检索结果-内蒙古大学图书馆

Plug'n Play Task-Level Autonomy for robotics Using POMDPs and Probabilistic Programs

IEEE robotics AND AUTOMATION LETTERS 2024年第1期9卷 587-594页

作者： Wertheim, Or Suissa, Dan R. Brafman, Ronen I. Ben Gurion Univ Negev Dept Comp Sci IL-84105 Beer Sheva Israel

We describe AOS, the first general-purpose system for model-based control of autonomous robots using ai planning that fully supports partial observability and noisy sensing. The AOS provides a code-based language for specifying a generative model of the system, making model specification easier and model sampling efficient. It provides a language for specifying the relation between the model and the code, using which it auto-generates all required integration code. This allows Plug'n Play behavior, which facilitates incremental and modular system design. Extensive experiments on real and simulated robotic platforms demonstrate these advantages.

关键词： ai-enabled robotics autonomous agents integrated planning and control planning under uncertainty software architecture for robotic and automation

来源：评论

学校读者我要写书评

暂无评论

Semantic Grasping Via a Knowledge Graph of Robotic Manipulation: A Graph Representation Learning Approach

引用

IEEE robotics AND AUTOMATION LETTERS 2022年第4期7卷 9397-9404页

作者： Kwak, Ji Ho Lee, Jaejun Whang, Joyce Jiyoung Jo, Sungho Korea Adv Inst Sci & Technol Sch Comp Daejeon 305701 South Korea

Semantic grasping aims to make stable robotic grasps suitable for specific object manipulation tasks. While existing semantic grasping models focus only on the grasping regions of objects based on their affordances, reasoning about which gripper to use for grasping, e.g., a rigid parallel-jaw gripper or a soft gripper, and how strongly to grasp the target object allows more sophisticated robotic manipulation. In this letter, we create a knowledge graph of robotic manipulation named roboKG to represent information about objects (e.g., the material and the components of an object), tasks, and appropriate robotic manipulation such as which component of an object to grasp, which gripper to use, and how strongly to grasp. Using knowledge graph embedding, we generate semantic representations of the entities and relations in roboKG, enabling us to make predictions on robotic manipulation. Based on the predicted gripper type, grasping component, and grasping force, a real robot performs seven different real-world tasks on 42 household objects, achieving an accuracy of 95.21%.

关键词： ai-enabled robotics representation learning grasping

来源：评论

学校读者我要写书评

暂无评论

Takeout Service Automation With Trained Robots in the Pandemic-Transformed Catering Business

引用

IEEE robotics AND AUTOMATION LETTERS 2021年第2期6卷 903-910页

作者： Lin, Ting-Yu Wu, Kun-Ru Chen, You-Shuo Huang, Wei-Hau Chen, Yi-Tuo Natl Chiao Tung Univ Coll Elect & Comp Engn Hsinchu 30010 Taiwan Natl Chiao Tung Univ Dept Comp Sci Hsinchu 30010 Taiwan

Under strict social-distancing directives during the COVID-19 pandemic, one of the most impacted businesses is probably the catering industry, which has been forced to earn their revenue mainly from delivery and takeout services. However, traditional takeouts require patrons to wait in line, order and pick up their meals, incurring unnecessary human contact and service inefficiency. We observe these drawbacks and propose a contactless meal order and takeout service (Mots) automated system realized by ai-assisted smart robots to address the issue. In our Mots system, we develop a bump-free schedule based on the Welsh-Powell coloring algorithm for grouping robots into several non-colliding moving batches. Simulation results show that our Mots solution can effectively improve takeout efficiency and promote service accuracy, boosting business profits up to 95.4% under simulated cases for various cafeteria scales and shop popularity differences, compared to the traditional takeout method. Our experiments suggest that Mots is also capable of accommodating a sudden surge of arriving patrons within a short period of time. Furthermore, we have implemented a proof-of-concept prototype to demonstrate our Mots automated operations.

关键词： Robots Collision avoidance Robot sensing systems Business Schedules Pandemics Automation ai-enabled robotics service robotics embedded systems for robotic and automation automation technologies for smart cities collision avoidance

来源：评论

学校读者我要写书评

暂无评论

LVDiffusor: Distilling Functional Rearrangement Priors From Large Models Into Diffusor

引用

IEEE robotics AND AUTOMATION LETTERS 2024年第10期9卷 8258-8265页

作者： Zeng, Yiming Wu, Mingdong Yang, Long Zhang, Jiyao Ding, Hao Cheng, Hui Dong, Hao Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510275 Peoples R China Peking Univ Sch CS Hyperplane Lab Beijing 100871 Peoples R China Peking Univ Natl Key Lab Multimedia Informat Proc Beijing 100871 Peoples R China Beijing Acad Artificial Intelligence Beijing 100084 Peoples R China

Object rearrangement, a fundamental challenge in robotics, demands versatile strategies to handle diverse objects, configurations, and functional needs. To achieve this, the ai robot needs to learn functional rearrangement priors to specify precise goals that meet the functional requirements. Previous methods typically learn such priors from either laborious human annotations or manually designed heuristics, which limits scalability and generalization. In this letter, we propose a novel approach that leverages large models to distill functional rearrangement priors. Specifically, our approach collects diverse arrangement examples using both LLMs and VLMs and then distills the examples into a diffusion model. During test time, the learned diffusion model is conditioned on the initial configuration and guides the positioning of objects to meet functional requirements. In this way, we balance zero-shot generalization with time efficiency. Extensive experiments in multiple domains, including real-world scenarios, demonstrate the effectiveness of our approach in generating compatible goals for object rearrangement tasks, significantly outperforming baseline methods.

