检索结果-内蒙古大学图书馆

A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Yonghao Su, Hu Yu, Haiyong Yang, Cong Sui, Wei Wang, Cong Liu, Song D-Robotics Institute of Automation of Chinese Academy of Sciences China BeeLab School of Future Science and Engineering Soochow University Taiwan the School of Information Science and Technology ShanghaiTech University China

Open-set object detection (OSOD) is highly desirable for robotic manipulation in unstructured environments. However, existing OSOD methods often fail to meet the requirements of robotic applications due to their high computational burden and complex deployment. To address this issue, this paper proposes a light-weight framework called Decoupled OSOD (DOSOD), which is a practical and highly efficient solution to support real-time OSOD tasks in robotic systems. Specifically, DOSOD builds upon the YOLO-World pipeline by integrating a vision-language model (VLM) with a detector. A Multilayer Perceptron (MLP) adaptor is developed to transform text embeddings extracted by the VLM into a joint space, within which the detector learns the region representations of classagnostic proposals. Cross-modality features are directly aligned in the joint space, avoiding the complex feature interactions and thereby improving computational efficiency. DOSOD operates like a traditional closed-set detector during the testing phase, effectively bridging the gap between closed-set and openset detection. Compared to the baseline YOLO-World, the proposed DOSOD significantly enhances real-time performance while maintaining comparable accuracy. The slight DOSODS model achieves a Fixed AP of 26.7%, compared to 26.2% for YOLO-World-v1-S and 22.7% for YOLO-World-v2-S, using similar backbones on the LVIS minival dataset. Meanwhile, the FPS of DOSOD-S is 57.1% higher than YOLO-World-v1- S and 29.6% higher than YOLO-World-v2-S. Meanwhile, we demonstrate that the DOSOD model facilitates the deployment of edge devices. The codes and models are publicly available at https://***/D-robotics-AI-Lab/DOSOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

The Development Status, Challenges and Development Trends in Rehabilitation robotics: A Review

学校读者我要写书评

暂无评论

The Development Status, Challenges and Development Trends in...

Rehabilitation engineering and Assistive Technology (i-CREATe), International Convention on

作者： Liyuan Zhang Yige Peng Xiaoxuan Qi Sheng Bao Jianjun Yuan Shanghai IC Technology & Industry Promotion Center Shanghai China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics and School of Mechatronic Engineering and Automation Shanghai China

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

This paper presents the research status of rehabilitation robot in detail. In order to understand the current situation of rehabilitation robots, they are divided into four categories, such as upper limb rehabilitation robots, lower limb rehabilitation robots, massage assistance robots and other rehabilitation robots. The research status and existing problems of rehabilitation robots at home and abroad in recent years are introduced in detail, and the functions of rehabilitation robots are demonstrated. Trained upper limb rehabilitation robots and lower limb rehabilitation robots have been introduced, which help patients undergo rehabilitation training and demonstrate strong recovery functions. Massage auxiliary robots provide continuous and stable massage therapy to the patient's specific muscle tissue, relieving the patient's pain. Thermal moxibustion robots and acupuncture robots provide rehabilitation treatment for patients in the way of traditional Chinese medicine. Finally, the common challenges in the research field of rehabilitation robots are discussed, and the future development trends of various rehabilitation robots are proposed.

关键词： Training Cloud computing Reviews Pain Patient rehabilitation Muscles Assistive robots Market research Acupuncture Robots

Speed Fluctuation Suppression of Current Scaling Errors Based on Improved Iterative Learning Control Method

学校读者我要写书评

暂无评论

Speed Fluctuation Suppression of Current Scaling Errors Base...

International Conference on Electrical Machines and Systems (ICEMS)

作者： Haoyi Mu Guodong Yu Shaobin Li Pengcheng Zhu Yongxiang Xu School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China State Key Laboratory of Robotics and System Harbin China

In recent years, there has been a growing demand for high-precision speed control of permanent magnet synchronous motor (PMSM), drawing significant attention to the issue of inherent current measurement errors in drive control. This paper presents a novel approach to mitigate periodic speed fluctuations using an expert system-based iterative learning control (ILC) method. The proposed method employs an expert system to dynamically adjust the weight values of the memory factor during online updates. This ensures the calculated relaxation factor optimally suppresses speed fluctuations across all operating conditions. Furthermore, the stability and parameter tuning aspects are analyzed from the perspective of transfer functions, and the feasibility of the proposed method is demonstrated through simulation.

