaled in depth, width, and resolution for enhanced fidelity. Furthermore, we design an implicit alignment mechanism that obviates phoneme-level duration labels by constraining phoneme-to-acoustic attention within character-level spans, thereby improving robustness under noisy or uncertain alignments. Extensive experiments validate that our approach enables scalable, alignment-free, and high-fidelity SVS.

cs.SD↗

arXiv2025

Achieving accurate entropy and melting point by ab initio molecular dynamics and zentropy theory: Application to fluoride and chloride molten salts

We have recently developed a breakthrough methodology for rapidly computing entropy in both solids and liquids by integrating a multiscale entropy approach (known as zentropy theory) with molecular dynamics (MD) simulations. This approach enables entropy estimation from a single MD trajectory by analyzing the probabilities of local structural configurations and atomic distributions, effectively addressing the long-standing challenge of capturing configurational entropy. Here, we demonstrate the power of this method by predicting entropies, enthalpies, and melting points for 25 binary and ternary chlorite- and fluoride-based molten salts using ab initio MD (AIMD) simulations. The strong agreement between our predictions and experimental data underscores the potential of this approach to transform computational thermodynamics, offering accurate, efficient, and direct predictions of thermodynamic properties across both solid and liquid phases.

cond-mat.mtrl-sci↗

arXiv2025

OASIS: A Deep Learning Framework for Universal Spectroscopic Analysis Driven by Novel Loss Functions

The proliferation of spectroscopic data across various scientific and engineering fields necessitates automated processing. We introduce OASIS (Omni-purpose Analysis of Spectra via Intelligent Systems), a machine learning (ML) framework for technique-independent, automated spectral analysis, encompassing denoising, baseline correction, and comprehensive peak parameter (location, intensity, FWHM) retrieval without human intervention. OASIS achieves its versatility through models trained on a strategically designed synthetic dataset incorporating features from numerous spectroscopy techniques. Critically, the development of innovative, task-specific loss functions-such as the vicinity peak response (ViPeR) for peak localization-enabled the creation of compact yet highly accurate models from this dataset, validated with experimental data from Raman, UV-vis, and fluorescence spectroscopy. OASIS demonstrates significant potential for applications including in situ experiments, high-throughput optimization, and online monitoring. This study underscores the optimization of the loss function as a key resource-efficient strategy to develop high-performance ML models.

cs.LG↗

arXiv2025

Thermodynamic Prediction Enabled by Automatic Dataset Building and Machine Learning

New discoveries in chemistry and materials science, with increasingly expanding volume of requisite knowledge and experimental workload, provide unique opportunities for machine learning (ML) to take critical roles in accelerating research efficiency. Here, we demonstrate (1) the use of large language models (LLMs) for automated literature reviews, and (2) the training of an ML model to predict chemical knowledge (thermodynamic parameters). Our LLM-based literature review tool (LMExt) successfully extracted chemical information and beyond into a machine-readable structure, including stability constants for metal cation-ligand interactions, thermodynamic properties, and other broader data types (medical research papers, and financial reports), effectively overcoming the challenges inherent in each domain. Using the autonomous acquisition of thermodynamic data, an ML model was trained using the CatBoost algorithm for accurately predicting thermodynamic parameters (e.g., enthalpy of formation) of minerals. This work highlights the transformative potential of integrated ML approaches to reshape chemistry and materials science research.

cond-mat.mtrl-sci↗

arXiv2025

Flying Calligrapher: Contact-Aware Motion and Force Planning and Control for Aerial Manipulation

Aerial manipulation has gained interest in completing high-altitude tasks that are challenging for human workers, such as contact inspection and defect detection, etc. Previous research has focused on maintaining static contact points or forces. This letter addresses a more general and dynamic task: simultaneously tracking time-varying contact force in the surface normal direction and motion trajectories on tangential surfaces. We propose a pipeline that includes a contact-aware trajectory planner to generate dynamically feasible trajectories, and a hybrid motion-force controller to track such trajectories. We demonstrate the approach in an aerial calligraphy task using a novel sponge pen design as the end-effector, whose stroke width is positively related to the contact force. Additionally, we develop a touchscreen interface for flexible user input. Experiments show our method can effectively draw diverse letters, achieving an IoU of 0.59 and an end-effector position (force) tracking RMSE of 2.9 cm (0.7 N). Website: https://xiaofeng-guo.github.io/flying-calligrapher/

cs.RO↗

arXiv2025

Flying Hand: End-Effector-Centric Framework for Versatile Aerial Manipulation Teleoperation and Policy Learning

