检索结果-内蒙古大学图书馆

Adaptive Task Allocation in Multi-Human Multi-Robot Teams under Team Heterogeneity and Dynamic information Uncertainty

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yuan, Ziqin Wang, Ruiqi Kim, Taehyeon Zhao, Dezhong Obi, Ike Min, Byung-Cheol SMART Laboratory Department of Computer and Information Technology Purdue University West LafayetteIN United States College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China

Task allocation in multi-human multi-robot (MH-MR) teams presents significant challenges due to the inherent heterogeneity of team members, the dynamics of task execution, and the information uncertainty of operational states. Existing approaches often fail to address these challenges simultaneously, resulting in suboptimal performance. To tackle this, we propose ATA-HRL, an adaptive task allocation framework using hierarchical reinforcement learning (HRL), which incorporates initial task allocation (ITA) that leverages team heterogeneity and conditional task reallocation in response to dynamic operational states. Additionally, we introduce an auxiliary state representation learning task to manage information uncertainty and enhance task execution. Through an extensive case study in large-scale environmental monitoring tasks, we demonstrate the benefits of our approach. More details are available on our website: https://***/view/ata-hrl. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

PrefMMT: Modeling Human Preferences in Preference-based Reinforcement Learning with Multimodal Transformers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Dezhong Wang, Ruiqi Suh, Dayoon Kim, Taehyeon Yuan, Ziqin Min, Byung-Cheol Chen, Guohua College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China SMART Laboratory Department of Computer and Information Technology Purdue University West LafayetteIN United States

Preference-based reinforcement learning (PbRL) shows promise in aligning robot behaviors with human preferences, but its success depends heavily on the accurate modeling of human preferences through reward models. Most methods adopt Markovian assumptions for preference modeling (PM), which overlook the temporal dependencies within robot behavior trajectories that impact human evaluations. While recent works have utilized sequence modeling to mitigate this by learning sequential non-Markovian rewards, they ignore the multimodal nature of robot trajectories, which consist of elements from two distinctive modalities: state and action. As a result, they often struggle to capture the complex interplay between these modalities that significantly shapes human preferences. In this paper, we propose a multimodal sequence modeling approach for PM by disentangling state and action modalities. We introduce a multimodal transformer network, named PrefMMT, which hierarchically leverages intra-modal temporal dependencies and inter-modal state-action interactions to capture complex preference patterns. Our experimental results demonstrate that PrefMMT consistently outperforms state-of-the-art PM and direct preference-based policy learning baselines on locomotion tasks from the D4RL benchmark and manipulation tasks from the MetaWorld benchmark. Source code and supplementary information are available at https: //***/view/prefmmt. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

PrefCLM: Enhancing Preference-based Reinforcement Learning with Crowdsourced Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Ruiqi Zhao, Dezhong Yuan, Ziqin Obi, Ike Min, Byung-Cheol SMART Laboratory Department of Computer and Information Technology Purdue University West LafayetteIN United States College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China

Preference-based reinforcement learning (PbRL) is emerging as a promising approach to teaching robots through human comparative feedback, sidestepping the need for complex reward engineering. However, the substantial volume of human feedback required in existing PbRL methods hinders broader applications. In this work, we introduce PrefCLM, a novel framework that utilizes crowdsourced large language models (LLMs) as synthetic teachers in PbRL. We utilize Dempster-Shafer Theory to fuse individual preferences from multiple LLM agents at the score level, efficiently leveraging their diversity and collective intelligence. We also introduce a human-in-the-loop pipeline, enabling iterative and collective refinements that adapt to the nuanced and individualized preferences inherent to human-robot interaction (HRI) scenarios. Experimental results across various general RL tasks show that PrefCLM achieves competitive performance compared to expert-engineered scripted teachers and excels in facilitating more more natural and efficient behaviors. A real-world user study (N=10) further demonstrates its capability to tailor robot behaviors to individual user preferences, significantly enhancing user satisfaction in HRI scenarios. Paper website: https://***. Copyright © 2024, The Authors. All rights reserved.

