arXiv subjects

Anqing Duan

Publications and source records attributed to Anqing Duan.

At least 19 recordsLinked to original sources

arXiv2026

Phase-and-First-Arrival VLM Feedback for Sparse-Reward Reinforcement Learning in Surgical Manipulation

Sparse outcome feedback limits what robots can learn from unsuccessful attempts at complex manipulation. Failed multi-stage surgical attempts can contain grasps, lifts, or transfers worth reusing. In sparse-reward reinforcement learning, terminal rewards collapse such attempts to the same outcome, while scalar vision-language model (VLM) ratings reveal neither what progress merits credit nor when it occurred. We introduce phase-and-first-arrival feedback: one VLM query per recorded episode identifies the furthest visually verified task phase and when that phase is first reached, allowing the learner to reuse partial behavior and localize credit. We instantiate it in SurgPhaseBench, a phase-structured suite spanning rigid and deformable tasks, and evaluate it in simulation and hardware. Across five simulated tasks, our method reaches 75.2% mean success, compared with 52.1% for a reward based on Contrastive Language-Image Pre-training (CLIP) using the same visual input; the advantage persists when only the feedback representation changes. On hardware, the same record supports autonomous block picking and slip recovery. Together, these results show that trajectory-level visual supervision can preserve partial progress while providing the temporal credit needed for sparse-reward control.

cs.RO↗

arXiv2026

Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics

Autonomous medical robots hold promise to improve patient outcomes, reduce provider workload, democratize access to care, and enable superhuman precision. However, autonomous medical robotics has been limited by a fundamental data problem: existing medical robotic datasets are small, single-embodiment, and rarely shared openly, restricting the development of foundation models that the field needs to advance. We introduce Open-H-Embodiment, the largest open dataset of medical robotic video with synchronized kinematics to date, spanning more than 50 institutions and multiple robotic platforms including the CMR Versius, Intuitive Surgical's da Vinci, da Vinci Research Kit (dVRK), Rob Surgical BiTrack, Virtual Incision's MIRA, Moon Surgical Maestro, and a variety of custom systems, spanning surgical manipulation, robotic ultrasound, and endoscopy procedures. We demonstrate the research enabled by this dataset through two foundation models. GR00T-H is the first open foundation vision-language-action model for medical robotics, which is the only evaluated model to achieve full end-to-end task completion on a structured suturing benchmark (25% of trials vs. 0% for all others) and achieves 64% average success across a 29-step ex vivo suturing sequence. We also train Cosmos-H-Surgical-Simulator, the first action-conditioned world model to enable multi-embodiment surgical simulation from a single checkpoint, spanning nine robotic platforms and supporting in silico policy evaluation and synthetic data generation for the medical domain. These results suggest that open, large-scale medical robot data collection can serve as critical infrastructure for the research community, enabling advances in robot learning, world modeling, and beyond.

cs.RO↗

arXiv2026

World2Act: Latent Action Post-Training from World Model Dynamics

World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve generalization under task and scene variation. However, most WM-based post-training methods rely on pixel-space supervision, making policies sensitive to visual artifacts introduced by imperfect WM rollouts. We present World2Act, a latent-space post-training framework that transfers WM dynamics to the VLA policy without pixel-space supervision. World2Act operates in two stages: 1) it induces a shared video-action latent space by contrastively aligning WM-dynamics latents with action embeddings, and 2) it post-trains the VLA by guiding policy action representations toward WM-imagined dynamics rather than decoded pixels. Built on GR00T-N1.6, World2Act delivers absolute success-rate gains of up to +2.5% on simulation benchmarks (RoboCasa, LIBERO, Bridge-SIMPLER) and +6.7% on a real robot over finetuned VLA baselines. Notably, it outperforms pixel-space WM supervision by up to +6.0%, including on LIBERO where pixel supervision degrades the baseline, suggesting that latent WM dynamics offer a more stable WM-based post-training alternative to pixel-space transfer.

cs.CV↗

arXiv2026

Choose What to Observe: Task-Aware Semantic-Geometric Representations for Visuomotor Policy

