检索结果-内蒙古大学图书馆

CoDriveVLM: VLM-Enhanced Urban Cooperative Dispatching and Motion Planning for Future Autonomous Mobility on Demand Systems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Haichao Yao, Ruoyu Liu, Wenru Huang, Zhenmin Shen, Shaojie Ma, Jun The Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China The Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

The increasing demand for flexible and efficient urban transportation solutions has spotlighted the limitations of traditional Demand Responsive Transport (DRT) systems, particularly in accommodating diverse passenger needs and dynamic urban environments. Autonomous Mobility-on-Demand (AMoD) systems have emerged as a promising alternative, leveraging connected and autonomous vehicles (CAVs) to provide responsive and adaptable services. However, existing methods primarily focus on either vehicle scheduling or path planning, which often simplify complex urban layouts and neglect the necessity for simultaneous coordination and mutual avoidance among CAVs. This oversimplification poses significant challenges to the deployment of AMoD systems in real-world scenarios. To address these gaps, we propose CoDriveVLM, a novel framework that integrates high-fidelity simultaneous dispatching and cooperative motion planning for future AMoD systems. Our method harnesses Vision-Language Models (VLMs) to enhance multi-modality information processing, and this enables comprehensive dispatching and collision risk evaluation. The VLM-enhanced CAV dispatching coordinator is introduced to effectively manage complex and unforeseen AMoD conditions, thus supporting efficient scheduling decision-making. Furthermore, we propose a scalable decentralized cooperative motion planning method via consensus alternating direction method of multipliers (ADMM) focusing on collision risk evaluation and decentralized trajectory optimization. Simulation results demonstrate the feasibility and robustness of CoDriveVLM in various traffic conditions, showcasing its potential to significantly improve the fidelity and effectiveness of AMoD systems in future urban transportation networks. The code is available at https://***/henryhcliu/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Risk assessment

HGDiffuser: Efficient Task-Oriented Grasp Generation via Human-Guided Grasp Diffusion Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Dehao Dong, Wenlong Tang, Chao Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China

Task-oriented grasping (TOG) is essential for robots to perform manipulation tasks, requiring grasps that are both stable and compliant with task-specific constraints. Humans naturally grasp objects in a task-oriented manner to facilitate subsequent manipulation tasks. By leveraging human grasp demonstrations, current methods can generate high-quality robotic parallel-jaw task-oriented grasps for diverse objects and tasks. However, they still encounter challenges in maintaining grasp stability and sampling efficiency. These methods typically rely on a two-stage process: first performing exhaustive task-agnostic grasp sampling in the 6-DoF space, then applying demonstration-induced constraints (e.g., contact regions and wrist orientations) to filter candidates. This leads to inefficiency and potential failure due to the vast sampling space. To address this, we propose the Human-guided Grasp Diffuser (HGDiffuser), a diffusion-based framework that integrates these constraints into a guided sampling process. Through this approach, HGDiffuser directly generates 6-DoF task-oriented grasps in a single stage, eliminating exhaustive task-agnostic sampling. Furthermore, by incorporating Diffusion Transformer (DiT) blocks as the feature backbone, HGDiffuser improves grasp generation quality compared to MLP-based methods. Experimental results demonstrate that our approach significantly improves the efficiency of task-oriented grasp generation, enabling more effective transfer of human grasping strategies to robotic systems. To access the source code and supplementary videos, visit https://***/ view/hgdiffuser. Copyright © 2025, The Authors. All rights reserved.

关键词： robotics

SELFMEDHPM: SELF PRE-TRAINING WITH HARD PATCHES MINING MASKED AUTOENCODERS FOR MEDICAL IMAGE SEGMENTATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lv, Yunhao Chen, Lingyu Wang, Jian Li, Yangxi Chen, Fang Department of Computer Science and Engineering Nanjing University of Aeronautics and Astronautics Nanjing China School of Biomedical Engineering The Institute of Medical Robotics Shanghai JiaoTong University Shanghai200240 China

In recent years, deep learning methods such as convolutional neural network (CNN) and transformers have made significant progress in CT multi-organ segmentation. However, CT multi-organ segmentation methods based on masked image modeling (MIM) are very limited. There are already methods using MAE for CT multi-organ segmentation task, we believe that the existing methods do not identify the most difficult areas to reconstruct. To this end, we propose a MIM self-training framework with hard patches mining masked autoencoders for CT multi-organ segmentation tasks (selfMedHPM). The method performs ViT self-pretraining on the training set of the target data and introduces an auxiliary loss predictor, which first predicts the patch loss and determines the location of the next mask. SelfMedHPM implementation is better than various competitive methods in abdominal CT multi-organ segmentation and body CT multi-organ segmentation. We have validated the performance of our method on the Multi Atlas Labeling Beyond The Cranial Vault (BTCV) dataset for abdomen mult-organ segmentation and the SinoMed Whole Body (SMWB) dataset for body multi-organ segmentation tasks. © 2025, CC BY.

