检索结果-内蒙古大学图书馆

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Kim, Hyuntae Seoul National University Asri Department of Electrical and Computer Engineering 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of

ISBN: (纸本)9798350316339

Nonlinear data-driven control strategies, particularly Model Reference Gaussian Process Regression (MRGPR), have been effective in designing controllers directly from system input/output data, bypassing the need for explicit system modeling. This approach is advantageous for complex nonlinear systems where traditional modeling methods may be inadequate. MR-GPR employs Gaussian Process Regression to provide a non-parametric control method, enhancing adaptability and performance. However, real-world applications present challenges due to variability in system parameters, such as ensuring robustness and consistent performance. To address these challenges, this paper proposes a robust MR-GPR controller incorporating domain randomization to improve adaptability to varying operational conditions. This extension aims to maintain stable performance across diverse settings, mitigating the impact of parameter changes on control efficacy. © 2024 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Diffused task-agnostic milestone planner 23

Diffused task-agnostic milestone planner

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Mineui Hong Minjae Kang Songhwai Oh Department of Electrical and Computer Engineering and ASRI Seoul National University

Addressing decision-making problems using sequence modeling to predict future trajectories shows promising results in recent years. In this paper, we take a step further to leverage the sequence predictive method in wider areas such as long-term planning, vision-based control, and multi-task decision-making. To this end, we propose a method to utilize a diffusion-based generative sequence model to plan a series of milestones in a latent space and to have an agent to follow the milestones to accomplish a given task. The proposed method can learn control-relevant, low-dimensional latent representations of milestones, which makes it possible to efficiently perform long-term planning and vision-based control. Furthermore, our approach exploits generation flexibility of the diffusion model, which makes it possible to plan diverse trajectories for multi-task decision-making. We demonstrate the proposed method across offline reinforcement learning (RL) benchmarks and an visual manipulation environment. The results show that our approach outperforms offline RL methods in solving long-horizon, sparse-reward tasks and multi-task problems, while also achieving the state-of-the-art performance on the most challenging vision-based manipulation benchmark.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial environment design via regret-guided diffusion models 24

Adversarial environment design via regret-guided diffusion m...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hojun Chung Junseo Lee Minsoo Kim Dohyeong Kim Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Department of Electrical and Computer Engineering and ASRI Seoul National University Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University and Department of Electrical and Computer Engineering and ASRI Seoul National University

ISBN: (纸本)9798331314385

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD

关键词：

来源：评论

学校读者我要写书评

暂无评论

Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? - A Theoretical and Empirical Study 38

Do Counterfactually Fair Image Classifiers Satisfy Group Fai...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Jung, Sangwon Yu, Sumin Chun, Sanghyuk Moon, Taesup Department of Electrical and Computer Engineering Seoul National University Korea Republic of NAVER AI Lab Korea Republic of ASRI/INMC/IPAI/AIIS Seoul National University Korea Republic of

The notion of algorithmic fairness has been actively explored from various aspects of fairness, such as counterfactual fairness (CF) and group fairness (GF). However, the exact relationship between CF and GF remains to be unclear, especially in image classification tasks;the reason is because we often cannot collect counterfactual samples regarding a sensitive attribute, essential for evaluating CF, from the existing images (e.g., a photo of the same person but with different secondary sex characteristics). In this paper, we construct new image datasets for evaluating CF by using a high-quality image editing method and carefully labeling with human annotators. Our datasets, CelebA-CF and LFW-CF, build upon the popular image GF benchmarks;hence, we can evaluate CF and GF simultaneously. We empirically observe that CF does not imply GF in image classification, whereas previous studies on tabular datasets observed the opposite. We theoretically show that it could be due to the existence of a latent attribute G that is correlated with, but not caused by, the sensitive attribute (e.g., secondary sex characteristics are highly correlated with hair length). From this observation, we propose a simple baseline, Counterfactual Knowledge Distillation (CKD), to mitigate such correlation with the sensitive attributes. Extensive experimental results on CelebA-CF and LFW-CF demonstrate that CF-achieving models satisfy GF if we successfully reduce the reliance on G (e.g., using CKD). © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fully Distributed EV Charging Scheduling for Load Flattening in V2G Systems 63

Fully Distributed EV Charging Scheduling for Load Flattening...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Heo, Jinwook Hyeon, Soojeong Shim, Hyungbo Kim, Jinsung Seoul National University Asri Department of Electrical and Computer Engineering Seoul08826 Korea Republic of Vehicle Sw Division Hyundai Motor Company Hwaseong18280 Korea Republic of

ISBN: (纸本)9798350316339

This paper presents a fully distributed algorithm for scheduling electric vehicle (EV) charging and discharging to flatten the total load of the grid, while considering constraints on grid transmission capacity. As a fully distributed solution, the proposed algorithm operates without the need for a central unit. Instead, each agent only communicates a single dual variable with its neighboring agents based on a communication graph, and thus no private information is shared. In particular, the algorithm does not rely on initial conditions, ensuring robustness in online changes of operational conditions. Simulation results verify the effectiveness of the proposed algorithm. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Spatially-Conditional 3D Furniture Generation Model for Indoor Scene Synthesis