关键词： Human robot interaction

REBEL: Rule-based and Experience-enhanced Learning with LLMs for Initial Task Allocation in Multi-Human Multi-Robot Teaming

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gupte, Arjun Wang, Ruiqi Venkatesh, Vishnunandan L.N. Kim, Taehyeon Zhao, Dezhong Yuan, Ziqin Min, Byung-Cheol SMART Laboratory Department of Computer and Information Technology Purdue University West LafayetteIN United States College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China

Multi-human multi-robot teams are increasingly recognized for their efficiency in executing large-scale, complex tasks by integrating heterogeneous yet potentially synergistic humans and robots. However, this inherent heterogeneity presents significant challenges in teaming, necessitating efficient initial task allocation (ITA) strategies that optimally form complementary human-robot pairs or collaborative chains and establish well-matched task distributions. While current learning-based methods demonstrate promising performance, they often incur high computational costs and lack the flexibility to incorporate user preferences in multi-objective optimization (MOO) or adapt to last-minute changes in dynamic real-world environments. To address these limitations, we propose REBEL, an LLM-based ITA framework that integrates rule-based and experience-enhanced learning to enhance LLM reasoning capabilities and improve in-context adaptability to MOO and situational changes. Extensive experiments validate the effectiveness of REBEL in both single-objective and multi-objective scenarios, demonstrating superior alignment with user preferences and enhanced situational awareness to handle unexpected team composition changes. Additionally, we show that REBEL can complement pre-trained ITA policies, further boosting situational adaptability and overall team performance. Website at https://***/view/ita-rebel. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

Prediction based Auto-Pilot Interface for Drone to Object Chasing using Historical TSPI Data

学校读者我要写书评

暂无评论

Prediction based Auto-Pilot Interface for Drone to Object Ch...

International Conference on Control, Automation and Systems ( ICCAS)

作者： Shinhyoung Jang Byeonghwi Park Juheon Jeong Jack Mahedy Nebey Gebreslassie Minji Lee Eric T. Matson Department of Computer Science and Engineering Chungnam National University Daejeon Republic of Korea Daejeon Korea Department of Computer and Information Technology Purdue University West Lafayette IN USA Department of Technology Purdue University West Lafayette IN USA

Replacing military aircraft with Unmanned Aerial Vehicles (UAV) offers advantages such as reducing costs and risks associated with conventional military aircraft. To defend against enemy UAV attacks, anti-drone systems are used. While most technologies focus on drone detection, this paper proposes a process of tracking targets using arbitrary UAV to enhance camera data quality or directly engage and neutralize targets. The system comprises drone detection, movement prediction, and chasing. Devices such as radar are used to detect drones, and they provide Time-Space-Position information (TSPI) using suitable data formats. Using Machine Learning (ML) techniques make it feasible to predict an object's future location, represented with equations. Utilizing trained machine learning models, the Auto-pilot Application Programming Interface (API) of the drone is employed to track based on the predicted results. Through experiments, the feasibility of predicting an object's future location using various ML techniques has been confirmed. Furthermore, verification has been conducted to establish the attainability of implementing the Auto-pilot API through the utilization of DJI's API.

关键词：

Hyper-STTN: Social Group-aware Spatial-Temporal Transformer Network for Human Trajectory Prediction with Hypergraph Reasoning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Weizheng Wang, Chaowei Yang, Baijian Chen, Guohua Min, Byung-Cheol Department of Computer and Information Technology Purdue University West LafayetteIN United States Department of Computer Science University of Nottingham Nottinghamshire United Kingdom College of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China

Predicting crowded intents and trajectories is crucial in various real-world applications, including social robots and autonomous vehicles. Understanding environmental dynamics is challenging, not only due to the complexities of modeling pair-wise spatial and temporal interactions but also the diverse influence of group-wise interactions. To decode the comprehensive pair-wise and group-wise interactions in crowded scenarios, we introduce Hyper-STTN, a Hypergraph-based Spatial-Temporal Transformer Network for crowd trajectory prediction. In Hyper-STTN, crowded group-wise correlations are constructed using a set of multi-scale hypergraphs with varying group sizes, captured through random-walk probability hypergraph spectral convolution. Additionally, a spatial-temporal transformer is adapted to capture pedestrians' pairwise latent interactions in spatial-temporal dimensions. These heterogeneous group-wise and pair-wise are then fused and aligned though a multi-modal transformer network. Hyper-STTN outperforms other state-of-the-art baselines and ablation models on several public pedestrian motion datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Social robots

Adversarial Attacks on Federated Learning Revisited: a Client-Selection Perspective

学校读者我要写书评

暂无评论

Adversarial Attacks on Federated Learning Revisited: a Clien...

