arXiv subjects

Xiaoqiang Ji

Publications and source records attributed to Xiaoqiang Ji.

11 recordsLinked to original sources

arXiv2026

CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding

Vision-language-action (VLA) models remain brittle in manipulation tasks that require physical commonsense. Current physical VQA data is typically disembodied and misaligned with robot action domains. Egocentric videos are used only as auxiliary pre-training. It remains unclear whether improved VLM physical understanding actually benefits downstream action generation. Therefore, we present CometVLA to close this gap. We construct CometData and CometBench, an embodied physical VQA corpus and benchmark strictly aligned with the robot's action data and embodiment. We introduce Global Action Prior (GAP) tokens, a compact learnable bottleneck that isolates task-agnostic motion regularities and lets the action head consume physical commonsense without corrupting the pre-trained VLM backbone. We co-train CometVLA across the embodied data pyramid, spanning teleoperation, simulation, egocentric trajectories, and VQA layers. On real-world manipulation tasks and RoboTwin simulation, CometVLA consistently outperforms strong VLA baselines. Correlation analysis shows that stronger VLM performance on CometBench indicates higher VLA success rates. Results demonstrate that physical understanding pre-training genuinely benefits downstream manipulation.

cs.RO↗

arXiv2026

ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability

Producing a hand-buildable, colored brick model of a 3D object from a few casual photographs is a clean testbed for a broader challenge: generating 3D content that meets hard physical-assembly constraints under a discrete, budget-limited voxel grid. On a coarse lattice, visual resemblance and structural stability pull against each other, yet prior brick pipelines address only one side and treat voxelization as fixed preprocessing rather than a variable to optimize. We present ResemBrick, which couples the two. Budgeted occupancy completion reframes discretization as allocation: given a target occupied-voxel count, a single resolution-conditioned network decides in one feed-forward pass which surface voxels to fill for best appearance, one weight set spanning 13 resolutions. Buildability by construction then combines support- and look-ahead-aware greedy placement with a deterministic, provably terminating repair that grounds every floating component. Under a matched budget, ResemBrick surpasses existing voxel selectors in perceptual fidelity while uniquely reaching zero floating and zero unstable bricks on unfiltered held-out objects; as a complete pipeline, it attains the best perceptual fidelity among prior brick-construction systems. Our results point to treating discretization and assembly as tightly coupled stages rather than independent ones.

cs.CV↗

arXiv2026

ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy Optimization

Offline reinforcement learning methods typically enforce strict constraints to ensure safety; yet this rigidity often prevents the discovery of optimal behaviors outside the immediate support of the behavior policy. To address this, we propose Implicit Support Expansion via stochastic Policy optimization (ISEP), which leverages a value function interpolated between in-distribution data and policy samples to implicitly expand the feasible action support. This mechanism "densifies" high-reward regions, creating a navigable path for policy improvement while theoretically guaranteeing bounded value error. However, optimizing against this expanded support creates a multimodal landscape where standard deterministic averaging leads to mode collapse and invalid actions. ISEP mitigates this via a stochastic action selection strategy, optimizing the policy by stochastically alternating between conservative cloning and optimistic expansion signals. We instantiate this framework as ISEP-FM using Conditional Flow Matching utilizing classifier-free guidance to effectively capture the interpolated value signal.

cs.LG↗

arXiv2026

Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustness

Vision-Language Models (VLMs) are essential for embodied AI and safety-critical applications, such as robotics and autonomous systems. However, existing benchmarks primarily focus on static or curated visual inputs, neglecting the challenges posed by adversarial conditions, value misalignment, and error propagation in continuous deployment. Current benchmarks either overlook the impact of real-world perturbations, or fail to account for the cumulative effect of inconsistent reasoning over time. To address these gaps, we introduce the Degraded Image Quality Leading to Hallucinations (DIQ-H) benchmark, the first to evaluate VLMs under adversarial visual conditions in continuous sequences. DIQ-H simulates real-world stressors including motion blur, sensor noise, and compression artifacts, and measures how these corruptions lead to persistent errors and misaligned outputs across time. The benchmark explicitly models error propagation and its long-term value consistency. To enhance scalability and reduce costs for safety-critical evaluation, we propose the Value-Guided Iterative Refinement (VIR) framework, which automates the generation of high-quality, ethically aligned ground truth annotations. VGIR leverages lightweight VLMs to detect and refine value misalignment, improving accuracy from 72.2% to 83.3%, representing a 15.3% relative improvement. The DIQ-H benchmark and VGIR framework provide a robust platform for embodied AI safety assessment, revealing vulnerabilities in error recovery, ethical consistency, and temporal value alignment.

cs.CV↗

arXiv2026

CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System

Large language models are enabling language-conditioned agents in interactive environments, but highly cooperative tasks often impose two simultaneous constraints: sub-second real-time coordination and sustained multi-episode adaptation under a strict online token budget. Existing approaches either rely on frequent in-episode reasoning that induces latency and timing jitter, or deliver post-episode improvements through unstructured text that is difficult to compile into reliable low-cost execution. We propose CoWork-X, an active co-evolution framework that casts peer collaboration as a closed-loop optimization problem across episodes, inspired by fast--slow memory separation. CoWork-X instantiates a Skill-Agent that executes via HTN (hierarchical task network)-based skill retrieval from a structured, interpretable, and compositional skill library, and a post-episode Co-Optimizer that performs patch-style skill consolidation with explicit budget constraints and drift regularization. Experiments in challenging Overcooked-AI-like realtime collaboration benchmarks demonstrate that CoWork-X achieves stable, cumulative performance gains while steadily reducing online latency and token usage.

