检索结果-内蒙古大学图书馆

OffRIPP: Offline RL-based Informative Path Planning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gadipudi, Srikar Babu Deolasee, Srujan Kailas, Siva Luo, Wenhao Sycara, Katia Kim, Woojun The Department of Electrical Engineering Indian Institute of Technology Madras India The Robotics Institute Carnegie Mellon University United States The School of Interactive Computing Georgia Institute of Technology United States The Department of Computer Science University of North Carolina at Charlotte United States

Informative path planning (IPP) is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment while adhering to resource constraints. Reinforcement learning (RL) has been shown to be effective for IPP, however, it requires environment interactions, which are risky and expensive in practice. To address this problem, we propose an offline RL-based IPP framework that optimizes information gain without requiring real-time interaction during training, offering safety and cost-efficiency by avoiding interaction, as well as superior performance and fast computation during execution—key advantages of RL. Our framework leverages batch-constrained reinforcement learning to mitigate extrapolation errors, enabling the agent to learn from pre-collected datasets generated by arbitrary algorithms. We validate the framework through extensive simulations and real-world experiments. The numerical results show that our framework outperforms the baselines, demonstrating the effectiveness of the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Spiking neural networks: Towards bio-inspired multimodal perception in robotics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Oikonomou, Katerina Maria Balaska, Vasiliki Tsintotas, Konstantinos A. Mavridis, Christos N. Kansizoglou, Ioannis Gasteratos, Antonios The Department of Production and Management Engineering Laboratory of Robotics and Automation Democritus University of Thrace Xanthi Greece The Department of Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

Spiking neural networks (SNNs) have captured apparent interest over the recent years, stemming from neuroscience and reaching the field of artificial intelligence. However, due to their nature SNNs remain far behind in achieving the exceptional performance of deep neural networks (DNNs). As a result, many scholars are exploring ways to enhance SNNs by using learning techniques from DNNs. While this approach has been proven to achieve considerable improvements in SNN performance, we propose another perspective: enhancing the biological plausibility of the models to leverage the advantages of SNNs fully. Our approach aims to propose a brain-like combination of audio-visual signal processing for recognition tasks, intended to succeed in more bio-plausible human-robot interaction applications. © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

Improving Visual Question Answering by Leveraging Depth and Adapting Explainability

学校读者我要写书评

暂无评论

Improving Visual Question Answering by Leveraging Depth and ...

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Amrita Panesar Fethiye Irmak Doğan Iolanda Leite Division of Robotics Perception and Learning From the School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9781728188591

ISBN: (纸本)9781665406802

During human-robot conversation, it is critical for robots to be able to answer users’ questions accurately and provide a suitable explanation for why they arrive at the answer they provide. Depth is a crucial component in producing more intelligent robots that can respond correctly as some questions might rely on spatial relations within the scene, for which 2D RGB data alone would be insufficient. Due to the lack of existing depth datasets for the task of VQA, we introduce a new dataset, VQA-SUNRGBD. When we compare our proposed model on this RGB-D dataset against the baseline VQN network on RGB data alone, we show that ours outperforms, particularly in questions relating to depth such as asking about the proximity of objects and relative positions of objects to one another. We also provide Grad-CAM activations to gain insight regarding the predictions on depth-related questions and find that our method produces better visual explanations compared to Grad-CAM on RGB data. To our knowledge, this work is the first of its kind to leverage depth and an explainability module to produce an explainable Visual Question Answering (VQA) system.

关键词： Visualization Oral communication Question answering (information retrieval) Data models Task analysis Intelligent robots

Short-Term Time Series State of Charge Prediction in Electric Vehicle LGM50 Batteries: A Rolling Forecasting Approach

学校读者我要写书评

暂无评论

Short-Term Time Series State of Charge Prediction in Electri...

International Conference on Sensing technology, ICST

作者： Zeyang Zhou Angelo Greco Fenix Huang Karthick Thiyagarajan Jun Li Mukesh Prasad Faulty of Engineering and Information Technology School of Computer Science University of Technology Sydney Australia Clarios Varta Hannover GmbH Hannover Germany KERF Technology Limited Taipei Taiwan Smart Sensing and Robotics Laboratory (SensR Lab) Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment Western Sydney University Penrith NSW Australia

ISBN: (数字)9798350374827

ISBN: (纸本)9798350374834

The prediction of the state of charge (SOC) for battery management systems has become increasingly important with the rapid growth of the electric vehicle industry. Traditional methods for SOC prediction often depend on extensive historical data from vehicles, which can be unreliable due to various uncontrollable factors such as driving behavior, weather, and road conditions. To overcome these limitations, we propose a rolling forecasting model that leverages month-by-month data from electric vehicles to predict the SOC for the subsequent month. This approach to short-term SOC prediction aims to enhance intelligent mechatronic monitoring systems, enabling the delivery of personalized driving and charging strategies to customers.

关键词： Mechatronics Roads Time series analysis Battery management systems Predictive models Electric vehicles State of charge Forecasting Monitoring Meteorology

Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guarantees

学校读者我要写书评

暂无评论

Adding Neural Network Controllers to Behavior Trees without ...