IEEE Conference on Communications and Network Security (CNS)

作者： Xingyu Lyu Shixiong Li Ning Wang Tao Li Danjue Chen Yimin Chen Miner School of Computer and Information Sciences University of Massachusetts Lowell USA Department of Computer Science and Engineering University of South Florida USA Department of Computer and Information Technology Purdue University USA Department of Civil Construction and Environmental Engineering North Carolina State University USA

ISBN: (数字)9798350375961

ISBN: (纸本)9798350375978

Federated Learning (FL) is a widely adopted distributed machine learning technique where clients collaboratively train a model without sharing their data. A critical component of FL is client selection, which involves choosing the necessary number of clients for each training round. Current client selection algorithms for wireless FL rely on the conditions of wireless channels but do not account for vulnerabilities from attacks on these channels, such as channel state information (CSI) forgery attacks. In this paper, we introduce AirTrojan, a novel attack vector that targets client selection in FL. Our key insight is that since the channel state can be manipulated by attackers, an attacker can adjust their probability of being chosen as a participant. AirTrojan enhances the feasibility of adversarial attacks on FL, which usually assume that malicious clients are always selected as participants. We demonstrate the effectiveness of AirTrojan by showing how it can disrupt client selection and facilitate model poisoning attacks on FL. Our work highlights that it is urgent to add security components to client selection processes in wireless FL.

关键词： Wireless communication Training Machine learning algorithms Federated learning Distributed databases Network security Vectors Forgery Data models Communication system security

BFTRAND: Low-Latency Random Number Provider for BFT Smart Contracts

学校读者我要写书评

暂无评论

BFTRAND: Low-Latency Random Number Provider for BFT Smart Co...

International Conference on Dependable Systems and Networks (DSN)

作者： Jinghui Liao Borui Gong Wenhai Sun Fengwei Zhang Zhenyu Ning Man Ho Au Weisong Shi Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology China Department of Computer Science and Engineering Southern University of Science and Technology China Computer Science Wayne State University USA Neo Foundation Department of Computing The Hong Kong Polytechnic University China Computer and Information Technology Purdue University USA Hunan University China Computer and Information Sciences University of Delaware USA

ISBN: (数字)9798350341058

ISBN: (纸本)9798350341065

Random numbers play a crucial role in decen-tralized applications (dApps) like decentralized finance (DeFi) and non-fungible tokens (NFTs). However, their generation faces challenges due to blolckchain's deterministic and decentralized nature, risking smart contract security and ecosystem stability. Prior solutions, including Oracles, employing commit-execute schemes, suffer from higher transaction fees, extended processing times, and increased on-chain storage, compromising efficiency. This paper proposes a novel random number provider (RNP) protocol for smart contracts, eliminating dependencies on traditional commit-execute approaches. Furthermore, we systematically identify potential random number-related attacks on smart contracts, particularly Post-reveal Undo Attacks (PUAs), where attackers may reverse contract operations when randomness is unfavorable, and discuss the security requirements. Our protocol addresses these attacks by (1) incorporating distributed random beacons (D RBs) with consensus processes, bridging the semantic gap between DRB and consensus, and (2) thoroughly analyzing and classifying four types of PUA and offering robust mitigations, alongside presenting a security proof. Our experiments show the protocol significantly enhances response times and security for random number queries in smart contracts, slashing request fees by at least 89 % and reducing on-chain data by 76.4% versus current methods. This work advances the integration of DRB protocols and consensus mechanisms, securing and optimizing random number applications in dApps, thus fostering the creation of more dependable, robust systems.

关键词： Protocols Prevention and mitigation Smart contracts Finance Decentralized applications Stability analysis Security

Straggler Mitigation and Latency Optimization in Blockchain-based Hierarchical Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Zhilin Hu, Qin Xu, Minghui Xiong, Zehui The Department of Computer and Information Science Indiana University Purdue University IndianapolisIN46202 United States The School of Computer Science and Technology Shandong University China Pillar of Information Systems Technology and Design Singapore University of Technology Design Singapore Singapore

Cloud-edge-device hierarchical federated learning (HFL) has been recently proposed to achieve communication-efficient and privacy-preserving distributed learning. However, there exist several critical challenges, such as the single point of failure and potential stragglers in both edge servers and local devices. To resolve these issues, we propose a decentralized and straggler-tolerant blockchain-based HFL (BHFL) framework. Specifically, a Raft-based consortium blockchain is deployed on edge servers to provide a distributed and trusted computing environment for global model aggregation in BHFL. To mitigate the influence of stragglers on learning, we propose a novel aggregation method, HieAvg, which utilizes the historical weights of stragglers to estimate the missing submissions. Furthermore, we optimize the overall latency of BHFL by jointly considering the constraints of global model convergence and blockchain consensus delay. Theoretical analysis and experimental evaluation show that our proposed BHFL based on HieAvg can converge in the presence of stragglers, which performs better than the traditional methods even when the loss function is non-convex and the data on local devices are non-independent and identically distributed (non-IID). Copyright © 2023, The Authors. All rights reserved.

关键词： Blockchain