cs.CL↗

arXiv2026

Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework

As Embodied AI systems move from research prototypes to real world deployments, they tend to evolve rapidly while remaining reliable under workload changes and partial failures. In practice, many deployments are only partially decoupled: middleware moves messages, but shared context and feedback semantics are implicit, causing interface drift, cross-module interference, and brittle recovery at scale. We present ANCHOR, a modular framework that makes decoupling and robustness explicit system-level primitives. ANCHOR separates (i) Canonical Records, an evolvable contract for the standardized shared state, from (ii) a communication bus for many-to-many dissemination and feedback-oriented coordination, forming an inspectable end-to-end loop. We validate closed-loop feasibility on a de-identified workflow instantiation, characterize latency distributions under varying payload sizes and publish rates, and demonstrate automatic stream resumption after hard crashes and restarts even with shared-memory loss. Overall, ANCHOR turns ad-hoc integration glue into explicit contracts, enabling controlled degradation under load and self-healing recovery for scalable deployment of closed-loop AI systems.

cs.RO↗

arXiv2025

A Learning-based Control Methodology for Transitioning VTOL UAVs

Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods' decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process.

cs.RO↗

arXiv2025

EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Control

This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical tasks. Our approach integrates a next-action prediction paradigm with a structured memory system to decompose tasks into executable robot skills while dynamically validating actions against environmental constraints. We present MultiPlan+, a dataset of more than 18,000 annotated planning instances spanning 100 scenarios, including a subset of impractical cases to mitigate hallucination. To evaluate performance, we propose the Robot Planning Assessment Schema (RPAS), combining automated metrics with LLM-aided expert grading. Experiments demonstrate EmbodiedAgent's superiority over state-of-the-art models, achieving 71.85% RPAS score. Real-world validation in an office service task highlights its ability to coordinate heterogeneous robots for long-horizon objectives.

cs.RO↗

arXiv2025

GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control

Developing bipedal robots capable of traversing diverse real-world terrains presents a fundamental robotics challenge, as existing methods using predefined height maps and static environments fail to address the complexity of unstructured landscapes. To bridge this gap, we propose GenTe, a framework for generating physically realistic and adaptable terrains to train generalizable locomotion policies. GenTe constructs an atomic terrain library that includes both geometric and physical terrains, enabling curriculum training for reinforcement learning-based locomotion policies. By leveraging function-calling techniques and reasoning capabilities of Vision-Language Models (VLMs), GenTe generates complex, contextually relevant terrains from textual and graphical inputs. The framework introduces realistic force modeling for terrain interactions, capturing effects such as soil sinkage and hydrodynamic resistance. To the best of our knowledge, GenTe is the first framework that systemically generates simulation environments for legged robot locomotion control. Additionally, we introduce a benchmark of 100 generated terrains. Experiments demonstrate improved generalization and robustness in bipedal robot locomotion.

cs.RO↗

arXiv2023

Koopman-type inverse operator for linear non-minimum phase systems with disturbances

In this paper, a novel Koopman-type inverse operator for linear time-invariant non-minimum phase systems with stochastic disturbances is proposed. This operator employs functions of the desired output to directly calculate the input. Furthermore, it can be applied as a data-driven approach for systems with unknown parameters yet a known relative degree, which is a departure from the majority of existing data-driven methods that are only applicable to minimum phase systems. Based on this foundation, we use the Monte Carlo approach to develop an improved Koopman-type method for addressing the issue of inaccurate parameter estimation in data-driven systems with large disturbances. The simulation results justify the tracking accuracy of Koopman-type operator.

eess.SY↗

arXiv2022

Design and Control of the "TransBoat": A Transformable Unmanned Surface Vehicle for Overwater Construction

This paper presents the TransBoat, a novel omnidirectional unmanned surface vehicle (USV) with a magnetbased docking system for overwater construction with wave disturbances. This is the first such USV that can build overwater structures by transporting modules. The TransBoat incorporates two features designed to reject wave disturbances. First, the TransBoat's expandable body structure can actively transform from a mono-hull into a multi-hull for stabilization in turbulent environments by extending its four outrigger hulls. Second, a real-time nonlinear model predictive control (NMPC) scheme is proposed for all shapes of the TransBoat to enhance its maneuverability and resist disturbance to its movement, based on a nonlinear dynamic model. An experimental approach is proposed to identify the parameters of the dynamic model, and a subsequent trajectory tracking test validates the dynamics, NMPC controller and system mobility. Further, docking experiments identify improved performance in the expanded form of the TransBoat compared with the contracted form, including an increased success rate (of ~ 10%) and reduced docking time (of ~ 40 s on average). Finally, a bridge construction test verifies our system design and the NMPC control method.

cs.RO↗