Aerial manipulation has recently attracted increasing interest from both industry and academia. Previous approaches have demonstrated success in various specific tasks. However, their hardware design and control frameworks are often tightly coupled with task specifications, limiting the development of cross-task and cross-platform algorithms. Inspired by the success of robot learning in tabletop manipulation, we propose a unified aerial manipulation framework with an end-effector-centric interface that decouples high-level platform-agnostic decision-making from task-agnostic low-level control. Our framework consists of a fully-actuated hexarotor with a 4-DoF robotic arm, an end-effector-centric whole-body model predictive controller, and a high-level policy. The high-precision end-effector controller enables efficient and intuitive aerial teleoperation for versatile tasks and facilitates the development of imitation learning policies. Real-world experiments show that the proposed framework significantly improves end-effector tracking accuracy, and can handle multiple aerial teleoperation and imitation learning tasks, including writing, peg-in-hole, pick and place, changing light bulbs, etc. We believe the proposed framework provides one way to standardize and unify aerial manipulation into the general manipulation community and to advance the field. Project website: https://lecar-lab.github.io/flying_hand/.

cs.RO↗

arXiv2025

Data-Driven Insights into Rare Earth Mineralization: Machine Learning Applications Using Functional Material Synthesis Data

Quantitative understanding of rare earth element (REE) mineralization mechanisms, crucial for improving industrial separation, remains limited. This study leverages 1239 hydrothermal synthesis datapoints from material science as a surrogate for natural REE mineralization. We trained machine learning models (KNN, RF, XGBoost) using precursor, additive, and reaction data to predict product elements and phases, validating predictions with new experiments. XGBoost exhibited the highest accuracy, with feature importance analysis indicating thermodynamic properties were critical for predictions. Observed correlations among reaction parameters aligned with classical crystallization theory. Further XGBoost models successfully predicted reaction temperature and pH from precursor/product data. Our findings demonstrate the cross-disciplinary utility of material science data for geochemical understanding, underscore the need for research on less-studied REE minerals (e.g., carbonates, heavy REEs), and suggest potential to accelerate REE resource development.

cond-mat.mtrl-sci↗

arXiv2025

Molecular Insights into Yb(III) Speciation in Sulfate-Bearing Hydrothermal Fluids from X-ray Absorption Spectra Informed by ab initio Molecular Dynamics

Rare earth elements (REEs) are critical for advanced technologies, yet in hydrothermal aqueous solutions the molecular level details of their interaction with ligands that control their geochemical transport and deposition remain poorly understood. This study elucidates the coordination behavior of Yb(III) in sulfate-rich hydrothermal fluids using in situ extended X-ray absorption fine structure (EXAFS) spectroscopy and ab initio molecular dynamics (AIMD) simulations. By integrating multi-angle EXAFS with AIMD-derived constraints, we precisely resolve Yb(III) coordination structures and ligand interactions under hydrothermal conditions. At room temperature, Yb (III) is coordinated by five water molecules and two sulfate ligands (coordination number, CN = 8), forming a distorted square antiprism geometry. Increasing temperature induces progressive dehydration, reducing the hydration shell and favoring stronger sulfate complexation. At 200 Celsius, sulfate ligands reorganize around Yb(III), shifting its geometry to a capped dodecahedron (CN = 7). At 300 Celsius, sulfate binding dominates, leading to structural reorganization that parallels the onset of sulfate mineral precipitation, consistent with the retrograde solubility of REE sulfates. These findings provide direct molecular-scale evidence that sulfate acts as both a transport and deposition ligand, critically influencing REE mobility in geochemical environments. Our results can also help to refine thermodynamic models of REE speciation in high-temperature hydrothermal fluids and improve our understanding of REE ore formation processes in nature.

physics.chem-ph↗

arXiv2025

Thermodynamic modeling of the LiCl-KCl-LaCl$_3$ system with Bayesian model selection and uncertainty quantification