关键词： Image segmentation

Ghost Swarms: Learning Swarm Rules from Environmental Changes Alone 28th

学校读者我要写书评

暂无评论

Ghost Swarms: Learning Swarm Rules from Environmental Chang...

28th European Conference on Genetic Programming, EuroGP 2025, Held as Part of EvoStar 2025

作者： Alharthi, Khulud Abdallah, Zahraa S. Hauert, Sabine Bristol Robotics Laboratory University of Bristol Bristol United Kingdom School of Engineering Mathematics and Technology University of Bristol Bristol United Kingdom Department of Computer Science College of Computers and Information Technology Taif University Taif Saudi Arabia

ISBN: (纸本)9783031899904

Swarm behaviours emerge from agents interacting with their local environment following simple rules. While directly observing each agent can be challenging, their collective behaviour leaves detectable environmental imprints that could offer insights into the underlying swarm dynamics. However, this task is complex due to the hidden and interconnected relationships between the rules governing agent interactions, the emergent swarm behaviour, and the environmental changes generated by this behaviour. In this work, we propose a method for extracting human-readable controllers from demonstrations showing only observable environmental imprints caused by the swarm. This approach explores whether these environmental imprints can reveal the swarm’s actions, even when the individual agents are challenging to track. Our approach eliminates the need for prior knowledge about the controller or its structure, enabling the successful learning of controllers from a single demonstration. We provide a novel method for understanding and managing both natural and engineered swarms by utilising the environmental imprints left by swarm behaviours, even when direct observation of the swarm’s actions is not feasible. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Environmental Imprints Imitation Learning Swarm Behaviour

Versatile, Robust, and Explosive Locomotion with Rigid and Articulated Compliant Quadrupeds

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ding, Jiatao Yang, Peiyu Boekel, Fabio Kober, Jens Pan, Wei Saveriano, Matteo Santina, Cosimo Della Cognitive Robotics Delft University of Technology Netherlands Department of Industrial Engineering University of Trento Trento Italy Department of Computer Science The University of Manchester United Kingdom Germany

Achieving versatile and explosive motion with robustness against dynamic uncertainties is a challenging task. Introducing parallel compliance in quadrupedal design is deemed to enhance locomotion performance, which, however, makes the control task even harder. This work aims to address this challenge by proposing a general template model and establishing an efficient motion planning and control pipeline. To start, we propose a reduced-order template model—the dual-legged actuated spring-loaded inverted pendulum with trunk rotation—which explicitly models parallel compliance by decoupling spring effects from active motor actuation. With this template model, versatile acrobatic motions, such as pronking, froggy jumping, and hop-turn, are generated by a dual-layer trajectory optimization, where the singularity-free body rotation representation is taken into consideration. Integrated with a linear singularity-free tracking controller, enhanced quadrupedal locomotion is achieved. Comparisons with the existing template model reveal the improved accuracy and generalization of our model. Hardware experiments with a rigid quadruped and a newly designed compliant quadruped demonstrate that i) the template model enables generating versatile dynamic motion;ii) parallel elasticity enhances explosive motion. For example, the maximal pronking distance, hop-turn yaw angle, and froggy jumping distance increase at least by 25%, 15% and 25%, respectively;iii) parallel elasticity improves the robustness against dynamic uncertainties, including modelling errors and external disturbances. For example, the allowable support surface height variation increases by 100% for robust froggy jumping. © 2025, CC BY.

关键词： Robustness (control systems)

External-Wrench Estimation for Aerial Robots Exploiting a Learned Model

学校读者我要写书评

暂无评论

External-Wrench Estimation for Aerial Robots Exploiting a Le...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Ayham Alharbat Gabriele Ruscelli Roberto Diversi Abeje Mersha Smart Mechatronics and Robotics research group Saxion University of Applied Science Enschede The Netherlands Robotics and Mechatronics research group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede The Netherlands Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper presents an external wrench estimator that uses a hybrid dynamics model consisting of a firstprinciples model and a neural network. This framework addresses one of the limitations of the state-of-the-art modelbased wrench observers: the wrench estimation of these observers comprises the external wrench (e.g. collision, physical interaction, wind); in addition to residual wrench (e.g. model parameters uncertainty or unmodeled dynamics). This is a problem if these wrench estimations are to be used as wrench feedback to a force controller, for example. In the proposed framework, a neural network is combined with a first-principles model to estimate the residual dynamics arising from unmodeled dynamics and parameters uncertainties, then, the hybrid trained model is used to estimate the external wrench, leading to a wrench estimation that has smaller contributions from the residual dynamics, and affected more by the external wrench. This method is validated with numerical simulations of an aerial robot in different flying scenarios and different types of residual dynamics, and the statistical analysis of the results shows that the wrench estimation error has improved significantly compared to a model-based wrench observer using only a firstprinciples model.

