arXiv subjects

Yu Zhan

Publications and source records attributed to Yu Zhan.

17 recordsLinked to original sources

arXiv2026

Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations

Robot crowd navigation requires the ability to infer human intentions while accounting for the structural constraints of the environment. Currently, deep reinforcement learning (DRL) provides a promising method for learning navigation policies that understand human intentions. However, most of them rely on limited scene representations, treating pedestrians as simple 2D points and ignoring rich visual cues from both humans and the environment. To address this issue, we introduce iCrowdNav, a novel visual crowd navigation method with intention-aware scene representations, to encode behavioral and structural context from egocentric visual observations. Our method employs two key components: a spatio-temporal encoder for extracting occupancy features of the scene, and Intent-Interact Former (I$^2$ Former), an attention-based module that encodes human poses to infer pedestrians' motion intentions. These features are integrated into a compact state embedding that supports effective DRL policy training. Extensive experiments show that our method achieves superior performance over baselines, and real-world deployment demonstrates vision-based crowd navigation.

cs.RO↗

arXiv2026

Can Single-View Mesh Reconstruction Generalize to Robot Camera Rotation?

Single-view mesh reconstruction predicts object meshes and spatial layouts from a single observation, making it attractive for fast robot spatial reasoning and real-to-sim digital twins. However, robot-mounted cameras naturally rotate during manipulation and navigation, while learned single-view reconstruction models often rely on view-dependent priors and may generalize poorly to out-of-distribution camera rotations. Such rotations can introduce 3D inconsistencies, incorrect layouts, and violations of physical constraints, but this failure mode remains under-evaluated. We introduce an evaluation protocol with controlled axis-wise roll, pitch, and yaw sweeps to trace errors in monocular depth estimation (MDE), canonical object meshes, camera-space layout, and physical plausibility within a representative SAM3D-style pipeline. On the Aria Digital Twin dataset and a real Franka wrist-camera sequence, camera rotations induce MDE distortion, layout drift, and collision penetration, while canonical mesh predictions remain relatively stable. A two-stage SAM3D+FoundationPose pipeline is more robust than one-stage feed-forward layout prediction, and our Gravity-Aware Refinement reduces one-stage pairwise ICP-based layout-orientation error by 47.1$\%$. Our evaluation reveals that current single-view mesh reconstruction methods generalize poorly to robot camera rotation, and suggests that explicit gravity cues are important for reliable robotic single-view mesh reconstruction.

cs.CV↗

arXiv2026

Fitting Unknown Number of Hyperplanes with Manifold Optimization

Fitting an unknown number of hyperplanes to data is a fundamental yet challenging problem in machine learning, characterized by its non-convexity, non-differentiability, and unknown model order. Existing approaches often struggle with local optima or lack geometric consistency. To address these limitations, we propose a novel framework based on Manifold Optimization. We reformulate the problem as an unsupervised learning task on the unit sphere manifold $\mathcal{S}^{\textbf{dim}-1}$. This formulation effectively handles the non-convex constraints and linearizes the distance measurement, rendering the gradient descent tractable. We propose a Two-Stage Manifold Optimization algorithm. In Phase I, we employ a Riemannian Expectation-Maximization process with a heavy-tailed kernel to robustly estimate posterior probabilities, effectively resolving the ambiguities of point distribution between intersecting hyperplanes. In Phase II, upon convergence of the soft estimates, the probabilistic weights degenerate into hard matching, generating a precise local optimum that strictly satisfies the geometric definition. Furthermore, we introduce a projected density estimation strategy for initialization to facilitate global convergence by significantly reducing the feature description space and search complexity. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines in both geometric accuracy and robustness.

cs.LG↗

arXiv2025

SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation

Deploying massive diffusion models for real-time, infinite-duration, audio-driven avatar generation presents a significant engineering challenge, primarily due to the conflict between computational load and strict latency constraints. Existing approaches often compromise visual fidelity by enforcing strictly unidirectional attention mechanisms or reducing model capacity. To address this problem, we introduce \textbf{SoulX-FlashTalk}, a 14B-parameter framework optimized for high-fidelity real-time streaming. Diverging from conventional unidirectional paradigms, we use a \textbf{Self-correcting Bidirectional Distillation} strategy that retains bidirectional attention within video chunks. This design preserves critical spatiotemporal correlations, significantly enhancing motion coherence and visual detail. To ensure stability during infinite generation, we incorporate a \textbf{Multi-step Retrospective Self-Correction Mechanism}, enabling the model to autonomously recover from accumulated errors and preventing collapse. Furthermore, we engineered a full-stack inference acceleration suite incorporating hybrid sequence parallelism, Parallel VAE, and kernel-level optimizations. Extensive evaluations confirm that SoulX-FlashTalk is the first 14B-scale system to achieve a \textbf{sub-second start-up latency (0.87s)} while reaching a real-time throughput of \textbf{32 FPS}, setting a new standard for high-fidelity interactive digital human synthesis.