Chloride molten salts are increasingly used in pyroprocessing techniques for the separation of lanthanides. Understanding thermodynamic properties of these salts is essential to predict their critical characteristics and optimize the separation process. Several thermodynamic models, including the associate model, the two-sublattice ionic model, and the modified quasichemical model with quadruplet approximation (MQMQA), have been utilized in the literature to capture the complexity of molten salts. In the present work, the Bayes factor is used to guide the model selection process for thermodynamic modeling of the KCl-LaCl3 system and provide statistical comparison of various models. The results indicate that the MQMQA model is the most favorable one based on available data. The LiCl-KCl-LaCl3 system has been further modelled with uncertainty quantification (UQ) using MQMQA with the thermodynamic properties of compounds in KCl-LaCl3 predicted by the quasiharmonic approach in terms of first-principles phonon calculations as a function of temperature. The calculated phase stability shows excellent agreement with experimental data, indicating that an appropriate thermodynamic model is important for accurately predicting critical characteristics of complex molten salts.

cond-mat.mtrl-sci↗

arXiv2024

Non-stoichiometric and Subnano-heterogeneous Ln-incorporated UO2: its defect chemistry and thermal oxidation

The defect chemistry and thermal oxidation of lanthanide (Ln) incorporated-UO2 are critical for understanding and predicting their behavior as enhanced fuels, mixed oxide (MOX) fuels, spent nuclear fuels (SNF), and particles for safeguard purposes. In this study, we independently controlled the Ln type (Ce4+, Nd3+, and Gd3+) and the preparation condition (reduced and nonreduced) to investigate their correlations to the generated non-equilibrated defects correspondingly. From early to late lanthanides: Ce and U formed close-to-ideal solid solutions in Fm-3m and oxidized to (Ce, U)4O9, Nd and U mixing under the reducing condition formed solid solutions with oxygen vacancies aggregating near Nd, and the mixing of smaller Gd with U resulted in short-range subnano-domain segregations with Ia-3 region embedded in the global Fm-3m matrix. Both trivalent Ln-incorporated UO2 oxidized to a mixture of (Ln, U)4O9 and (Ln, U)3O8. From these signature defect structures resulting from both Ln type and preparation condition, we proposed kinetic model and thermodynamic hypothesis for explaining the oxidation resistance of (Ln, U)O2. Although originated from f-block oxides, the discovery of long-range disorder short-range ordering may be not uncommon in other metal oxide systems, which can strongly influence their functionalities and properties.

cond-mat.mtrl-sci↗

arXiv2024

Molecular interaction volume model of mixing enthalpy for molten salt system: An integrated calorimetry-model case study of LaCl$_3$-(LiCl-KCl)

Calorimetric determination of enthalpies of mixing ($Δ$H$_{\rm mix}$) of multicomponent molten salts often employs empirical models that lack parameters with clear physical interpretation (e.g., coordination numbers, molar volumes, and pair potentials). Although such physics informed models are not always needed, a thermodynamic understanding of the relationships between excess energies of mixing and local to intermediate solvation structures is particularly important for pyrochemical separation, as is the case for lanthanides (Ln), which are common neutron poisons and critical industrial elements found in spent nuclear fuels. Here we implement the molecular interaction volume model (MIVM) to synthesize information from experimentally measured $Δ$H$_{\rm mix}$ (using high temperature melt drop calorimetry) and the distribution of solvation structures from ab initio molecular dynamics (AIMD) simulations. This was demonstrated by a case study of molten salt system consisted of LaCl$_3$ mixing with a eutectic LiCl-KCl (58mol% to 42mol%) at 873 K and 1133 K. The parameters modelled from MIVM were used to extrapolate excess Gibbs energy ($Δ$G$_{\rm mix}$), and compositional dependence of La$^{3+}$ activity in the LaCl$_3$-(LiCl-KCl) system. In contrast, by AIMD or polarizable ion model (PIM) simulations, a significant deviation regarding the predicted $Δ$H$_{\rm mix}$ was seen if computed directly from the molecular dynamic trajectories. The integrated experimental and simulation data within the MIVM formalism are generalizable to a wide variety of molten salts and demonstrate a significant improvement over currently employed methods to study molten salts for nuclear and separations sciences.

cond-mat.mtrl-sci↗