关键词： Uncertain systems Analytical models Statistical analysis Atmospheric modeling Dynamics Neural networks Observers Autonomous aerial vehicles Numerical simulation Numerical models

External-Wrench Estimation for Aerial Robots Exploiting a Learned Model

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Alharbat, Ayham Ruscelli, Gabriele Diversi, Roberto Mersha, Abeje Smart Mechatronics and Robotics research group Saxion University of Applied Science Enschede Netherlands Robotics and Mechatronics research group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede Netherlands Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

This paper presents an external wrench estimator that uses a hybrid dynamics model consisting of a first-principles model and a neural network. This framework addresses one of the limitations of the state-of-the-art model-based wrench observers: the wrench estimation of these observers comprises the external wrench (e.g. collision, physical interaction, wind);in addition to residual wrench (e.g. model parameters uncertainty or unmodeled dynamics). This is a problem if these wrench estimations are to be used as wrench feedback to a force controller, for example. In the proposed framework, a neural network is combined with a first-principles model to estimate the residual dynamics arising from unmodeled dynamics and parameters uncertainties, then, the hybrid trained model is used to estimate the external wrench, leading to a wrench estimation that has smaller contributions from the residual dynamics, and affected more by the external wrench. This method is validated with numerical simulations of an aerial robot in different flying scenarios and different types of residual dynamics, and the statistical analysis of the results shows that the wrench estimation error has improved significantly compared to a model-based wrench observer using only a first-principles model. © 2025, CC BY-NC-ND.

关键词：

Invisible Servoing: A Visual Servoing Approach with Return-Conditioned Latent Diffusion

学校读者我要写书评

暂无评论

Invisible Servoing: A Visual Servoing Approach with Return-C...

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Bishoy Gerges Barbara Bazzana Nicolò Botteghi Youssef Aboudorra Antonio Franchi Robotics and Mechatronics group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede The Netherlands Department of Applied Mathematics University of Twente Enschede The Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

In this paper, we present a novel visual servoing (VS) approach based on latent Denoising Diffusion Probabilistic Models (DDPMs), that explores the application of generative models for vision-based navigation of UAVs (Uncrewed Aerial Vehicles). Opposite to classical VS methods, the proposed approach allows reaching the desired target view, even when the target is initially not visible. This is possible thanks to the learning of a latent representation that the DDPM uses for planning and a dataset of trajectories encompassing target-invisible initial views. A compact representation is learned from raw images using a Cross-Modal Variational Autoencoder. Given the current image, the DDPM generates trajectories in the latent space driving the robotic platform to the desired visual target. The approach has been validated in simulation using two generic multi-rotor UAVs (a quadrotor and a hexarotor). The results show that we can successfully reach the visual target, even if not visible in the initial view. A video summary with simulations can be found in: https://***/2Hb3nkkcszE.

关键词： Location awareness Visualization Pipelines Noise reduction Autonomous aerial vehicles Visual servoing Trajectory Planning Standards Robots

An Perception Enhanced Human-Robot Skill Transfer Method for Reactive Interaction 25th

学校读者我要写书评

暂无评论

An Perception Enhanced Human-Robot Skill Transfer Method for...

25th Annual Conference on Towards Autonomous Robotic Systems, TAROS 2024

作者： Si, Weiyong Dong, Jiale Wang, Ning Yang, Chenguang School of Computer Science and Electronic Engineering University of Essex Wivenhoe Park ColchesterCO4 3SQ United Kingdom South China University of Technology Guangzhou510640 China Bristol Robotics Lab University of the West of England BristolBS16 1QY United Kingdom Department of Computer Science University of Liverpool LiverpoolL69 3BX United Kingdom

ISBN: (纸本)9783031720611

In this paper, we propose a trust human-robot skill transfer framework, interpretive and reactive dynamic system (IRDS), by investigating the behaviour tree (BT) and dynamic movement primitives (DMPs) enhanced by the feedback from perceived information for dynamic and uncertain tasks and environments. Human sensorimotor control allows interactions with various environments and accomplishes complex manipulation tasks with uncertainty;however, it is still hard for robots to own this capability. In this work, we aim to transfer these reactive skills to robots, which enable robots to interact with humans and environments under varying uncertainty. The main challenges of robot skill learning are the generalization, safety and stability issues during the skills learning and execution autonomously. BT was investigated for task planning and reactive interaction during the robot execution. The dynamic system-based model generates action for the low-level compliant controller. The convergence of the proposed IRDS framework under dynamic interaction and disturbance was proved by control theory. We conducted simulations and physical experiments on the real robots to evaluate the generalization performance and the convergence capability under uncertainty. And the results show that the reactivity, convergence and interaction performance can be guaranteed, and the learned skills can be transferred among different physical robot platforms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Human robot interaction