关键词：

NA-CPG: A robust and stable rhythm generator for robot motion control

学校读者我要写书评

暂无评论

Biomimetic Intelligence & robotics 2022年第4期2卷 30-38页

作者： Ru Tong Changlin Qiu Zhengxing Wu Jian Wang Min Tan Junzhi Yu State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Advanced Manufacturing and Robotics College of EngineeringPeking UniversityBeijing 100871China

Central pattern generators(CPGs)have been widely applied in robot motion control for the spontaneous output of coherent periodic ***,the underlying CPG network exhibits good convergence performance only within a certain range of parameter spaces,and the coupling of oscillators affects the network output accuracy in complex topological ***,CPGs may diverge when parameters change drastically,and the divergence is irreversible,which is catastrophic for the control of robot ***,normalized asymmetric CPGs(NA-CPGs)that normalize the amplitude parameters of Hopf-based CPGs and add a constraint function and a frequency regulation mechanism are ***-CPGs can realize parameter decoupling,precise amplitude output,and stable and rapid convergence,as well as asymmetric output ***,it can effectively cope with large parameter changes to avoid network oscillations and *** optimize the parameters of the NA-CPG model,a reinforcement-learning-based online optimization method is further ***,a biomimetic robotic fish is illustrated to realize the whole optimization *** demonstrated that the designed NA-CPGs exhibit stable,secure,and accurate network outputs,and the proposed optimization method effectively improves the swimming speed and reduces the lateral swing of the multijoint robotic fish by 6.7%and 41.7%,*** proposed approach provides a significant improvement in CPG research and can be widely employed in the field of robot motion control.

关键词： Normalized asymmetric CPGs Rhythm generator Motion control Robotic fish

Making Parameterization and Constrains of Object Landmark Globally Consistent via SPD(3) Manifold and Improved Cost Functions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Yutong Wang, Wei The Robotics Institute School of Mechanical Engineering and Automation Beihang University Beijing China

Object-level SLAM introduces semantic meaningful and compact object landmarks that help both indoor robot applications and outdoor autonomous driving tasks. However, the back end of object-level SLAM suffers from singularity problems because existing methods parameterize object landmark separately by their scales and poses. Under that parameterization method, the same abstract object can be represented by rotating the object coordinate frame by 90◦ and swapping its length with width value, making the pose of the same object landmark not globally consistent. To avoid the singularity problem, we first introduce the symmetric positive-definite (SPD) matrix manifold as an improved object-level landmark representation and further improve the cost functions in the back end to make them compatible with the representation. Our method demonstrates a faster convergence rate and more robustness in simulation experiments. Experiments on real datasets also reveal that using the same front-end data, our strategy improves the mapping accuracy by 22% on average. Copyright © 2022, The Authors. All rights reserved.

关键词： Cost functions

Distributed Solvers for Network Linear Equations with Scalarized Compression

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Lei Ren, Zihao Yuan, Deming Shi, Guodong College of Control Science and Engineering Zhejiang University China School of Automation Nanjing University of Science and Technology China Australia Centre for Robotics The University of Sydney Australia

Distributed computing is fundamental to multiagent systems, with solving distributed linear equations as a typical example. In this paper, we study distributed solvers for network linear equations over a network with node-tonode communication messages compressed as scalar values. Our key idea lies in a dimension compression scheme that includes a dimension-compressing vector and a data unfolding step. The compression vector applies to individual node states as an inner product to generate a real-valued message for node communication. In the unfolding step, such scalar message is then plotted along the subspace generated by the compression vector for the local computations. We first present a compressed consensus flow that relies only on such scalarized communication, and show that linear convergence can be achieved with well excited signals for the compression vector. We then employ such a compressed consensus flow as a fundamental consensus subroutine to develop distributed continuous-time and discretetime solvers for network linear equations, and prove their linear convergence properties under scalar node communications. With scalar communications, a direct benefit would be the reduced node-to-node communication channel burden for distributed computing. Numerical examples are presented to illustrate the effectiveness of the established theoretical results. Copyright © 2024, The Authors. All rights reserved.

