检索结果-内蒙古大学图书馆

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Liu, Zhibo Lu, Xiaozhen Chen, Yuhan Xiao, Yilin Xiao, Liang Bu, Yanling Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Xiamen University Department of Informatics and Communication Engineering Xiamen China

ISBN: (纸本)9798350345384

Most of the typical reinforcement learning algorithms help wireless devices choose the security policy such as the moving strategy and communication policy by exploring all the possible state-action pairs including the risky policies that cause a severe collision or network disaster. In this paper, we design a safe reinforcement learning algorithm for safety-critical applications (e.g., intelligent transportation systems) to guide the learning agent to avoid exploring risky policies. This algorithm uses Q-network (i.e., a convolutional neural network or a deep neural network) to choose the policy and designs a safety guide to modify the chosen policy that results in dangerous status. More specifically, the safety guide includes a risk alarm module that evaluates the immediate warning value corresponding to the risk of each state-action pair and a G-network that estimates the long-term risk value. By adding the long-term risk value and the long-term expected reward output by the Q-network, this algorithm uses a safety dock to modify the chosen policy. This algorithm uses the immediate warning value to formulate a safe buffer and a risky buffer for the G-network updating to ensure fully exploration in the initial learning process. As a case study, we apply the designed algorithm in a cargo transportation system, in which the experimental results verify the effectiveness of our algorithm compared with the benchmark safe deep Q-network. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Fusion of Inertial Sensor Suit and Monocular Camera for 3D Human Pelvis Pose Estimation

Fusion of Inertial Sensor Suit and Monocular Camera for 3D H...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Mihaela Popescu Kashmira Shinde Proneet Sharma Lisa Gutzeit Frank Kirchner Robotics Group Faculty of Mathematics and Computer Science University of Bremen Bremen Germany Robotics Innovation Center German Research Center for Artificial Intelligence (DFKI GmbH) Bremen Germany

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

In real-world scenarios, robots come closer to humans in many applications, sharing the same workspace or even manipulating the same objects. To ensure safe and intuitive collaboration, it is crucial to have an accurate knowledge of the human’s 3D position in space, which should be estimated with high precision, high frequency and low latency. However, individual sensors such as inertial measurement units (IMUs) or cameras cannot meet all requirements for reliable human pose estimation under conditions such as long operating times, large distances and occlusions. In this study, we highlight the limitations of different visual pose methods and present a fused approach for real-time estimation of the 3D position of the human pelvis using machine learning-based visual pose from a monocular camera and an IMU sensor suit. The multimodal fusion is based on the Invariant Extended Kalman filter (InEKF) on Lie Groups, which fuses drift-free visual poses with high-frequency inertial measurements in a loosely-coupled manner. The evaluation is performed on a recorded dataset of multiple subjects performing various experimental scenarios. The results show that the fused approach can increase the accuracy and robustness of the estimates, taking a step closer towards smooth human-robot collaboration.

关键词： Visualization Three-dimensional displays Accuracy Pose estimation Robot vision systems Sensor fusion Cameras Real-time systems Pelvis Robots

来源：评论

学校读者我要写书评

暂无评论

Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects

arXiv

引用

arXiv 2024年

作者： Mosbach, Malte Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI - Intelligent Systems and Robotics The Center for Robotics The Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

Interactive grasping from clutter, akin to human dexterity, is one of the longest-standing problems in robot learning. Challenges stem from the intricacies of visual perception, the demand for precise motor skills, and the complex interplay between the two. In this work, we present Teacher-Augmented Policy Gradient (TAPG), a novel two-stage learning framework that synergizes reinforcement learning and policy distillation. After training a teacher policy to master the motor control based on object pose information, TAPG facilitates guided, yet adaptive, learning of a sensorimotor policy, based on object segmentation. We zero-shot transfer from simulation to a real robot by using Segment Anything Model for promptable object segmentation. Our trained policies adeptly grasp a wide variety of objects from cluttered scenarios in simulation and the real world based on human-understandable prompts. Furthermore, we show robust zero-shot transfer to novel objects. Videos of our experiments are available at https://***/grasp_anything. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Algorithms from Pairwise User Preferences

