大模型对齐与安全 - arXivDaily 专题

2102.05490 2021-10-28 eess.SY cs.SY 50%

Safe-visor Architecture for Sandboxing (AI-based) Unverified Controllers in Stochastic Cyber-Physical Systems

Bingzhuo Zhong, Abolfazl Lavaei, Hongpeng Cao, Majid Zamani, Marco Caccamo

专题命中安全训练：safety(abstract)

2110.12591 2021-10-27 cs.SE cs.HC cs.LO 50%

Assuring Increasingly Autonomous Systems in Human-Machine Teams: An Urban Air Mobility Case Study

Siddhartha Bhattacharyya, Jennifer Davis, Anubhav Gupta, Nandith Narayan, Michael Matessa

专题命中安全训练：safety(abstract)

Comments In Proceedings FMAS 2021, arXiv:2110.11527

Journal ref EPTCS 348, 2021, pp. 150-166

2110.05440 2021-10-12 cs.RO 50%

Safe Human-Interactive Control via Shielding

Jeevana Priya Inala, Yecheng Jason Ma, Osbert Bastani, Xin Zhang, Armando Solar-Lezama

专题命中安全训练：safety(abstract)

2007.12666 2021-10-06 eess.SY cs.SY math.OC 50%

Safe Model-Based Reinforcement Learning for Systems with Parametric Uncertainties

S M Nahid Mahmud, Scott A Nivison, Zachary I. Bell, Rushikesh Kamalapurkar

专题命中安全训练：safety(abstract)

Comments This manuscript has been accepted in Frontiers in Robotics and AI. doi: 10.3389/frobt.2021.733104

2103.14186 2021-10-01 eess.SY cs.SY 50%

Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems

Thanh Long Vu, Sayak Mukherjee, Renke Huang, Qiuhua Hung

专题命中安全训练：safety(abstract)

Comments IEEE CDC 2021. arXiv admin note: substantial text overlap with arXiv:2011.09664

2109.09909 2021-09-22 eess.SY cs.SY math.OC 50%

Generalization of Safe Optimal Control Actions on Networked Multi-Agent Systems

Lin Song, Neng Wan, Aditya Gahlawat, Chuyuan Tao, Naira Hovakimyan, Evangelos A. Theodorou

专题命中安全训练：safety(abstract)

Comments 10 pages, 9 figures

1606.04241 2021-08-30 physics.soc-ph 50%

An Empirically grounded Agent Based simulator for the Air Traffic Management in the SESAR scenario

Gérald Gurtner, Christian Bongiorno, Marco Ducci, Salvatore Miccichè

专题命中安全训练：safety(abstract)

Journal ref JATM, 59, 26-43, (2017)

2107.07986 2021-07-19 cs.HC cs.CV eess.SP 50%

In-Bed Person Monitoring Using Thermal Infrared Sensors

Elias Josse, Amanda Nerborg, Kevin Hernandez-Diaz, Fernando Alonso-Fernandez

专题命中安全训练：safety(abstract)

Comments Accepted for publication at FedCSIS 2021

2106.00936 2021-06-03 cs.RO 50%

Least-Restrictive Multi-Agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control

Salar Asayesh, Mo Chen, Mehran Mehrandezh, Kamal Gupta

专题命中安全训练：safety(abstract)

2104.13210 2021-04-28 eess.SY cs.SC cs.SY 50%

CPS Engineering: Gap Analysis and Perspectives

Emmanuel Ledinot

专题命中安全训练：safety(abstract)

Comments 41 pages, 19 figures, submitted to Leibniz Journal special issue on CPS Enigineering

1908.09506 2021-04-08 eess.SY cs.SY 50%

Constraint Learning for Control Tasks with Limited Duration Barrier Functions

Motoya Ohnishi, Gennaro Notomista, Masashi Sugiyama, Magnus Egerstedt

专题命中安全训练：safety(abstract)

Comments 11 pages, 4 figures; published in Automatica

Journal ref Automatica 127 (2021)

