检索结果-内蒙古大学图书馆

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks

学校读者我要写书评

暂无评论

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in D...

IEEE International Conference on Robotic Computing (IRC)

作者： Adarsh Sehga Nicholas Ward Hung Manh La Christos Papachristos Sushil Louis Advanced Robotics and Automation (ARA) Laboratory Department of Computer Science and Engineering University of Nevada Reno NV USA

ISBN: (纸本)9781665472616

Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.

关键词： Deep learning Reinforcement learning Task analysis Robots Tuning Genetic algorithms

GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Grasping

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tang, Chao Huang, Dehao Ge, Wenqi Liu, Weiyu 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 Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

Task-oriented grasping (TOG) refers to the problem of predicting grasps on an object that enable subsequent manipulation tasks. To model the complex relationships between objects, tasks, and grasps, existing methods incorporate semantic knowledge as priors into TOG pipelines. However, the existing semantic knowledge is typically constructed based on closed-world concept sets, restraining the generalization to novel concepts out of the pre-defined sets. To address this issue, we propose GraspGPT, a large language model (LLM) based TOG framework that leverages the open-end semantic knowledge from an LLM to achieve zero-shot generalization to novel concepts. We conduct experiments on Language Augmented TaskGrasp (LA-TaskGrasp) dataset and demonstrate that GraspGPT outperforms existing TOG methods on different held-out settings when generalizing to novel concepts out of the training set. The effectiveness of GraspGPT is further validated in real-robot experiments. Our code, data, appendix, and video are publicly available at https://***/view/graspgpt. Copyright © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

VoroNav: voronoi-based zero-shot object navigation with large language model 24

学校读者我要写书评

暂无评论

VoroNav: voronoi-based zero-shot object navigation with larg...

Proceedings of the 41st International Conference on Machine Learning

作者： Pengying Wu Yao Mu Bingxian Wu Yi Hou Ji Ma Shanghang Zhang Chang Liu Department of Advancded Manufacturing and Robotics College of Engineering Peking University Beijing China The University of Hong Kong and OpenGVLab Shanghai AI Laboratory National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China

In the realm of household robotics, the Zero-Shot Object Navigation (ZSON) task empowers agents to adeptly traverse unfamiliar environments and locate objects from novel categories without prior explicit training. This paper introduces VoroNav, a novel semantic exploration framework that proposes the Reduced Voronoi Graph to extract exploratory paths and planning nodes from a semantic map constructed in real time. By harnessing topological and semantic information, VoroNav designs text-based descriptions of paths and images that are readily interpretable by a large language model (LLM). In particular, our approach presents a synergy of path and farsight descriptions to represent the environmental context, enabling LLM to apply commonsense reasoning to ascertain waypoints for navigation. Extensive evaluation on HM3D and HSSD validates VoroNav surpasses existing benchmarks in both success rate and exploration efficiency (absolute improvement: +2.8% Success and +3.7% SPL on HM3D, +2.6% Success and +3.8% SPL on HSSD). Additionally introduced metrics that evaluate obstacle avoidance proficiency and perceptual efficiency further corroborate the enhancements achieved by our method in ZSON planning. Project page: https://***

关键词：

VINet: Visual and Inertial-based Terrain Classification and Adaptive Navigation over Unknown Terrain

学校读者我要写书评

暂无评论

VINet: Visual and Inertial-based Terrain Classification and ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Tianrui Guan Ruitao Song Zhixian Ye Liangjun Zhang Department of Computer Science University of Maryland College Park MD USA Baidu RAL USA Robotics and Autonomous Driving Laboratory Baidu USA Sunnyvale CA USA

We present a visual and inertial-based terrain classification network (VINet) for robotic navigation over different traversable surfaces. We use a novel navigation-based labeling scheme for terrain classification and generalization on unknown surfaces. Our proposed perception method and adaptive scheduling control framework can make predictions according to terrain navigation properties and lead to better performance on both terrain classification and navigation control on known and unknown surfaces. Our VINet can achieve 98.37% in terms of accuracy under supervised setting on known terrains and improve the accuracy by 8.51% on unknown terrains compared to previous methods. We deploy VINet on a mobile tracked robot for trajectory following and navigation on different terrains, and we demonstrate an improvement of 10.3% compared to a baseline controller in terms of RMSE.