Visuomotor policies learned from demonstrations often overfit to nuisance visual factors in raw RGB observations, resulting in brittle behavior under appearance shifts such as background changes and object recoloring. We propose a task-aware observation interface that canonicalizes visual input into a shared representation, improving robustness to out-of-distribution (OOD) appearance changes without modifying or fine-tuning the policy. Given an RGB image and an open-vocabulary specification of task-relevant entities, we use SAM3 to segment the target object and robot/gripper. We construct an L0 observation by repainting segmented entities with predefined semantic colors on a constant background. For tasks requiring stronger geometric cues, we further inject monocular depth from Depth Anything 3 into the segmented regions via depth-guided overwrite, yielding a unified semantic--geometric observation (L1) that remains a standard 3-channel, image-like input. We evaluate on RoboMimic (Lift), ManiSkill YCB grasping under clutter, four RLBench tasks under controlled appearance shifts, and two real-world Franka tasks (ReachX and CloseCabinet). Across benchmarks and policy backbones (Flow Matching Policy and SmolVLA), our interface preserves in-distribution performance while substantially improving robustness under OOD visual shifts.

cs.RO↗

arXiv2025

3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning

Diffusion models have shown strong potential for robot skill learning, yet their role in coverage path planning remains underexplored. In industrial surface processing (painting, polishing, spray coating), high coverage requires globally ordered, temporally coherent trajectories rather than stitching unordered local segments. We reformulate coverage path planning as conditional sequence generation and adopt a geometry-conditioned diffusion framework that synthesizes continuous trajectories directly from raw 3D point clouds. Our method produces temporally ordered trajectory chunks and avoids post-hoc heuristic ordering or stitching in prior learning-based methods via simple sequential concatenation, improving sequence-level consistency. A single shared policy generalizes across different geometries without category-specific architectures. Extensive benchmarks show substantial gains over prior learning-based baselines: 98.2\% lower point-wise Chamfer Distance (lower is better), 97.0\% lower jerk (smoother trajectories), and +67.5 percentage points overlapping surface coverage on average.

cs.RO↗

arXiv2025

Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference

Visual observations from different viewpoints can significantly influence the performance of visuomotor policies in robotic manipulation. Among these, egocentric (in-hand) views often provide crucial information for precise control. However, in some applications, equipping robots with dedicated in-hand cameras may pose challenges due to hardware constraints, system complexity, and cost. In this work, we propose to endow robots with imaginative perception - enabling them to 'imagine' in-hand observations from agent views at inference time. We achieve this via novel view synthesis (NVS), leveraging a fine-tuned diffusion model conditioned on the relative pose between the agent and in-hand views cameras. Specifically, we apply LoRA-based fine-tuning to adapt a pretrained NVS model (ZeroNVS) to the robotic manipulation domain. We evaluate our approach on both simulation benchmarks (RoboMimic and MimicGen) and real-world experiments using a Unitree Z1 robotic arm for a strawberry picking task. Results show that synthesized in-hand views significantly enhance policy inference, effectively recovering the performance drop caused by the absence of real in-hand cameras. Our method offers a scalable and hardware-light solution for deploying robust visuomotor policies, highlighting the potential of imaginative visual reasoning in embodied agents.

cs.RO↗

arXiv2025

Towards Safe Imitation Learning via Potential Field-Guided Flow Matching

Deep generative models, particularly diffusion and flow matching models, have recently shown remarkable potential in learning complex policies through imitation learning. However, the safety of generated motions remains overlooked, particularly in complex environments with inherent obstacles. In this work, we address this critical gap by proposing Potential Field-Guided Flow Matching Policy (PF2MP), a novel approach that simultaneously learns task policies and extracts obstacle-related information, represented as a potential field, from the same set of successful demonstrations. During inference, PF2MP modulates the flow matching vector field via the learned potential field, enabling safe motion generation. By leveraging these complementary fields, our approach achieves improved safety without compromising task success across diverse environments, such as navigation tasks and robotic manipulation scenarios. We evaluate PF2MP in both simulation and real-world settings, demonstrating its effectiveness in task space and joint space control. Experimental results demonstrate that PF2MP enhances safety, achieving a significant reduction of collisions compared to baseline policies. This work paves the way for safer motion generation in unstructured and obstaclerich environments.