2103.15231 2021-03-30 cs.CV 50%

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

Dominik Bauer, Timothy Patten, Markus Vincze

专题命中安全训练：alignment(abstract)

Comments Accepted at CVPR 2021

2103.12553 2021-03-24 cs.MA cs.RO 50%

Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions

Zhiyuan Cai, Huanhui Cao, Wenjie Lu, Lin Zhang, Hao Xiong

专题命中安全训练：safety(abstract)

2103.09016 2021-03-19 cs.RO 50%

Manipulator-Independent Representations for Visual Imitation

Yuxiang Zhou, Yusuf Aytar, Konstantinos Bousmalis

专题命中安全训练：alignment(abstract)

2102.01023 2021-02-02 eess.IV physics.med-ph 50%

MRSaiFE: Tissue Heating Prediction for MRI: a Feasibility Study

Simone Angela Winkler, Isabelle Saniour, Akshay Chaudhari, Fraser Robb, J Thomas Vaughan

专题命中安全训练：safety(abstract)

Comments 3 pages, 1 figure

2012.10261 2020-12-21 eess.SY cs.SY 50%

Collision Avoidance and Liveness of Multi-agent Systems with CBF-based Controllers

Mrdjan Jankovic, Mario Santillo

专题命中安全训练：safety(abstract)

2012.10153 2020-12-21 cs.MA 50%

A Distributed Simplex Architecture for Multi-Agent Systems

Usama Mehmood, Scott D. Stoller, Radu Grosu, Shouvik Roy, Amol Damare, Scott A. Smolka

专题命中安全训练：safety(abstract)

2008.06508 2020-11-25 hep-ph nucl-th 50%

Covariantizing Phase Space

Andrew J. Larkoski, Tom Melia

专题命中安全训练：safety(abstract)

Comments 6 pages, 1 figure; v2: PRD version, extended discussion of IRC safe and additive observables from Stokes' theorem

Journal ref Phys. Rev. D 102, 094014 (2020)

2011.09664 2020-11-20 eess.SY cs.SY 50%

Safe Reinforcement Learning for Emergency LoadShedding of Power Systems

Thanh Long Vu, Sayak Mukherjee, Tim Yin, Renke Huang, and Jie Tan, Qiuhua Huang

专题命中安全训练：safety(abstract)

Comments arXiv admin note: text overlap with arXiv:2006.12667

2003.03498 2020-10-20 math.OC 50%

Control Barrier Functions for Stochastic Systems

Andrew Clark

专题命中安全训练：safety(abstract)

2009.14756 2020-10-01 eess.SP 50%

A Plausibility-based Fault Detection Method for High-level Fusion Perception Systems

Florian Geissler, Alex Unnervik, Michael Paulitsch

专题命中安全训练：trustworthy(abstract)

Comments 11 pages, 7 figures

Journal ref IEEE Open Journal of Intelligent Transportation Systems (OJ-ITS), 2020

2009.12877 2020-09-29 cs.CV 50%

Virtual Experience to Real World Application: Sidewalk Obstacle Avoidance Using Reinforcement Learning for Visually Impaired

Faruk Ahmed, Md Sultan Mahmud, Kazi Ashraf Moinuddin, Mohammed Istiaque Hyder, Mohammed Yeasin

专题命中安全训练：safety(abstract)

Comments Journal, to be submitted

2005.07872 2020-08-18 cs.HC cs.RO 50%

Gentlemen on the Road: Understanding How Pedestrians Interpret Yielding Behavior of Autonomous Vehicles using Machine Learning

Yoon Kyung Lee, Yong-Eun Rhee, Jeh-Kwang Ryu, Sowon Hahn

专题命中安全训练：safety(abstract)

Comments 14 pages, 8 figures, submitted for publication

2007.08050 2020-07-17 cond-mat.mes-hall 50%

Sarin and Air Permeation Through a Nanoporous Graphene

Marco A. Maria, Alexandre F. Fonseca

专题命中安全训练：safety(abstract)

Comments Submitted version of the published paper

Journal ref MRS Advances 5, 1475 (2020)