关键词： Vectors

TrunkFlex: Enhancing Engagement in Post-Stroke Trunk Rehabilitation through a Follow-and-Stimulate Cable-Driven Robotic System

学校读者我要写书评

暂无评论

TrunkFlex: Enhancing Engagement in Post-Stroke Trunk Rehabil...

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Lufeng Chen Yingming Han Chenyang Liu Bin Li Jiacheng Huang Jing Qiu Center for Robotics School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Center for Robotics School of Mechanical and Electric Engineering University of Electronic Science and Technology of China Chengdu China Yingcai Honors College of UESTC University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Trunk rehabilitation plays a pivotal role in enhancing locomotive capacities and balance for patients with hemiplegia. In this paper, we present TrunkFlex, a cable-driven robotic system designed specifically to promote self-engagement in post-stroke trunk rehabilitation. Unlike conventional rehabilitation robots, which often interact with patients in a rigid manner, TrunkFlex incorporates a cable-driven mechanism powered by eight servo motors, allowing for versatile rehabilitation exercises. Our introduced follow-and-stimulate module, along with posture correction and speed limit modules, is integrated into the control scheme and operates in parallel to induce patient-initiated movement, thereby encouraging self-engagement and promoting a more flexible and seamless rehabilitation process. Muscle activation experiments demonstrate a significant enhancement in active engagement, as evidenced by a marked increase in muscle activity intensity compared to passive rehabilitation methods.

关键词： Mechatronics Process control Muscles Clinical trials Stroke (medical condition) Assistive robots Safety Servomotors Robots

Sim-Grasp: Learning 6-DOF Grasp Policies for Cluttered Environments Using a Synthetic Benchmark

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Juncheng Cappelleri, David J. The Multi-Scale Robotics & Automation Lab School of Mechanical Engineering Purdue University West LafayetteIN United States Purdue University West LafayetteIN United States

In this paper, we present Sim-Grasp, a robust 6-DOF two-finger grasping system that integrates advanced language models for enhanced object manipulation in cluttered environments. We introduce the Sim-Grasp-Dataset, which includes 1,550 objects across 500 scenarios with 7.9 million annotated labels, and develop Sim-GraspNet to generate grasp poses from point clouds. The Sim-Grasp-Polices achieve grasping success rates of 97.14% for single objects and 87.43% and 83.33% for mixed clutter scenarios of Levels 1-2 and Levels 3-4 objects, respectively. By incorporating language models for target identification through text and box prompts, Sim-Grasp enables both object-agnostic and target picking, pushing the boundaries of intelligent robotic systems. The codebase can be accessed at https://***/junchengli1/Sim-Grasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Robot learning

Safety-Critical Scenario Generation by Causal Influence Detection 27

学校读者我要写书评

暂无评论

Safety-Critical Scenario Generation by Causal Influence Dete...

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Yang, Yibing Zhang, Chi Xu, Linhai Ma, Shuangxun Li, Li Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Shaanxi Xi'an China School of Future Transportation Chang'an University Xi'an710064 China Tsinghua University BNRist Department of Automation Beijing100084 China

ISBN: (纸本)9798331505929

Appropriate behavior intervention for a specific background vehicle at the right moment is a crucial step in identifying safety-critical scenarios. Existing methods generate scenarios by estimating the data distribution, but when noise interventions are present, the emergence of safety-critical scenarios becomes colinearity with the noise interventions, potentially resulting in unnecessary interventions and unrealistic vehicle behaviors. To address this, we propose to integrate the causal relationship between the background vehicle behavior and the safety status of ego-vehicle as a prior into scenario generation. In this notion, we present a reinforcement learning framework with a causal influence detection module (CausalID). Specifically, we employ conditional mutual information to quantify the causal influence between vehicle sequential behaviors, and intervene on the background vehicle's behavior when the causal influence exceeds a certain threshold. Additionally, to prevent unrealistic collision-oriented driving, we sample the final intervention action from a set of candidate actions according to their probabilities of occurring in natural driving scenarios. Our experiments in 3-lane highway scenarios with multiple vehicles validate the effectiveness of the proposed framework. © 2024 IEEE.

关键词： Vehicle safety