cs.RO↗

arXiv2025

Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation

Enabling humanoid robots to perform long-horizon mobile manipulation planning in real-world environments based on embodied perception and comprehension abilities has been a longstanding challenge. With the recent rise of large language models (LLMs), there has been a notable increase in the development of LLM-based planners. These approaches either utilize human-provided textual representations of the real world or heavily depend on prompt engineering to extract such representations, lacking the capability to quantitatively understand the environment, such as determining the feasibility of manipulating objects. To address these limitations, we present the Instruction-Augmented Long-Horizon Planning (IALP) system, a novel framework that employs LLMs to generate feasible and optimal actions based on real-time sensor feedback, including grounded knowledge of the environment, in a closed-loop interaction. Distinct from prior works, our approach augments user instructions into PDDL problems by leveraging both the abstract reasoning capabilities of LLMs and grounding mechanisms. By conducting various real-world long-horizon tasks, each consisting of seven distinct manipulatory skills, our results demonstrate that the IALP system can efficiently solve these tasks with an average success rate exceeding 80%. Our proposed method can operate as a high-level planner, equipping robots with substantial autonomy in unstructured environments through the utilization of multi-modal sensor inputs.

cs.RO↗

arXiv2025

Iterative Shaping of Multi-Particle Aggregates based on Action Trees and VLM

In this paper, we address the problem of manipulating multi-particle aggregates using a bimanual robotic system. Our approach enables the autonomous transport of dispersed particles through a series of shaping and pushing actions using robotically-controlled tools. Achieving this advanced manipulation capability presents two key challenges: high-level task planning and trajectory execution. For task planning, we leverage Vision Language Models (VLMs) to enable primitive actions such as tool affordance grasping and non-prehensile particle pushing. For trajectory execution, we represent the evolving particle aggregate's contour using truncated Fourier series, providing efficient parametrization of its closed shape. We adaptively compute trajectory waypoints based on group cohesion and the geometric centroid of the aggregate, accounting for its spatial distribution and collective motion. Through real-world experiments, we demonstrate the effectiveness of our methodology in actively shaping and manipulating multi-particle aggregates while maintaining high system cohesion.

cs.RO↗

arXiv2024

Non-Prehensile Tool-Object Manipulation by Integrating LLM-Based Planning and Manoeuvrability-Driven Controls

The ability to wield tools was once considered exclusive to human intelligence, but it's now known that many other animals, like crows, possess this capability. Yet, robotic systems still fall short of matching biological dexterity. In this paper, we investigate the use of Large Language Models (LLMs), tool affordances, and object manoeuvrability for non-prehensile tool-based manipulation tasks. Our novel method leverages LLMs based on scene information and natural language instructions to enable symbolic task planning for tool-object manipulation. This approach allows the system to convert a human language sentence into a sequence of feasible motion functions. We have developed a novel manoeuvrability-driven controller using a new tool affordance model derived from visual feedback. This controller helps guide the robot's tool utilization and manipulation actions, even within confined areas, using a stepping incremental approach. The proposed methodology is evaluated with experiments to prove its effectiveness under various manipulation scenarios.

cs.RO↗

arXiv2023

Explicit-Implicit Subgoal Planning for Long-Horizon Tasks with Sparse Reward

The challenges inherent in long-horizon tasks in robotics persist due to the typical inefficient exploration and sparse rewards in traditional reinforcement learning approaches. To address these challenges, we have developed a novel algorithm, termed Explicit-Implicit Subgoal Planning (EISP), designed to tackle long-horizon tasks through a divide-and-conquer approach. We utilize two primary criteria, feasibility and optimality, to ensure the quality of the generated subgoals. EISP consists of three components: a hybrid subgoal generator, a hindsight sampler, and a value selector. The hybrid subgoal generator uses an explicit model to infer subgoals and an implicit model to predict the final goal, inspired by way of human thinking that infers subgoals by using the current state and final goal as well as reason about the final goal conditioned on the current state and given subgoals. Additionally, the hindsight sampler selects valid subgoals from an offline dataset to enhance the feasibility of the generated subgoals. While the value selector utilizes the value function in reinforcement learning to filter the optimal subgoals from subgoal candidates. To validate our method, we conduct four long-horizon tasks in both simulation and the real world. The obtained quantitative and qualitative data indicate that our approach achieves promising performance compared to other baseline methods. These experimental results can be seen on the website \url{https://sites.google.com/view/vaesi}.

cs.RO↗

arXiv2023

Learning Rhythmic Trajectories with Geometric Constraints for Laser-Based Skincare Procedures

The increasing deployment of robots has significantly enhanced the automation levels across a wide and diverse range of industries. This paper investigates the automation challenges of laser-based dermatology procedures in the beauty industry; This group of related manipulation tasks involves delivering energy from a cosmetic laser onto the skin with repetitive patterns. To automate this procedure, we propose to use a robotic manipulator and endow it with the dexterity of a skilled dermatology practitioner through a learning-from-demonstration framework. To ensure that the cosmetic laser can properly deliver the energy onto the skin surface of an individual, we develop a novel structured prediction-based imitation learning algorithm with the merit of handling geometric constraints. Notably, our proposed algorithm effectively tackles the imitation challenges associated with quasi-periodic motions, a common feature of many laser-based cosmetic tasks. The conducted real-world experiments illustrate the performance of our robotic beautician in mimicking realistic dermatological procedures; Our new method is shown to not only replicate the rhythmic movements from the provided demonstrations but also to adapt the acquired skills to previously unseen scenarios and subjects.

cs.RO↗

arXiv2023

A Structured Prediction Approach for Robot Imitation Learning

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework.

cs.RO↗

arXiv2023

PSO-Based Optimal Coverage Path Planning for Surface Defect Inspection of 3C Components with a Robotic Line Scanner

The automatic inspection of surface defects is an important task for quality control in the computers, communications, and consumer electronics (3C) industry. Conventional devices for defect inspection (viz. line-scan sensors) have a limited field of view, thus, a robot-aided defect inspection system needs to scan the object from multiple viewpoints. Optimally selecting the robot's viewpoints and planning a path is regarded as coverage path planning (CPP), a problem that enables inspecting the object's complete surface while reducing the scanning time and avoiding misdetection of defects. However, the development of CPP strategies for robotic line scanners has not been sufficiently studied by researchers. To fill this gap in the literature, in this paper, we present a new approach for robotic line scanners to detect surface defects of 3C free-form objects automatically. Our proposed solution consists of generating a local path by a new hybrid region segmentation method and an adaptive planning algorithm to ensure the coverage of the complete object surface. An optimization method for the global path sequence is developed to maximize the scanning efficiency. To verify our proposed methodology, we conduct detailed simulation-based and experimental studies on various free-form workpieces, and compare its performance with a state-of-the-art solution. The reported results demonstrate the feasibility and effectiveness of our approach.

cs.RO↗

arXiv2023

Efficient Robot Skill Learning with Imitation from a Single Video for Contact-Rich Fabric Manipulation

Classical policy search algorithms for robotics typically require performing extensive explorations, which are time-consuming and expensive to implement with real physical platforms. To facilitate the efficient learning of robot manipulation skills, in this work, we propose a new approach comprised of three modules: (1) learning of general prior knowledge with random explorations in simulation, including state representations, dynamic models, and the constrained action space of the task; (2) extraction of a state alignment-based reward function from a single demonstration video; (3) real-time optimization of the imitation policy under systematic safety constraints with sampling-based model predictive control. This solution results in an efficient one-shot imitation-from-video strategy that simplifies the learning and execution of robot skills in real applications. Specifically, we learn priors in a scene of a task family and then deploy the policy in a novel scene immediately following a single demonstration, preventing time-consuming and risky explorations in the environment. As we do not make a strong assumption of dynamic consistency between the scenes, learning priors can be conducted in simulation to avoid collecting data in real-world circumstances. We evaluate the effectiveness of our approach in the context of contact-rich fabric manipulation, which is a common scenario in industrial and domestic tasks. Detailed numerical simulations and real-world hardware experiments reveal that our method can achieve rapid skill acquisition for challenging manipulation tasks.