cs.CV↗

arXiv2025

MfNeuPAN: Proactive End-to-End Navigation in Dynamic Environments via Direct Multi-Frame Point Constraints

Obstacle avoidance in complex and dynamic environments is a critical challenge for real-time robot navigation. Model-based and learning-based methods often fail in highly dynamic scenarios because traditional methods assume a static environment and cannot adapt to real-time changes, while learning-based methods rely on single-frame observations for motion constraint estimation, limiting their adaptability. To overcome these limitations, this paper proposes a novel framework that leverages multi-frame point constraints, including current and future frames predicted by a dedicated module, to enable proactive end-to-end navigation. By incorporating a prediction module that forecasts the future path of moving obstacles based on multi-frame observations, our method allows the robot to proactively anticipate and avoid potential dangers. This proactive planning capability significantly enhances navigation robustness and efficiency in unknown dynamic environments. Simulations and real-world experiments validate the effectiveness of our approach.

cs.RO↗

arXiv2025

Adap-RPF: Adaptive Trajectory Sampling for Robot Person Following in Dynamic Crowded Environments

Robot person following (RPF) is a core capability in human-robot interaction, enabling robots to assist users in daily activities, collaborative work, and other service scenarios. However, achieving practical RPF remains challenging due to frequent occlusions, particularly in dynamic and crowded environments. Existing approaches often rely on fixed-point following or sparse candidate-point selection with oversimplified heuristics, which cannot adequately handle complex occlusions caused by moving obstacles such as pedestrians. To address these limitations, we propose an adaptive trajectory sampling method that generates dense candidate points within socially aware zones and evaluates them using a multi-objective cost function. Based on the optimal point, a person-following trajectory is estimated relative to the predicted motion of the target. We further design a prediction-aware model predictive path integral (MPPI) controller that simultaneously tracks this trajectory and proactively avoids collisions using predicted pedestrian motions. Extensive experiments show that our method outperforms state-of-the-art baselines in smoothness, safety, robustness, and human comfort, with its effectiveness further demonstrated on a mobile robot in real-world scenarios.

cs.RO↗

arXiv2025

Follow-Bench: A Unified Motion Planning Benchmark for Socially-Aware Robot Person Following

Robot person following (RPF) -- mobile robots that follow and assist a specific person -- has emerging applications in personal assistance, security patrols, eldercare, and logistics. To be effective, such robots must follow the target while ensuring safety and comfort for both the target and surrounding people. In this work, we present the first comprehensive study of RPF, which (i) surveys representative scenarios, motion-planning methods, and evaluation metrics with a focus on safety and comfort; (ii) introduces Follow-Bench, a unified benchmark simulating diverse scenarios, including various target trajectory patterns, crowd dynamics, and environmental layouts; and (iii) re-implements eight representative RPF planners, ensuring that both safety and comfort are systematically considered. Moreover, we evaluate the two best-performing planners from our benchmark on a differential-drive robot to provide insights into real-world deployment of RPF planners. Extensive simulation and real-world experiments provide quantitative study of the safety-comfort trade-offs of existing planners, while revealing open challenges and future research directions.

cs.RO↗

arXiv2025

TPT-Bench: A Large-Scale, Long-Term and Robot-Egocentric Dataset for Benchmarking Target Person Tracking

Tracking a target person from robot-egocentric views is crucial for developing autonomous robots that provide continuous personalized assistance or collaboration in Human-Robot Interaction (HRI) and Embodied AI. However, most existing target person tracking (TPT) benchmarks are limited to controlled laboratory environments with few distractions, clean backgrounds, and short-term occlusions. In this paper, we introduce a large-scale dataset designed for TPT in crowded and unstructured environments, demonstrated through a robot-person following task. The dataset is collected by a human pushing a sensor-equipped cart while following a target person, capturing human-like following behavior and emphasizing long-term tracking challenges, including frequent occlusions and the need for re-identification from numerous pedestrians. It includes multi-modal data streams, including odometry, 3D LiDAR, IMU, panoramic images, and RGB-D images, along with exhaustively annotated 2D bounding boxes of the target person across 48 sequences, both indoors and outdoors. Using this dataset and visual annotations, we perform extensive experiments with existing SOTA TPT methods, offering a thorough analysis of their limitations and suggesting future research directions.