关键词： ai-enabled robotics deep learning methods big data in robotics and automation ai-enabled robotics deep learning methods big data in robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Employing Latent Categories of Entities for Knowledge Graph Embeddings With Contrastive Learning

引用

IEEE robotics AND AUTOMATION LETTERS 2023年第6期8卷 3390-3397页

作者： Yang, Jinfa Ying, Xianghua Chen, Taiyan Peking Univ Sch Intelligence Sci & Technol Beijing 100871 Peoples R China

Knowledge graph embedding aims to represent entities and relations as low-dimensional vectors, which is an effective way for robotics to learn and reason about semantic knowledge. It is crucial for knowledge graph embedding models to infer various relation patterns, such as symmetry/antisymmetry. However, most existing approaches ignore the latent semantic categories information of entities. For example, when robots use a faucet with relation OperatesOn, its tail entity category should be washable objects, such as apple, bowl, rather than non-washable objects, such as mobile phone, computer. To address such issues, we propose a novel and simple framework for knowledge graph embedding, which utilizes contrastive learning to cluster entities based on the constraints arising from relations, and enhances the discriminative ability for entities with the latent same category. Experimental results demonstrate the effectiveness of our proposed method on four standard knowledge graph completion benchmarks. It is noteworthy that our method can yield some new state-of-the-art results, achieving 88.2% MRR, 84.9% Hits@1 on the ai2Thor dataset, and 39.8% MRR, 30.0% Hits@1 on the FB15k-237 dataset.

关键词： Knowledge graphs Tail Robots Semantics Predictive models Magnetic heads Cognition ai-enabled robotics representation learning

来源：评论

学校读者我要写书评

暂无评论

How Generalizable is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation

引用

IEEE robotics AND AUTOMATION LETTERS 2024年第10期9卷 8619-8626页

作者： Vincent, Joseph A. Nishimura, Haruki Itkina, Masha Shah, Paarth Schwager, Mac Kollar, Thomas Stanford Univ Dept Aeronaut & Astronaut Stanford CA 94305 USA Toyota Res Inst Los Altos CA 94305 USA

With the rise of stochastic generative models in robot policy learning, end-to-end visuomotor policies are increasingly successful at solving complex tasks by learning from human demonstrations. Nevertheless, since real-world evaluation costs afford users only a small number of policy rollouts, it remains a challenge to accurately gauge the performance of such policies. This is exacerbated by distribution shifts causing unpredictable changes in performance during deployment. To rigorously evaluate behavior cloning policies, we present a framework that provides a tight lower-bound on robot performance in an arbitrary environment, using a minimal number of experimental policy rollouts. Notably, by applying the standard stochastic ordering to robot performance distributions, we provide a worst-case bound on the entire distribution of performance (via bounds on the cumulative distribution function) for a given task. We build upon established results to ensure that the bounds hold with a user-specified confidence level and tightness, and are constructed from as few policy rollouts as possible. In experiments we evaluate policies for visuomotor manipulation in both simulation and hardware. Specifically, we i) empirically validate the guarantees of the bounds in simulated manipulation settings, ii) find the degree to which a learned policy deployed on hardware generalizes to new real-world environments, and iii) rigorously compare two policies tested out-of-distribution. Our data, code, and implementation of confidence bounds are open-source.

关键词： Measurement Robots Hardware Task analysis Stochastic processes Standards Cloning Performance evaluation and benchmarking probability and statistical methods learning from demonstration ai-enabled robotics

来源：评论

学校读者我要写书评

暂无评论

On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach

引用

IEEE robotics AND AUTOMATION LETTERS 2023年第11期8卷 7865-7872页

作者： Chriat, Alaa Eddine Sun, Chuangchuang Mississippi State Univ Aerosp Engn Dept Starkville 39759 MS USA

Safety has been a critical issue for the deployment of learning-based approaches in real-world applications. To address this issue, control barrier function (CBF) and its variants have attracted extensive attention for safety-critical control. However, due to the myopic one-step nature of CBF and the lack of principled methods to design the class-$\mathcal {K}$ functions, there are still fundamental limitations of current CBFs: optimality, stability, and feasibility. In this letter, we proposed a novel and unified approach to address these limitations with Adaptive Multi-step Control Barrier Function (AM-CBF), where we parameterize the class-$\mathcal {K}$ function by a neural network and train it together with the reinforcement learning policy. Moreover, to mitigate the myopic nature, we propose a novel multi-step training and single-step execution paradigm to make CBF farsighted while the execution remains solving a single-step convex quadratic program. Our method is evaluated on the first and second-order systems in various scenarios, where our approach outperforms the conventional CBF both qualitatively and quantitatively.