Spatially-Conditional 3D Furniture Generation Model for Indo...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Jeongho Park Obin Kwon Songhwai Oh Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Recent advances in generative models have significantly enhanced the capabilities of 3D indoor scene synthesis, a field that is rapidly gaining interest due to its implications for applications such as embodied AI. These applications often require diverse, large-scale indoor datasets that include realistically modeled 3D furniture. Traditional text-to-3D models, while capable of producing realistic assets, often lack precise control over spatial dimensions, which is critical for ensuring that furniture fits appropriately within the scenes. This paper introduces SC-Shap·E, a spatially conditional 3D generative model that not only enhances the realism of 3D furniture but also ensures it adheres to specified spatial dimensions of height, width, and depth. Built on the pretrained Shap·E model, SC-Shap·E incorporates an additional network that utilizes spatial information alongside textual prompts, offering improved control over furniture sizing within generated scenes. By comparing our model with the original Shap·E, we demonstrate its superior ability to reflect accurate spatial conditions. Additionally, we present a novel three-stage system for 3D indoor scene synthesis that includes floor-plan creation, furniture layout, and 3D furniture mesh production, showing its effective application in creating diverse and realistic 3D indoor scenes.

关键词： Solid modeling Visualization Three-dimensional displays Automation Accuracy Layout Production Control systems Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

New Results on Finite Convergence Time Mode Consensus: a Summary 63

New Results on Finite Convergence Time Mode Consensus: a Sum...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Huang, Chao Shim, Hyungbo Yu, Siliang Anderson, Brian D. O. Tongji University College of Electronic and Information Engineering Shanghai200092 China Seoul National University Asri Department of Electrical and Computer Engineering Seoul Korea Republic of Australian National University School of Engineering ActonACT2601 Australia

ISBN: (纸本)9798350316339

This paper studies the distributed mode consensus problem in a multi-agent system. Three algorithms are proposed to find the most frequent attribute (the mode) owned by the agents via distributed computation. The first algorithm computes the frequency of each attribute using consensus protocols rooted in blended dynamics, then identifies the most frequent attribute as the mode. The second algorithm, under the assumption that each agent possesses a priori knowledge of a minimum frequency for the mode, can decrease the frequency computations required at each agent for large lower bounds. In contrast, the third algorithm eliminates the necessity for such information by implementing an adaptive updating mechanism. These algorithms successfully determine the mode within a finite time frame, and predictive estimates for convergence time are included. Moreover, the first and second algorithms demonstrate plug-and-play property with a dwell time. © 2024 IEEE.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems

arXiv

引用

arXiv 2025年

作者： Yoo, Se-Wook Seo, Seung-Woo Department of Electrical and Computer Engineering ASRI Seoul National University Seoul Korea Republic of

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent challenge. Recent research highlights the potential of leveraging pre-acquired task-agnostic knowledge to enhance both safety and sample efficiency in related tasks. Building on this insight, we propose a novel method to learn shared constraint distributions across multiple tasks. Our approach identifies the shared constraints through imitation learning and then adapts to new tasks by adjusting risk levels within these learned distributions. This adaptability addresses variations in risk sensitivity stemming from expert-specific biases, ensuring consistent adherence to general safety principles even with imperfect demonstrations. Our method can be applied to control and navigation domains, including multi-task and meta-task scenarios, accommodating constraints such as maintaining safe distances or adhering to speed limits. Experimental results validate the efficacy of our approach, demonstrating superior safety performance and success rates compared to baselines, all without requiring task-specific constraint definitions. These findings underscore the versatility and practicality of our method across a wide range of real-world tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Authentication of Multi-agent System with Verifiable Computation and Distributed Aggregation 63

Authentication of Multi-agent System with Verifiable Computa...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Lee, Seungbeom Kim, Dongwoo Chung, Heewon Kim, Junsoo Shim, Hyungbo Seoul National University Asri Department of Electrical and Computer Engineering Korea Republic of Dongguk University Department of Ai · Sw Convergence Korea Republic of Desilo Inc Korea Republic of Seoul National University of Science and Technology Department of Electrical and Information Engineering Korea Republic of

ISBN: (纸本)9798350316339

We propose an authentication scheme for a multiagent system over integers, based on verifiable computation primitives. The naive approach, employing Freivalds' algorithm in centralized way, faces several challenges. Specifically, unreliability of the network introduces the risk of information tampering by other agents. To this end, it requires locally updating and merging the proofs of the individual states in a distributed manner. Our proposed method addresses these issues with assuming presence of a leader agent who is responsible for validating the correctness of all the states of the agents. This can be achieved by a distributed protocol that aggregates proofs from the individual agents, relying on the well-known knowledge-of-exponent assumption. By using this distributed protocol, computational complexity and communication cost are reduced compared to centralized verification. Furthermore, we incorporate a clustering technique to distribute storage requirements. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Reference-Tracking Sliding-Mode Control Robust to Mismatched Exogenous Disturbances

Reference-Tracking Sliding-Mode Control Robust to Mismatched...

引用

Asian Control Conference

作者： Sunghyun Koo Hyungbo Shim ASRI Department of Electrical and Computer Engineering Seoul National University Seoul Korea

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

A dynamic state-feedback sliding-mode controller (SMC) based on the internal model principle (IMP) is proposed for the tracking of exogenous signals. The proposed SMC is robust to both matched disturbances and mismatched exogenous disturbances. It also achieves robustness to matched parametric uncertainties and a certain degree of mismatched parametric uncertainties. The stability of the closed-loop system and the existence of a global solution are theoretically guaranteed by a specific initialization of the internal model. Its performance is demonstrated through numerical simulations.

关键词： Uncertainty Numerical simulation Stability analysis Robustness Regulation Numerical models Closed loop systems

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：