cs.RO↗

arXiv2025

RPF-Search: Field-based Search for Robot Person Following in Unknown Dynamic Environments

Autonomous robot person-following (RPF) systems are crucial for personal assistance and security but suffer from target loss due to occlusions in dynamic, unknown environments. Current methods rely on pre-built maps and assume static environments, limiting their effectiveness in real-world settings. There is a critical gap in re-finding targets under topographic (e.g., walls, corners) and dynamic (e.g., moving pedestrians) occlusions. In this paper, we propose a novel heuristic-guided search framework that dynamically builds environmental maps while following the target and explicitly addresses these two types of occlusions through distinct mechanisms. For topographic occlusions, a belief-guided search field estimates the likelihood of the target's presence and guides search toward promising frontiers. For dynamic occlusions, an observation-based search strategy adaptively switches between a fluid-following field and an overtaking potential field based on occluder motion patterns. Our results demonstrate that the proposed method outperforms existing approaches in terms of search efficiency and success rates, both in simulations and real-world tests. Our target search method enhances the adaptability and reliability of RPF systems in unknown and dynamic environments, supporting their use in real-world applications.

cs.RO↗

arXiv2025

Monocular Person Localization under Camera Ego-motion

Localizing a person from a moving monocular camera is critical for Human-Robot Interaction (HRI). To estimate the 3D human position from a 2D image, existing methods either depend on the geometric assumption of a fixed camera or use a position regression model trained on datasets containing little camera ego-motion. These methods are vulnerable to severe camera ego-motion, resulting in inaccurate person localization. We consider person localization as a part of a pose estimation problem. By representing a human with a four-point model, our method jointly estimates the 2D camera attitude and the person's 3D location through optimization. Evaluations on both public datasets and real robot experiments demonstrate our method outperforms baselines in person localization accuracy. Our method is further implemented into a person-following system and deployed on an agile quadruped robot.

cs.CV↗

arXiv2024

The weak form method for acoustoelastic simulation with arbitrary prestress

Acoustoelastic theory has been widely used to evaluate the residual stress (or prestress). However, most of the research remains focused on plate under simple tensile stress condition. In this paper, we propose a new approach: using weak form PDE modeling for acoustoelastic simulation. In the theory part, the weak form of acoustoelastic theory and semi-analytical finite element (SAFE) method is derived. In the numerical simulation part, two cases: the propagation direction is perpendicular to the prestress and parallel to the prestress are presented. The results are compared with the superposition of partial bulk wave (SPBW) method and the previously commonly used Effective Elastic Constants (EEC) method. The results show that the method proposed in this paper is highly accurate. Compared to the EEC method, this approach has no theoretical flaws and aligns more closely with the theoretical solution, especially in the low frequency range where the EEC method's results are almost incorrect. This study provides an accurate method for the simulation of acoustoelasticity.

physics.app-ph↗

arXiv2024

A new approach for the inversion of residual stress based on acoustoelasticity theory and full waveform inversion

Acoustoelasticity theory has been widely used to evaluate the residual stress (or prestress), almost all the available ultrasonic stress detection methods are based on the relationship between the magnitude of stress and wave speed, but these measurement methods make the assumption that the stress is uniform, only one point or average stress in the direction of ultrasound propagation can be obtained. However, the real stress distribution is usually nonuniform. In order to obtain the stress distribution in the direction of ultrasound propagation, in this paper, we propose a new approach: the inversion of residual stress. In the theory part, the inversion of residual stress is transformed into an optimization problem. The objective function is established, and the gradient of the objective function to the stress is derived using the adjoint method, which has been maturely applied in full waveform inversion. In the numerical simulation part, the welding process is simulated using the finite element method to obtain a database of the residual stress field. Then the residual stress is evaluated by inversion approach and the influence of the number of sources and receivers and the frequency of the excitation wave on the inversion effect is discussed. The results show that the inversion of residual stress is still challenging with a small amount of data, but a more accurate inversion can be obtained by appropriately increasing the number of sources and receivers. This study provides an appropriate method for the evaluation of residual stress distribution and lays the theoretical and simulation foundation for the application of ultrasonic stress testing in it.