2007.07436 2020-07-16 eess.SY cs.SY 50%

Modulation of Control Authority in Adaptive HapticShared Control Paradigms

Vahid Izadi, Amir H. Ghasemi

专题命中安全训练：safety(abstract)

Comments 33 pages, 9 figures, Journal of Engineering Control Practice

2004.05213 2020-07-16 cs.GT cs.FL 50%

Deceptive Labeling: Hypergames on Graphs for Stealthy Deception

Abhishek N. Kulkarni, Huan Luo, Nandi O. Leslie, Charles A. Kamhoua, Jie Fu

专题命中安全训练：safety(abstract)

Comments 6 page, 3 figures, submitted to CDC 2020/L-CSS

1911.01697 2020-07-08 physics.soc-ph cond-mat.stat-mech cs.MA 50%

Learning to flock through reinforcement

Mihir Durve, Fernando Peruani, Antonio Celani

专题命中安全训练：alignment(abstract)

Journal ref Phys. Rev. E 102, 012601 (2020)

2004.10674 2020-04-23 cs.CR cs.DC 50%

Hybrid Blockchain-Enabled Secure Microservices Fabric for Decentralized Multi-Domain Avionics Systems

Ronghua Xu, Yu Chen, Erik Blasch, Alexander Aved, Genshe Chen, Dan Shen

专题命中安全训练：safety(abstract)

Comments 2020 SPIE Defense + Commercial Sensing

2003.09267 2020-03-23 eess.SY cs.MA cs.RO cs.SY math.OC 50%

Barrier Functions for Multiagent-POMDPs with DTL Specifications

Mohamadreza Ahmadi, Andrew Singletary, Joel W. Burdick, Aaron D. Ames

专题命中安全训练：safety(abstract)

Comments arXiv admin note: text overlap with arXiv:1903.07823

2003.04950 2020-03-12 cs.RO cs.SY eess.SY 50%

Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach

Mohit Srinivasan, Amogh Dabholkar, Samuel Coogan, Patricio Vela

专题命中安全训练：safety(abstract)

Comments Submitted to the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

1. 安全训练 3317 篇

Safe-visor Architecture for Sandboxing (AI-based) Unverified Controllers in Stochastic Cyber-Physical Systems

Assuring Increasingly Autonomous Systems in Human-Machine Teams: An Urban Air Mobility Case Study

Safe Human-Interactive Control via Shielding

Safe Model-Based Reinforcement Learning for Systems with Parametric Uncertainties

Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems

Generalization of Safe Optimal Control Actions on Networked Multi-Agent Systems

An Empirically grounded Agent Based simulator for the Air Traffic Management in the SESAR scenario

In-Bed Person Monitoring Using Thermal Infrared Sensors

Least-Restrictive Multi-Agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control

CPS Engineering: Gap Analysis and Perspectives

Constraint Learning for Control Tasks with Limited Duration Barrier Functions

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions

Manipulator-Independent Representations for Visual Imitation

MRSaiFE: Tissue Heating Prediction for MRI: a Feasibility Study

Collision Avoidance and Liveness of Multi-agent Systems with CBF-based Controllers

A Distributed Simplex Architecture for Multi-Agent Systems

Covariantizing Phase Space

Safe Reinforcement Learning for Emergency LoadShedding of Power Systems

Control Barrier Functions for Stochastic Systems

A Plausibility-based Fault Detection Method for High-level Fusion Perception Systems

Virtual Experience to Real World Application: Sidewalk Obstacle Avoidance Using Reinforcement Learning for Visually Impaired

Gentlemen on the Road: Understanding How Pedestrians Interpret Yielding Behavior of Autonomous Vehicles using Machine Learning

Sarin and Air Permeation Through a Nanoporous Graphene

Modulation of Control Authority in Adaptive HapticShared Control Paradigms

Deceptive Labeling: Hypergames on Graphs for Stealthy Deception

Learning to flock through reinforcement

Hybrid Blockchain-Enabled Secure Microservices Fabric for Decentralized Multi-Domain Avionics Systems

Barrier Functions for Multiagent-POMDPs with DTL Specifications

Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach