arXiv subjects

Zhirui Sun

Publications and source records attributed to Zhirui Sun.

18 recordsLinked to original sources

arXiv2026

CrossTracer: Cross-Embodiment Navigation via VLA Model Reasoning and Trace Residuals Adapting

Vision-language-action (VLA) models provide strong semantic priors for robot navigation, but they often ignore embodiment-specific mobility constraints. A path that is semantically plausible for one robot may be physically infeasible for another. We propose CrossTracer, a hierarchical framework for cross-embodiment navigation through adaptive trace residuals. CrossTracer represents navigation plans as normalized image-plane waypoints, forming a unified pixel-space interface between semantic reasoning and physical grounding. First, Vision-Language Trace Proposer (VL-Tracer) adapts a pretrained VLA model to predict an initial navigation trace from egocentric observations and flexible goal specifications. Second, CE-Adapter refines this trace by predicting embodiment-conditioned residual corrections from visual traversability cues, robot identity, and the initial trace. To train the refinement module without costly manual annotation, Cross-Embodiment RRT* (CE-RRT*) converts panoptic segmentation into robot-conditioned traversability cost maps and generates cost-minimizing pixel-space traces. We evaluate CrossTracer on the NaviTrace benchmark, which tests whether a model can generate embodiment-consistent navigation traces from egocentric observations, language instructions, and robot embodiment types. CrossTracer achieves a total score of 45.68, outperforming the strongest evaluated general-purpose baseline, Gemini-2.5-Pro, by 10.01 points, corresponding to a 28.1% relative improvement. Real-world deployment on wheeled and legged robots further shows improved navigation success and execution efficiency.

cs.RO↗

arXiv2026

UMCP: A Unified Multi-Task Collaborative Perception Network for Luggage Trolley Pose Estimation

In robotic autonomous luggage trolley collection, robots must continuously localize scattered luggage trolleys in cluttered and dynamic environments. This requires the vision system to achieve both high accuracy and real-time performance. However, existing visual perception approaches for luggage trolleys often rely on cascaded multi-model inference, leading to increased inference latency and high deployment costs. To address these limitations, this article presents a unified multi-task collaborative perception network (UMCP) that simultaneously performs luggage trolley detection, keypoint detection and orientation estimation. Based on the YOLOv12 architecture, keypoint features are fused with orientation features and then fed into an orientation feature enhancement module (OFEM), thereby improving orientation estimation accuracy. In addition, circular probability distribution modeling with a Kullback-Leibler (KL) divergence loss is adopted to enhance orientation estimation accuracy further. Experimental results demonstrate that the proposed method achieves competitive overall accuracy while substantially reducing model complexity and computational cost compared with existing methods. A website about this work is available at https://sites.google.com/view/robot-umcp.

cs.RO↗

arXiv2025

Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation

Frame-level autoregressive (frame-AR) models have achieved significant progress, enabling real-time video generation comparable to bidirectional diffusion models and serving as a foundation for interactive world models and game engines. However, current approaches in long video generation typically rely on window attention, which naively discards historical context outside the window, leading to catastrophic forgetting and scene inconsistency; conversely, retaining full history incurs prohibitive memory costs. To address this trade-off, we propose Memorize-and-Generate (MAG), a framework that decouples memory compression and frame generation into distinct tasks. Specifically, we train a memory model to compress historical information into a compact KV cache, and a separate generator model to synthesize subsequent frames utilizing this compressed representation. Furthermore, we introduce MAG-Bench to strictly evaluate historical memory retention. Extensive experiments demonstrate that MAG achieves superior historical scene consistency while maintaining competitive performance on standard video generation benchmarks.

cs.CV↗

arXiv2025

SONAR: Semantic-Object Navigation with Aggregated Reasoning through a Cross-Modal Inference Paradigm

Understanding human instructions and accomplishing Vision-Language Navigation tasks in unknown environments is essential for robots. However, existing modular approaches heavily rely on the quality of training data and often exhibit poor generalization. Vision-Language Model based methods, while demonstrating strong generalization capabilities, tend to perform unsatisfactorily when semantic cues are weak. To address these issues, this paper proposes SONAR, an aggregated reasoning approach through a cross modal paradigm. The proposed method integrates a semantic map based target prediction module with a Vision-Language Model based value map module, enabling more robust navigation in unknown environments with varying levels of semantic cues, and effectively balancing generalization ability with scene adaptability. In terms of target localization, we propose a strategy that integrates multi-scale semantic maps with confidence maps, aiming to mitigate false detections of target objects. We conducted an evaluation of the SONAR within the Gazebo simulator, leveraging the most challenging Matterport 3D (MP3D) dataset as the experimental benchmark. Experimental results demonstrate that SONAR achieves a success rate of 38.4% and an SPL of 17.7%.

cs.RO↗

arXiv2025

DA-VPC: Disturbance-Aware Visual Predictive Control Scheme of Docking Maneuvers for Autonomous Trolley Collection

Service robots have demonstrated significant potential for autonomous trolley collection and redistribution in public spaces like airports or warehouses to improve efficiency and reduce cost. Usually, a fully autonomous system for the collection and transportation of multiple trolleys is based on a Leader-Follower formation of mobile manipulators, where reliable docking maneuvers of the mobile base are essential to align trolleys into organized queues. However, developing a vision-based robotic docking system faces significant challenges: high precision requirements, environmental disturbances, and inherent robot constraints. To address these challenges, we propose a Disturbance-Aware Visual Predictive Control (DA-VPC) scheme that incorporates active infrared markers for robust feature extraction across diverse lighting conditions. This framework explicitly models nonholonomic kinematics and visibility constraints for image-based visual servoing (IBVS), solving the predictive control problem through optimization. It is augmented with an extended state observer (ESO) designed to counteract disturbances during trolley pushing, ensuring precise and stable docking. Experimental results across diverse environments demonstrate the robustness of this system, with quantitative evaluations confirming high docking accuracy.

cs.RO↗

arXiv2025

Integrating Maneuverable Planning and Adaptive Control for Robot Cart-Pushing under Disturbances

Precise and flexible cart-pushing is a challenging task for mobile robots. The motion constraints during cart-pushing and the robot's redundancy lead to complex motion planning problems, while variable payloads and disturbances present complicated dynamics. In this work, we propose a novel planning and control framework for flexible whole-body coordination and robust adaptive control. Our motion planning method employs a local coordinate representation and a novel kinematic model to solve a nonlinear optimization problem, thereby enhancing motion maneuverability by generating feasible and flexible push poses. Furthermore, we present a disturbance rejection control method to resist disturbances and reduce control errors for the complex control problem without requiring an accurate dynamic model. We validate our method through extensive experiments in simulation and real-world settings, demonstrating its superiority over existing approaches. To the best of our knowledge, this is the first work to systematically evaluate the flexibility and robustness of cart-pushing methods in experiments. The video supplement is available at https://sites.google.com/view/mpac-pushing/.

cs.RO↗

arXiv2025

Socially Aware Robot Crowd Navigation via Online Uncertainty-Driven Risk Adaptation

Navigation in human-robot shared crowded environments remains challenging, as robots are expected to move efficiently while respecting human motion conventions. However, many existing approaches emphasize safety or efficiency while overlooking social awareness. This article proposes Learning-Risk Model Predictive Control (LR-MPC), a data-driven navigation algorithm that balances efficiency, safety, and social awareness. LR-MPC consists of two phases: an offline risk learning phase, where a Probabilistic Ensemble Neural Network (PENN) is trained using risk data from a heuristic MPC-based baseline (HR-MPC), and an online adaptive inference phase, where local waypoints are sampled and globally guided by a Multi-RRT planner. Each candidate waypoint is evaluated for risk by PENN, and predictions are filtered using epistemic and aleatoric uncertainty to ensure robust decision-making. The safest waypoint is selected as the MPC input for real-time navigation. Extensive experiments demonstrate that LR-MPC outperforms baseline methods in success rate and social awareness, enabling robots to navigate complex crowds with high adaptability and low disruption. A website about this work is available at https://sites.google.com/view/lr-mpc.

cs.RO↗

arXiv2025

A Predictive Cooperative Collision Avoidance for Multi-Robot Systems Using Control Barrier Function

Control barrier function (CBF)-based methods provide the minimum modification necessary to formally guarantee safety in the context of quadratic programming, and strict safety guarantee for safety critical systems. However, most CBF-related derivatives myopically focus on present safety at each time step, a reasoning over a look-ahead horizon is exactly missing. In this paper, a predictive safety matrix is constructed. We then consolidate the safety condition based on the smallest eigenvalue of the proposed safety matrix. A predefined deconfliction strategy of motion paths is embedded into the trajectory tracking module to manage deadlock conflicts, which computes the deadlock escape velocity with the minimum attitude angle. Comparison results show that the introduction of the predictive term is robust for measurement uncertainty and is immune to oscillations. The proposed deadlock avoidance method avoids a large detour, without obvious stagnation.

eess.SY↗

arXiv2025

Collision Risk Quantification and Conflict Resolution in Trajectory Tracking for Acceleration-Actuated Multi-Robot Systems

One of the pivotal challenges in a multi-robot system is how to give attention to accuracy and efficiency while ensuring safety. Prior arts cannot strictly guarantee collision-free for an arbitrarily large number of robots or the results are considerably conservative. Smoothness of the avoidance trajectory also needs to be further optimized. This paper proposes an accelerationactuated simultaneous obstacle avoidance and trajectory tracking method for arbitrarily large teams of robots, that provides a nonconservative collision avoidance strategy and gives approaches for deadlock avoidance. We propose two ways of deadlock resolution, one involves incorporating an auxiliary velocity vector into the error function of the trajectory tracking module, which is proven to have no influence on global convergence of the tracking error. Furthermore, unlike the traditional methods that they address conflicts after a deadlock occurs, our decision-making mechanism avoids the near-zero velocity, which is much more safer and efficient in crowed environments. Extensive comparison show that the proposed method is superior to the existing studies when deployed in a large-scale robot system, with minimal invasiveness.

cs.RO↗

arXiv2024

NAMR-RRT: Neural Adaptive Motion Planning for Mobile Robots in Dynamic Environments

Robots are increasingly deployed in dynamic and crowded environments, such as urban areas and shopping malls, where efficient and robust navigation is crucial. Traditional risk-based motion planning algorithms face challenges in such scenarios due to the lack of a well-defined search region, leading to inefficient exploration in irrelevant areas. While bi-directional and multi-directional search strategies can improve efficiency, they still result in significant unnecessary exploration. This article introduces the Neural Adaptive Multi-directional Risk-based Rapidly-exploring Random Tree (NAMR-RRT) to address these limitations. NAMR-RRT integrates neural network-generated heuristic regions to dynamically guide the exploration process, continuously refining the heuristic region and sampling rates during the planning process. This adaptive feature significantly enhances performance compared to neural-based methods with fixed heuristic regions and sampling rates. NAMR-RRT improves planning efficiency, reduces trajectory length, and ensures higher success by focusing the search on promising areas and continuously adjusting to environments. The experiment results from both simulations and real-world applications demonstrate the robustness and effectiveness of our proposed method in navigating dynamic environments. A website about this work is available at https://sites.google.com/view/namr-rrt.

cs.RO↗

arXiv2024

LSTP-Nav: Lightweight Spatiotemporal Policy for Map-free Multi-agent Navigation with LiDAR

Safe and efficient multi-agent navigation in dynamic environments remains inherently challenging, particularly when real-time decision-making is required on resource-constrained platforms. Ensuring collision-free trajectories while adapting to uncertainties without relying on pre-built maps further complicates real-world deployment. To address these challenges, we propose LSTP-Nav, a lightweight end-to-end policy for multi-agent navigation that enables map-free collision avoidance in complex environments by directly mapping raw LiDAR point clouds to motion commands. At the core of this framework lies LSTP-Net, an efficient network that processes raw LiDAR data using a GRU architecture, enhanced with attention mechanisms to dynamically focus on critical environmental features while minimizing computational overhead. Additionally, a novel HS reward optimizes collision avoidance by incorporating angular velocity, prioritizing obstacles along the predicted heading, and enhancing training stability. To narrow the sim-to-real gap, we develop PhysReplay-Simlab, a physics-realistic multi-agent simulator, employs localized replay to mine near-failure experiences. Relying solely on LiDA, LSTP-Nav achieves efficient zero-shot sim-to-real transfer on a CPU-only robotic platform, enabling robust navigation in dynamic environments while maintaining computation frequencies above 40 Hz. Extensive experiments demonstrate that LSTP-Nav outperforms baselines with a 9.58% higher success rate and a 12.30% lower collision rate, underscoring its practicality and robustness for real-world applications.