关键词： Robot safety reinforcement learning ai-enabled robotics

来源：评论

学校读者我要写书评

暂无评论

State Estimation for HALE UAVs With Deep-Learning-aided Virtual AOA/SSA Sensors for Analytical Redundancy

引用

IEEE robotics AND AUTOMATION LETTERS 2021年第3期6卷 5276-5283页

作者： Youn, Wonkeun Lim, Hyungtae Choi, Hyoung Sik Rhudy, Matthew B. Ryu, Hyeok Kim, Sungyug Myung, Hyun Chungnam Natl Univ Dept Autonomous Vehicle Syst Engn Daejeon 34134 South Korea KAIST Korea Adv Inst Sci & Technol Sch Elect Engn KI AI KI R Daejeon 34141 South Korea Korea Aerosp Res Inst Daejeon South Korea Penn State Univ Div Engn Business & Comp Reading PA 19610 USA

High-altitudelong-endurance (HALE) unmanned aerial vehicles (UAVs) are employed in a variety of fields because of their ability to fly for a long time at high altitudes, even in the stratosphere. Two paramount concerns exist: enhancing their safety during long-term flight and reducing their weight as much as possible to increase their energy efficiency based on analytical redundancy approaches. In this letter, a novel deep-learning-aided navigation filter is proposed, which consists of two parts: an end-to-end mapping-based synthetic sensor measurement model that utilizes long short-term memory (LSTM) networks to estimate the angle of attack (AOA) and sideslip angle (SSA) and an unscented Kalman filter for state estimation. Our proposed method can not only reduce the weight of HALE UAVs but also ensure their safety by means of an analytical redundancy approach. In contrast to conventional approaches, our LSTM-based method achieves better estimation by virtue of its nonlinear mapping capability.

关键词： Aerodynamics Atmospheric measurements Sensors State estimation Redundancy Global Positioning System Pollution measurement Sensor fusion aerial systems applications field robotics ai-enabled robotics

来源：评论

学校读者我要写书评

暂无评论

Toward ai-enabled Commercial Telepresence Robots to Combine Home Care Needs and Affordability

引用

IEEE robotics AND AUTOMATION LETTERS 2023年第10期8卷 6691-6698页

作者： Beraldo, Gloria De Benedictis, Riccardo Cesta, Amedeo Fracasso, Francesca Cortellessa, Gabriella CNR Inst Cognit Sci & Technol I-00185 Rome Italy

As life expectancy increases, social and health assistance requires sustainable and affordable solutions possibly usable from one's own domestic environment. In this letter, we propose a transformer-based approach combined with a task-planning system and enhanced with ai sub-modules to run on low-cost telepresence robots in order to support more advanced and autonomous assistance services. The proposed system allows to dynamically generate and adapt in autonomy heterogeneous robotic actions according to the information emerged during the interaction. The ai-enhanced telepresence robot was assessed in an unstructured domestic environment by 10 users. The results show an accuracy of more than 95% in the expected robot's functioning. The participants judged the system efficient, useful and intuitive, and showed a positive inclination to re-use the robot in the future. Such outcomes derive both from a proper coordination among the heterogeneous ai sub-modules in the system and from the fast capability to frequently co-adapt the interaction.

关键词： Robots Telepresence Robot kinematics Task analysis Behavioral sciences Monitoring Aging ai-enabled robotics human-centered robotics social HRI

来源：评论

学校读者我要写书评

暂无评论

Persistent Homology Meets Object Unity: Object Recognition in Clutter

引用

IEEE TRANSACTIONS ON robotics 2024年 40卷 886-902页

作者： Samani, Ekta U. Banerjee, Ashis G. Univ Washington Dept Mech Engn Seattle WA 98195 USA Univ Washington Dept Ind & Syst Engn Seattle WA 98195 USA

Recognition of occluded objects in unseen and unstructured indoor environments is a challenging problem for mobile robots. To address this challenge, we propose a new descriptor, Topological features Of Point cloud Slices (TOPS), for point clouds generated from depth images and an accompanying recognition framework, TOPS for Human-inspired Object Recognition (THOR), inspired by human reasoning. The descriptor employs a novel slicing-based approach to compute topological features from filtrations of simplicial complexes using persistent homology and facilitates reasoning-based recognition using object unity. Apart from a benchmark dataset, we report performance on a new dataset, the UW Indoor Scenes (UW-IS) Occluded dataset, curated using commodity hardware to reflect real-world scenarios with different environmental conditions and degrees of object occlusion. THOR outperforms state-of-the-art methods on both the datasets and achieves substantially higher recognition accuracy for all the scenarios of the UW-IS Occluded dataset. Therefore, THOR is a promising step toward robust recognition in low-cost robots, meant for everyday use in indoor settings.

关键词： Point cloud compression Object recognition Robots Shape Three-dimensional displays Face recognition Image recognition ai-enabled robotics object recognition RGB-D perception topological learning

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：