physics.app-ph↗

arXiv2024

Human Orientation Estimation under Partial Observation

Reliable Human Orientation Estimation (HOE) from a monocular image is critical for autonomous agents to understand human intention. Significant progress has been made in HOE under full observation. However, the existing methods easily make a wrong prediction under partial observation and give it an unexpectedly high confidence. To solve the above problems, this study first develops a method called Part-HOE that estimates orientation from the visible joints of a target person so that it is able to handle partial observation. Subsequently, we introduce a confidence-aware orientation estimation method, enabling more accurate orientation estimation and reasonable confidence estimation under partial observation. The effectiveness of our method is validated on both public and custom-built datasets, and it shows great accuracy and reliability improvement in partial observation scenarios. In particular, we show in real experiments that our method can benefit the robustness and consistency of the Robot Person Following (RPF) task.

cs.RO↗

arXiv2023

Person Re-Identification for Robot Person Following with Online Continual Learning

Robot person following (RPF) is a crucial capability in human-robot interaction (HRI) applications, allowing a robot to persistently follow a designated person. In practical RPF scenarios, the person can often be occluded by other objects or people. Consequently, it is necessary to re-identify the person when he/she reappears within the robot's field of view. Previous person re-identification (ReID) approaches to person following rely on a fixed feature extractor. Such an approach often fails to generalize to different viewpoints and lighting conditions in practical RPF environments. In other words, it suffers from the so-called domain shift problem where it cannot re-identify the person when his re-appearance is out of the domain modeled by the fixed feature extractor. To mitigate this problem, we propose a ReID framework for RPF where we use a feature extractor that is optimized online with both short-term and long-term experiences (i.e., recently and previously observed samples during RPF) using the online continual learning (OCL) framework. The long-term experiences are maintained by a memory manager to enable OCL to update the feature extractor. Our experiments demonstrate that even in the presence of severe appearance changes and distractions from visually similar people, the proposed method can still re-identify the person more accurately than the state-of-the-art methods.

cs.RO↗

arXiv2023

HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks

Hypergraph neural networks (HGNN) have shown superior performance in various deep learning tasks, leveraging the high-order representation ability to formulate complex correlations among data by connecting two or more nodes through hyperedge modeling. Despite the well-studied adversarial attacks on Graph Neural Networks (GNN), there is few study on adversarial attacks against HGNN, which leads to a threat to the safety of HGNN applications. In this paper, we introduce HyperAttack, the first white-box adversarial attack framework against hypergraph neural networks. HyperAttack conducts a white-box structure attack by perturbing hyperedge link status towards the target node with the guidance of both gradients and integrated gradients. We evaluate HyperAttack on the widely-used Cora and PubMed datasets and three hypergraph neural networks with typical hypergraph modeling techniques. Compared to state-of-the-art white-box structural attack methods for GNN, HyperAttack achieves a 10-20X improvement in time efficiency while also increasing attack success rates by 1.3%-3.7%. The results show that HyperAttack can achieve efficient adversarial attacks that balance effectiveness and time costs.

cs.LG↗

arXiv2022

Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization

In this paper, we propose a novel monocular ray-based 3D (Ray3D) absolute human pose estimation with calibrated camera. Accurate and generalizable absolute 3D human pose estimation from monocular 2D pose input is an ill-posed problem. To address this challenge, we convert the input from pixel space to 3D normalized rays. This conversion makes our approach robust to camera intrinsic parameter changes. To deal with the in-the-wild camera extrinsic parameter variations, Ray3D explicitly takes the camera extrinsic parameters as an input and jointly models the distribution between the 3D pose rays and camera extrinsic parameters. This novel network design is the key to the outstanding generalizability of Ray3D approach. To have a comprehensive understanding of how the camera intrinsic and extrinsic parameter variations affect the accuracy of absolute 3D key-point localization, we conduct in-depth systematic experiments on three single person 3D benchmarks as well as one synthetic benchmark. These experiments demonstrate that our method significantly outperforms existing state-of-the-art models. Our code and the synthetic dataset are available at https://github.com/YxZhxn/Ray3D .

cs.CV↗

arXiv2018

Instance Search via Instance Level Segmentation and Feature Representation

Instance search is an interesting task as well as a challenging issue due to the lack of effective feature representation. In this paper, an instance level feature representation built upon fully convolutional instance-aware segmentation is proposed. The feature is ROI-pooled from the segmented instance region. So that instances in various sizes and layouts are represented by deep features in uniform length. This representation is further enhanced by the use of deformable ResNeXt blocks. Superior performance is observed in terms of its distinctiveness and scalability on a challenging evaluation dataset built by ourselves. In addition, the proposed enhancement on the network structure also shows superior performance on the instance segmentation task.

cs.CV↗