cs.RO↗

arXiv2024

HPPS: A Hierarchical Progressive Perception System for Luggage Trolley Detection and Localization at Airports

The robotic autonomous luggage trolley collection system employs robots to gather and transport scattered luggage trolleys at airports. However, existing methods for detecting and locating these luggage trolleys often fail when they are not fully visible. To address this, we introduce the Hierarchical Progressive Perception System (HPPS), which enhances the detection and localization of luggage trolleys under partial occlusion. The HPPS processes the luggage trolley's position and orientation separately, which requires only RGB images for labeling and training, eliminating the need for 3D coordinates and alignment. The HPPS can accurately determine the position of the luggage trolley with just one well-detected keypoint and estimate the luggage trolley's orientation when it is partially occluded. Once the luggage trolley's initial pose is detected, HPPS updates this information continuously to refine its accuracy until the robot begins grasping. The experiments on detection and localization demonstrate that HPPS is more reliable under partial occlusion compared to existing methods. Its effectiveness and robustness have also been confirmed through practical tests in actual luggage trolley collection tasks. A website about this work is available at HPPS.

cs.RO↗

arXiv2024

Autonomous Multiple-Trolley Collection System with Nonholonomic Robots: Design, Control, and Implementation

The intricate and multi-stage task in dynamic public spaces like luggage trolley collection in airports presents both a promising opportunity and an ongoing challenge for automated service robots. Previous research has primarily focused on handling a single trolley or individual functional components, creating a gap in providing cost-effective and efficient solutions for practical scenarios. In this paper, we propose a mobile manipulation robot incorporated with an autonomy framework for the collection and transportation of multiple trolleys that can significantly enhance operational efficiency. We address the key challenges in the trolley collection problem through the novel design of the mechanical system and the vision-based control strategy. We design a lightweight manipulator and docking mechanism, optimized for the sequential stacking and transportation of multiple trolleys. Additionally, based on the Control Lyapunov Function and Control Barrier Function, we propose a novel vision-based control with the online Quadratic Programming which significantly improves the accuracy and efficiency of the collection process. The practical application of our system is demonstrated in real world scenarios, where it successfully executes multiple-trolley collection tasks.

cs.RO↗

arXiv2023

Multi-Risk-RRT: An Efficient Motion Planning Algorithm for Robotic Autonomous Luggage Trolley Collection at Airports

Robots have become increasingly prevalent in dynamic and crowded environments such as airports and shopping malls. In these scenarios, the critical challenges for robot navigation are reliability and timely arrival at predetermined destinations. While existing risk-based motion planning algorithms effectively reduce collision risks with static and dynamic obstacles, there is still a need for significant performance improvements. Specifically, the dynamic environments demand more rapid responses and robust planning. To address this gap, we introduce a novel risk-based multi-directional sampling algorithm, Multi-directional Risk-based Rapidly-exploring Random Tree (Multi-Risk-RRT). Unlike traditional algorithms that solely rely on a rooted tree or double trees for state space exploration, our approach incorporates multiple sub-trees. Each sub-tree independently explores its surrounding environment. At the same time, the primary rooted tree collects the heuristic information from these sub-trees, facilitating rapid progress toward the goal state. Our evaluations, including simulation and real-world environmental studies, demonstrate that Multi-Risk-RRT outperforms existing unidirectional and bi-directional risk-based algorithms in planning efficiency and robustness.

cs.RO↗

arXiv2023

Indoor Exploration and Simultaneous Trolley Collection Through Task-Oriented Environment Partitioning