关键词：

Evaluating Immersive Teleoperation Interfaces: Coordinating Robot Radiation Monitoring Tasks in Nuclear Facilities

学校读者我要写书评

暂无评论

Evaluating Immersive Teleoperation Interfaces: Coordinating ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Harvey Stedman Basaran Bahadir Kocer Nejra van Zalk Mirko Kovac Vijay M. Pawar Department of Computer Science Autonomous Manufacturing Laboratory University College London London UK Aerial Robotics Laboratory Imperial College London London UK Department of Aerospace Engineering University of Bristol Bristol UK Dyson School of Design Engineering Imperial College London London UK Laboratory of Sustainability Robotics at the Swiss Federal Laboratories for Materials Science and Technology Switzerland

We present a virtual reality (VR) teleoperation interface for a ground-based robot, featuring dense 3D environment reconstruction and a low latency video stream, with which operators can immersively explore remote environments. At the UK Atomic Energy Authority's (UKAEA) Remote Applications in Challenging Environments (RACE) facility, we applied the interface in a user study where trained robotics operators completed simulated nuclear monitoring and decommissioning style tasks to compare VR and traditional teleoperation interface designs. We found that operators in the VR condition took longer to complete the experiment, had reduced collisions, and rated the generated 3D map with higher importance when compared to non-VR operators. Additional physiological data suggested that VR operators had a lower objective cognitive workload during the experiment but also experienced increased physical demand. Overall the presented results show that VR interfaces may benefit work patterns in teleoperation tasks within the nuclear industry, but further work is needed to investigate how such interfaces can be integrated into real world decommissioning workflows.

关键词：

ON ACCELERATING EDGE AI: OPTIMIZING RESOURCE-CONSTRAINED ENVIRONMENTS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sander, Jacob Cohen, Achraf Dasari, Venkat R. Venable, Brent Jalaian, Brian Department of Computer Science University of West Florida PensacolaFL United States Department of Mathematics and Statistics University of West Florida PensacolaFL United States DEVCOM Army Research Laboratory Aberdeen Proving Ground MD United States Department of Intelligent Systems and Robotics University of West Florida Institute for Human & Machine Cognition PensacolaFL United States Department of Computer Science Department of Intelligent Systems and Robotics University of West Florida Institute for Human & Machine Cognition PensacolaFL United States

Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating deep learning models under such constraints. First, we examine model compression techniques-pruning, quantization, tensor decomposition, and knowledge distillation-that streamline large models into smaller, faster, and more efficient variants. Next, we explore Neural Architecture Search (NAS), a class of automated methods that discover architectures inherently optimized for particular tasks and hardware budgets. We then discuss compiler and deployment frameworks, such as TVM, TensorRT, and OpenVINO, which provide hardware-tailored optimizations at inference time. By integrating these three pillars into unified pipelines, practitioners can achieve multi-objective goals, including latency reduction, memory savings, and energy efficiency-all while maintaining competitive accuracy. We also highlight emerging frontiers in hierarchical NAS, neurosymbolic approaches, and advanced distillation tailored to large language models, underscoring open challenges like pre-training pruning for massive networks. Our survey offers practical insights, identifies current research gaps, and outlines promising directions for building scalable, platform-independent frameworks to accelerate deep learning models at the edge. © 2025, CC BY.

关键词： Budget control

DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Guoping Wu, Xiaming Liao, Wentao Wu, Xinglong Huang, Qing Li, Chang Hubei Key Laboratory of Intelligent Robotics School of Computer Science and Engineering Wuhan Institute of Technology Hubei Wuhan430205 China Department of Biomedical Engineering Hefei University of Technology Anhui Hefei230009 China