cs.RO↗

arXiv2022

Ultrasound-Guided Assistive Robots for Scoliosis Assessment with Optimization-based Control and Variable Impedance

Assistive robots for healthcare have seen a growing demand due to the great potential of relieving medical practitioners from routine jobs. In this paper, we investigate the development of an optimization-based control framework for an ultrasound-guided assistive robot to perform scoliosis assessment. A conventional procedure for scoliosis assessment with ultrasound imaging typically requires a medical practitioner to slide an ultrasound probe along a patient's back. To automate this type of procedure, we need to consider multiple objectives, such as contact force, position, orientation, energy, posture, etc. To address the aforementioned components, we propose to formulate the control framework design as a quadratic programming problem with each objective weighed by its task priority subject to a set of equality and inequality constraints. In addition, as the robot needs to establish constant contact with the patient during spine scanning, we incorporate variable impedance regulation of the end-effector position and orientation in the control architecture to enhance safety and stability during the physical human-robot interaction. Wherein, the variable impedance gains are retrieved by learning from the medical expert's demonstrations. The proposed methodology is evaluated by conducting real-world experiments of autonomous scoliosis assessment with a robot manipulator xArm. The effectiveness is verified by the obtained coronal spinal images of both a phantom and a human subject.

cs.RO↗

arXiv2021

Keypoint-Based Bimanual Shaping of Deformable Linear Objects under Environmental Constraints using Hierarchical Action Planning

This paper addresses the problem of contact-based manipulation of deformable linear objects (DLOs) towards desired shapes with a dual-arm robotic system. To alleviate the burden of high-dimensional continuous state-action spaces, we model the DLO as a kinematic multibody system via our proposed keypoint detection network. This new perception network is trained on a synthetic labeled image dataset and transferred to real manipulation scenarios without conducting any manual annotations. Our goal-conditioned policy can efficiently learn to rearrange the configuration of the DLO based on the detected keypoints. The proposed hierarchical action framework tackles the manipulation problem in a coarse-to-fine manner (with high-level task planning and low-level motion control) by leveraging on two action primitives. The identification of deformation properties is avoided since the algorithm replans its motion after each bimanual execution. The conducted experimental results reveal that our method achieves high performance in state representation of the DLO, and is robust to uncertain environmental constraints.

cs.RO↗

arXiv2021

Learning Cloth Folding Tasks with Refined Flow Based Spatio-Temporal Graphs

Cloth folding is a widespread domestic task that is seemingly performed by humans but which is highly challenging for autonomous robots to execute due to the highly deformable nature of textiles; It is hard to engineer and learn manipulation pipelines to efficiently execute it. In this paper, we propose a new solution for robotic cloth folding (using a standard folding board) via learning from demonstrations. Our demonstration video encoding is based on a high-level abstraction, namely, a refined optical flow-based spatiotemporal graph, as opposed to a low-level encoding such as image pixels. By constructing a new spatiotemporal graph with an advanced visual corresponding descriptor, the policy learning can focus on key points and relations with a 3D spatial configuration, which allows to quickly generalize across different environments. To further boost the policy searching, we combine optical flow and static motion saliency maps to discriminate the dominant motions for better handling the system dynamics in real-time, which aligns with the attentional motion mechanism that dominates the human imitation process. To validate the proposed approach, we analyze the manual folding procedure and developed a custom-made end-effector to efficiently interact with the folding board. Multiple experiments on a real robotic platform were conducted to validate the effectiveness and robustness of the proposed method.

cs.RO↗