Optimizing Algorithms from Pairwise User Preferences

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Leonid Keselman Katherine Shih Martial Hebert Aaron Steinfeld Robotics Institute School of Computer Science Carnegie Mellon University Pittsburgh PA USA

Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provide precise metric scores. Existing approaches leverage human feedback in an attempt to model an implicit reward function; however, this reward may be difficult or impossible to effectively capture. In this work, we introduce SortCMA to optimize algorithm parameter configurations in high dimensions based on pairwise user preferences. SortCMA efficiently and robustly leverages user input to find parameter sets without directly modeling a reward. We apply this method to tuning a commercial depth sensor without ground truth, and to robot social navigation, which involves highly complex preferences over robot behavior. We show that our method succeeds in optimizing for the user's goals and perform a user study to evaluate social navigation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service robotics

A Comparison of Prompt Engineering Techniques for Task Plann...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Jonas Bode Bastian Pätzold Raphael Memmesheimer Sven Behnke Autonomous Intelligent Systems group Computer Science Institute VI – Intelligent Systems and Robotics Lamarr Institute for Machine Learning and Artificial Intelligence and Center for Robotics University of Bonn Germany

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

Recent advances in Large Language Models (LLMs) have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLMs to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models. We make our code, including all prompts, available at https://***/AIS-Bonn/Prompt_Engineering.

关键词： Knowledge engineering Service robots Large language models Instruments Humanoid robots Reliability engineering Time measurement Planning Prompt engineering Tuning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Motion Planning for Collision Free Autonomous Docking of Satellite Emulation Platform Using Reinforcement Learning

引用

IFAC-PapersOnLine 2023年第2期56卷 3354-3359页

作者： D. Athauda A. Banerjee S. Satpute A. Agha-Mohammadi G. Nikolakopoulos Department of Computer Science Electrical and Space Engineering Luleå University of Technology Robotics and AI group Department of Computer Science Electrical and Space Engineering Luleå University of Technology AI for Humanity Inc.

A reinforcement learning (RL) enabled intelligent motion planning for collision-free autonomous docking manoeuvre explicitly designed for a robotic floating satellite emulation platform is presented in this article. The Twin Delayed Deep Deterministic Policy Gradient-based RL algorithm involving deep neural network architecture in the actor-critic framework is considered to obtain the collision-free safe docking policy. The RL agents have been trained to perform a resilient target acquisition, ensuring its terminal position and velocity requirements while enabling the capability to avoid both static and dynamic obstacles. The resulting optimal policy is implemented as a feedback control law to enable computationally efficient onboard reactive motion planning for autonomous safe docking of the robotic floating satellite platform in a complex dense debris environment. The efficacy of the proposed motion planning scheme is validated with numerous simulation studies, where it is depicted that the trained RL-based planner has the potential to address the target acquisition with a sufficient degree of accuracy in the presence of both static and dynamic obstacle scenarios.

关键词： Reinforcement Learning Floating satellite platform Obstacle avoidance Intelligent motion planning Safe autonomous docking

来源：评论

学校读者我要写书评

暂无评论

Enabling Reachability Across Multiple Domains Without Controller Synchronization in SDN

引用

computers, Materials & Continua 2021年第10期69卷 945-965页

作者： Nauman Khan Rosli Bin Salleh Ihsan Ali Zahid Khan Noman Mazhar Roobaea Alroobaea Fahad Almansour Usman Ali Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversity of MalayaMalaysia Department of Computer Science and IT University of MalakandPakistan Robotics and Internet-of-Things Lab Prince Sultan UniversityRiyadhSaudi Arabia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Science College of Sciences and Arts RassQassim UniversityBuraydah51452Saudi Arabia