Objective: Accurately segmenting lesions in ultrasound images remains a challenging task due to the inherent ambiguity in distinguishing boundaries between lesions and adjacent tissues. Although deep learning has made significant progress in accurate ultrasound image segmentation, there is still a lack of attention to the quality of boundary segmentation and its relationship with the body. As a result, the current accuracy of ultrasound image segmentation still has room for improvement in enhancing the precision of lesion delineation. We aim to improve the overall segmentation accuracy and the quality of boundary segmentation by exploring the relationship between the body and the boundary in ultrasound images. Methods: We introduce a dual-branch structure based on a deep neural network that allows the model to learn the relationship between the body and boundary parts under supervision, leading to an improvement in overall segmentation accuracy and boundary segmentation quality. Additionally, we propose a novel feature fusion module aimed at facilitating the integration and interaction of body and boundary information. Based on the dual-branch structure and feature fusion strategy, we have designed UBBS-Net for ultrasound image segmentation. Results: The proposed approach is evaluated on three challenging public ultrasound image datasets. Our experimental results demonstrate the superiority of the proposed method compared to existing state-of-the-art methods. Specifically, we achieve a Dice Similarity Coefficient of 81.05±10.44% for breast cancer segmentation, 76.41±5.52% for brachial plexus nerves segmentation, and 87.75±4.18% for infantile hemangioma segmentation on BUSI, UNS and UHES datasets, respectively. Conclusions: We propose UBBS-Net, a novel network for ultrasound image segmentation that combines body and boundary information with a proposed feature fusion module. Our method outperforms existing approaches on three challenging public datasets, demonstratin

关键词： Ultrasonic imaging

MoSS: Monocular Shape Sensing for Continuum Robots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shentu, Chengnan Li, Enxu Chen, Chaojun Dewi, Puspita Triana Lindell, David B. Burgner-Kahrs, Jessica Department of Computer Science University of Toronto Canada Department of Mechanical and Industrial Engineering University of Toronto Canada Continuum Robotics Laboratory Department of Mathematical and Computational Sciences University of Toronto Canada Waabi Canada

Continuum robots are promising candidates for interactive tasks in medical and industrial applications due to their unique shape, compliance, and miniaturization capability. Accurate and real-time shape sensing is essential for such tasks yet remains a challenge. Embedded shape sensing has high hardware complexity and cost, while vision-based methods require stereo setup and struggle to achieve real-time performance. This paper proposes a novel eye-to-hand monocular approach to continuum robot shape sensing. Utilizing a deep encoder-decoder network, our method, MoSSNet, eliminates the computation cost of stereo matching and reduces requirements on sensing hardware. In particular, MoSSNet comprises an encoder and three parallel decoders to uncover spatial, length, and contour information from a single RGB image, and then obtains the 3D shape through curve fitting. A two-segment tendon-driven continuum robot is used for data collection and testing, demonstrating accurate (mean shape error of 0.91 mm, or 0.36% of robot length) and real-time (70 fps) shape sensing on real-world data. Additionally, the method is optimized end-to-end and does not require fiducial markers, manual segmentation, or camera calibration. Code and datasets will be made available at https://github. com/ContinuumroboticsLab/MoSSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Curve fitting

Graph Neural Networks for Human-Aware Social Navigation 21st

学校读者我要写书评

暂无评论

Graph Neural Networks for Human-Aware Social Navigation

21st International Workshop of Physical Agents, WAF 2020

作者： Manso, Luis J. Jorvekar, Ronit R. Faria, Diego R. Bustos, Pablo Bachiller, Pilar Department of Computer Science College of Engineering and Physical Sciences Aston University Birmingham United Kingdom Department of Computer Engineering Pune Institute of Computer Technology Pune India Robotics and Artificial Vision Laboratory University of Extremadura Badajoz Spain

ISBN: (纸本)9783030625788

Autonomous navigation is a key skill for assistive and service robots. To be successful, robots have to comply with social rules, such as avoiding the personal spaces of the people surrounding them, or not getting in the way of human-to-human and human-to-object interactions. This paper suggests using Graph Neural Networks to model how inconvenient the presence of a robot would be in a particular scenario according to learned human conventions so that it can be used by path planning algorithms. To do so, we propose two automated scenario-to-graph transformations and benchmark them with different Graph Neural Networks using the SocNav1 dataset [1]. We achieve close-to-human performance in the dataset and argue that, in addition to its promising results, the main advantage of the approach is its scalability in terms of the number of social factors that can be considered and easily embedded in code in comparison with model-based approaches. The code used to train and test the resulting graph neural network is available in a public repository. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Human robot interaction