In this paper, we present a simultaneous exploration and object search framework for the application of autonomous trolley collection. For environment representation, a task-oriented environment partitioning algorithm is presented to extract diverse information for each sub-task. First, LiDAR data is classified as potential objects, walls, and obstacles after outlier removal. Segmented point clouds are then transformed into a hybrid map with the following functional components: object proposals to avoid missing trolleys during exploration; room layouts for semantic space segmentation; and polygonal obstacles containing geometry information for efficient motion planning. For exploration and simultaneous trolley collection, we propose an efficient exploration-based object search method. First, a traveling salesman problem with precedence constraints (TSP-PC) is formulated by grouping frontiers and object proposals. The next target is selected by prioritizing object search while avoiding excessive robot backtracking. Then, feasible trajectories with adequate obstacle clearance are generated by topological graph search. We validate the proposed framework through simulations and demonstrate the system with real-world autonomous trolley collection tasks.

cs.RO↗

arXiv2023

FabricFolding: Learning Efficient Fabric Folding without Expert Demonstrations

Autonomous fabric manipulation is a challenging task due to complex dynamics and potential self-occlusion during fabric handling. An intuitive method of fabric folding manipulation first involves obtaining a smooth and unfolded fabric configuration before the folding process begins. However, the combination of quasi-static actions such as pick & place and dynamic action like fling proves inadequate in effectively unfolding long-sleeved T-shirts with sleeves mostly tucked inside the garment. To address this limitation, this paper introduces an improved quasi-static action called pick & drag, specifically designed to handle this type of fabric configuration. Additionally, an efficient dual-arm manipulation system is designed in this paper, which combines quasi-static (including pick & place and pick & drag) and dynamic fling actions to flexibly manipulate fabrics into unfolded and smooth configurations. Subsequently, keypoints of the fabric are detected, enabling autonomous folding. To address the scarcity of publicly available keypoint detection datasets for real fabric, we gathered images of various fabric configurations and types in real scenes to create a comprehensive keypoint dataset for fabric folding. This dataset aims to enhance the success rate of keypoint detection. Moreover, we evaluate the effectiveness of our proposed system in real-world settings, where it consistently and reliably unfolds and folds various types of fabrics, including challenging situations such as long-sleeved T-shirts with most parts of sleeves tucked inside the garment. Specifically, our method achieves a coverage rate of 0.822 and a success rate of 0.88 for long-sleeved T-shirts folding.

cs.RO↗

arXiv2023

A Systematic Evaluation of Different Indoor Localization Methods in Robotic Autonomous Luggage Trolley Collection at Airports

This article addresses the localization problem in robotic autonomous luggage trolley collection at airports and provides a systematic evaluation of different methods to solve it. The robotic autonomous luggage trolley collection is a complex system that involves object detection, localization, motion planning and control, manipulation, etc. Among these components, effective localization is essential for the robot to employ subsequent motion planning and end-effector manipulation because it can provide a correct goal position. In this article, we survey four popular and representative localization methods to achieve object localization in the luggage collection process, including radio frequency identification (RFID), Keypoints, ultrawideband (UWB), and Reflectors. To test their performance, we construct a qualitative evaluation framework with Localization Accuracy, Mobile Power Supplies, Coverage Area, Cost, and Scalability. Besides, we conduct a series of quantitative experiments regarding Localization Accuracy and Success Rate on a real-world robotic autonomous luggage trolley collection system. We further analyze the performance of different localization methods based on experiment results, revealing that the Keypoints method is most suitable for indoor environments to achieve the luggage trolley collection.

cs.RO↗

arXiv2022

Multi-Tree Guided Efficient Robot Motion Planning

Motion Planning is necessary for robots to complete different tasks. Rapidly-exploring Random Tree (RRT) and its variants have been widely used in robot motion planning due to their fast search in state space. However, they perform not well in many complex environments since the motion planning needs to simultaneously consider the geometry constraints and differential constraints. In this article, we propose a novel robot motion planning algorithm that utilizes multi-tree to guide the exploration and exploitation. The proposed algorithm maintains more than two trees to search the state space at first. Each tree will explore the local environment. The tree starts from the root will gradually collect information from other trees and grow towards the goal state. This simultaneous exploration and exploitation method can quickly find a feasible trajectory. We compare the proposed algorithm with other popular motion planning algorithms. The experiment results demonstrate that our algorithm achieves the best performance on different evaluation metrics.

cs.RO↗