Software-defined networking(SDN)makes network agile and flexible due to its programmable *** extensive network has multiple domains in SDN for the scalability and performance of the ***,the inter-domain link is also crucial for the stability of the entire network on the data plane *** than one inter-domain connection enhances the scalability of the data plane ***,it faces a reachability problem with the principal root,which causes forwarding loops and packet drops in the network,thereby degrading network *** proposed solution is a multiple controller architecture;however,this approach increases the complexity and affects network ***,in this study,we propose a framework that avoids forwarding loops and packet drops without the synchronization of multiple-domain controllers in the network using an avoid loop with test packet ***,we collect the link status for improved routing and load balancing for the upcoming flow across inter-domain links to prevent congestion and increase throughput in real *** proposed methodology can significantly reduce the controller workload against multiple controller architecture,minimize flow setup latency,and improve throughput.

关键词： Multiple domain packet drop forwarding loop load balancing SDN multiple controller

来源：评论

学校读者我要写书评

暂无评论

PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving

PhysORD: A Neuro-Symbolic Approach for Physics-infused Motio...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Zhipeng Zhao Bowen Li Yi Du Taimeng Fu Chen Wang Department of Computer Science and Engineering Spatial AI & Robotics (SAIR) Lab Institute for Artificial Intelligence and Data Science University at Buffalo Buffalo NY USA Robotics Institute Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Motion prediction is critical for autonomous off-road driving, however, it presents significantly more challenges than on-road driving because of the complex interaction between the vehicle and the terrain. Traditional physics-based approaches encounter difficulties in accurately modeling dynamic systems and external disturbance. In contrast, data-driven neural networks require extensive datasets and struggle with explicitly capturing the fundamental physical laws, which can easily lead to poor generalization. By merging the advantages of both methods, neuro-symbolic approaches present a promising direction. These methods embed physical laws into neural models, potentially significantly improving generalization capabilities. However, no prior works were evaluated in real-world settings for off-road driving. To bridge this gap, we present PhysORD, a neural-symbolic approach integrating the conservation law, i.e., the Euler-Lagrange equation, into data-driven neural models for motion prediction in off-road driving. Our experiments showed that PhysORD can accurately predict vehicle motion and tolerate external disturbance by modeling uncertainties. It outperforms existing methods both in accuracy and efficiency and demonstrates data-efficient learning and generalization ability in long-term prediction.

关键词： Bridges Uncertainty Accuracy Neural networks Merging Predictive models Mathematical models Dynamical systems Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models

arXiv

引用

arXiv 2024年

作者： Cao, Helin Behnke, Sven The Autonomous Intelligent Systems group Computer Science Institute VI – Intelligent Systems and Robotics The Center for Robotics The Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle’s surroundings. However, such systems struggle to perceive occluded areas and gaps in the scene due to the sparsity of these point clouds and their lack of semantics. To address these challenges, Semantic Scene Completion (SSC) jointly predicts unobserved geometry and semantics in the scene given raw LiDAR measurements, aiming for a more complete scene representation. Building on promising results of diffusion models in image generation and super-resolution tasks, we propose their extension to SSC by implementing the noising and denoising diffusion processes in the point and semantic spaces individually. To control the generation, we employ semantic LiDAR point clouds as conditional input and design local and global regularization losses to stabilize the denoising process. We evaluate our approach on autonomous driving datasets and our approach outperforms the state-of-the-art for SSC. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net

arXiv

引用

arXiv 2024年

作者： Cao, Helin Behnke, Sven Autonomous Intelligent Systems group Computer Science Institute VI-Intelligent Systems and Robotics Center for Robotics and the Lamarr Institute for Machine Learning and Artificial Intelligence University of Bonn Germany

We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features with the 3D scene volume, we introduce Gaussian-decay Depth-prior Projection (GDP). This module projects the 2D features into the 3D volume along the line of sight with a Gaussian-decay function, centered around the depth prior. Volumetric semantics is computed by a 3D U-Net. We propagate the hidden 3D U-Net state using the sensor motion and design a novel loss to ensure temporal consistency. We evaluate our approach on the SemanticKITTI dataset and compare it with leading SSC approaches. The SLCF-Net excels in all SSC metrics and shows great temporal consistency. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：