IEEE Conference on Decision and Control

作者： Christopher Iliffe Sprague Petter Ögren Robotics Perception and Learning Lab. School of Electrical Engineering and Computer Science Royal Institute of Technology (KTH) Stockholm Sweden

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

In this paper, we show how Behavior Trees that have performance guarantees, in terms of safety and goal convergence, can be extended with components that were designed using machine learning, without destroying those performance *** learning approaches such as reinforcement learning or learning from demonstration can be very appealing to AI designers that want efficient and realistic behaviors in their agents. However, those algorithms seldom provide guarantees for solving the given task in all different situations while keeping the agent safe. Instead, such guarantees are often easier to find for manually designed model-based approaches. In this paper we exploit the modularity of behavior trees to extend a given design with an efficient, but possibly unreliable, machine learning component in a way that preserves the guarantees. The approach is illustrated with an inverted pendulum example.

关键词： Machine learning algorithms Neural networks Buildings Reinforcement learning System recovery Control systems Safety

Modular Adaptive Aerial Manipulation under Unknown Dynamic Coupling Forces

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yadav, Rishabh Dev Dantu, Swati Pan, Wei Sun, Sihao Roy, Spandan Baldi, Simone Department of Computer Science The Univerity of Manchester United Kingdom Multi-robot systems group Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Department of Cognitive Robotics Delft Univesrity of Technology Netherlands Robotics Research Center International Institute of Information Technology Hyderabad India School of Mathematics Southeast University Nanjing China

Successful aerial manipulation largely depends on how effectively a controller can tackle the coupling dynamic forces between the aerial vehicle and the manipulator. However, this control problem has remained largely unsolved as the existing control approaches either require precise knowledge of the aerial vehicle/manipulator inertial couplings, or neglect the state-dependent uncertainties especially arising during the interaction phase. This work proposes an adaptive control solution to overcome this long standing control challenge without any a priori knowledge of the coupling dynamic terms. Additionally, in contrast to the existing adaptive control solutions, the proposed control framework is modular, that is, it allows independent tuning of the adaptive gains for the vehicle position sub-dynamics, the vehicle attitude sub-dynamics, and the manipulator sub-dynamics. Stability of the closed loop under the proposed scheme is derived analytically, and real-time experiments validate the effectiveness of the proposed scheme over the state-of-the-art approaches. © 2024, CC BY.

关键词： Adaptive control systems

FaRo-PPF: Fast and Robust Point Pair Feature for 6D Pose Estimation in Industrial Stamping

学校读者我要写书评

暂无评论

FaRo-PPF: Fast and Robust Point Pair Feature for 6D Pose Est...

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Cheng He Xuebo Zhang Zhenjie Zhao Tianjin Key Laboratory of Intelligent Robotics Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin P. R. China School of Computer Science Nanjing University of Information Science and Technology Nanjing P. R. China

Estimating 6D poses of targets efficiently is critical for industrial stamping tasks, in which the Point Pair Feature (PPF) method has been widely used. Based on PPF, this paper proposes Fast and Robust PPF, i.e. FaRo-PPF, which improves PPF in the following three key aspects: adaptive down-sampling based on surface features, point pair matching based on voting ball, and normal-based pose verification. The three designs alleviate existing problems of the local matching stage in PPF, and make FaRo-PPF a stronger method of 6D pose estimation in industrial stamping. To demonstrate the effectiveness of FaRo-PPF, we compare it with PPF on five publically available datasets. Experiment results showed that FaRo-PPF is able to significantly improve accuracy by about 15% and reduce the execution time by about 40% across all test data. We further conduct a grasping and assembly experiment on a physical robot arm, and similar improvement can be observed. FaRo-PPF achieves a higher success rate of assembly and reduces the execution time by about 50%.

关键词：

Complementary Information Mutual Learning for Multimodality Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shen, Chuyun Li, Wenhao Chen, Haoqing Wang, Xiaoling Zhu, Fengping Li, Yuxin Wang, Xiangfeng Jin, Bo School of Computer Science and Technology East China Normal University Shanghai200062 China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China Huashan Hospital Fudan University Shanghai200040 China School of Computer Science and Technology East China Normal University Shanghai AI Laboratory Shanghai200062 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China

Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the development of multimodal learning in medical image segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect. To emphasize, message-passing-based redundancy filtering allows neural network visualization techniques to visualize the knowledge relationship among different modalitie

关键词： Redundancy

Improving Adversarial Transferability with Neighbourhood Gradient Information

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Haijing Wang, Jiafeng Chen, Zhaoyu Jiang, Kaixun Hong, Lingyi Guo, Pinxue Li, Jinglun Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai200433 China Engineering Research Center of Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai200433 China

Deep neural networks (DNNs) are known to be susceptible to adversarial examples, leading to significant performance degradation. In black-box attack scenarios, a considerable attack performance gap between the surrogate model and the target model persists. This work focuses on enhancing the transferability of adversarial examples to narrow this performance gap. We observe that the gradient information around the clean image, i.e. Neighbourhood Gradient Information, can offer high transferability. Leveraging this, we propose the NGI-Attack, which incorporates Example Backtracking and Multiplex Mask strategies, to use this gradient information and enhance transferability fully. Specifically, we first adopt Example Backtracking to accumulate Neighbourhood Gradient Information as the initial momentum term. Multiplex Mask, which forms a multi-way attack strategy, aims to force the network to focus on non-discriminative regions, which can obtain richer gradient information during only a few iterations. Extensive experiments demonstrate that our approach significantly enhances the adversarial transferability. Especially, when attacking numerous defense models, we achieve an average attack success rate of 95.8%. Notably, our method can plugin with any off-the-shelf algorithm to improve their attack performance without additional time cost. Copyright © 2024, The Authors. All rights reserved.

关键词：