大模型对齐与安全 - arXivDaily 专题

2103.01840 2022-11-15 cs.RO math.OC 50%

Multi-robot task allocation for safe planning against stochastic hazard dynamics

Daniel Tihanyi, Yimeng Lu, Orcun Karaca, Maryam Kamgarpour

专题命中安全训练：safety(abstract)

2105.05701 2022-11-08 eess.SY cs.SY 50%

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

Dong Chen, Mohammad Hajidavalloo, Zhaojian Li, Kaian Chen, Yongqiang Wang, Longsheng Jiang, Yue Wang

专题命中安全训练：safety(abstract)

Comments 15 figures

2210.17381 2022-11-01 cs.RO cs.MA 50%

Safe and Efficient Manoeuvring for Emergency Vehicles in Autonomous Traffic using Multi-Agent Proximal Policy Optimisation

Leandro Parada, Eduardo Candela, Luis Marques, Panagiotis Angeloudis

专题命中安全训练：safety(abstract)

2210.16944 2022-11-01 math.OC 50%

Personalized Dose Guidance using Safe Bayesian Optimization

Dinesh Krishnamoorthy, Francis J. Doyle

专题命中安全训练：safety(abstract)

Comments Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc. 09 pages

2210.09586 2022-10-19 cs.NI 50%

Deep Deterministic Policy Gradient to Minimize the Age of Information in Cellular V2X Communications

Zoubeir Mlika, Soumaya Cherkaoui

专题命中安全训练：safety(abstract)

Comments 16 pages, 11 figures, 2 tables, 2 algorithms

Journal ref IEEE Transactions on Intelligent Transportation Systems, 25 July 2022

2209.14042 2022-09-29 cs.MA cs.LO cs.RO 50%

Generating Safe Autonomous Decision-Making in ROS

Yi Yang, Tom Holvoet

专题命中安全训练：safety(abstract)

Comments In Proceedings FMAS2022 ASYDE2022, arXiv:2209.13181

Journal ref EPTCS 371, 2022, pp. 184-192

2209.14036 2022-09-29 cs.LO cs.FL cs.SE 50%

Towards a Digital Highway Code using Formal Modelling and Verification of Timed Automata

Gleifer Vaz Alves, Maike Schwammberger

专题命中安全训练：trustworthy(abstract)

Comments In Proceedings FMAS2022 ASYDE2022, arXiv:2209.13181

Journal ref EPTCS 371, 2022, pp. 77-85

2209.01120 2022-09-05 eess.SY cs.SY 50%

A Universal Framework for Generalized Run Time Assurance with JAX Automatic Differentiation

Umberto Ravaioli, Kyle Dunlap, Kerianne Hobbs

专题命中安全训练：safety(abstract)

2208.13555 2022-08-30 cs.CV 50%

Explainability of Deep Learning models for Urban Space perception

Ruben Sangers, Jan van Gemert, Sander van Cranenburgh

专题命中安全训练：safety(abstract)

Comments 5 pages, 3 figures

2208.06949 2022-08-17 cs.RO 50%

MACE: Multi-Agent Autonomous Collaborative Exploration of Unknown Environments

Charbel Toumieh, Alain Lambert

专题命中安全训练：safety(abstract)

2208.00824 2022-08-02 cs.CV 50%

Safe Perception -- A Hierarchical Monitor Approach

Cornelius Buerkle, Fabian Oboril, Johannes Burr, Kay-Ulrich Scholl

专题命中安全训练：safety(abstract)

2208.00096 2022-08-02 cs.RO cs.MA 50%

Perspectives on the System-level Design of a Safe Autonomous Driving Stack

Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy

专题命中安全训练：safety(abstract)

Comments AI Communications special issue on Multi-agent Systems Research in the UK

2207.10275 2022-07-22 eess.SY cs.SY 50%

Adversary Detection and Resilient Control for Multi-Agent Systems

Aquib Mustafa, Dimitra Panagou

专题命中安全训练：safety(abstract)

2207.05896 2022-07-14 cs.RO cs.SY eess.SY 50%

Safe Human-Robot Collaborative Transportation via Trust-Driven Role Adaptation

Tony Zheng, Monimoy Bujarbaruah, Yvonne R. Stürz, Francesco Borrelli

专题命中安全训练：safety(abstract)

2207.05220 2022-07-13 eess.SY cs.RO cs.SY math.OC 50%

Safe Drone Flight with Time-Varying Backup Controllers

Andrew Singletary, Aiden Swann, Ivan Dario Jimenez Rodriguez, Aaron D. Ames

专题命中安全训练：safety(abstract)

Comments Submitted to IROS 2022

2207.04915 2022-07-12 eess.SY cs.SY 50%

Multi-agent systems with CBF-based controllers -- collision avoidance and liveness from instability

Mrdjan Jankovic, Mario Santillo, Yan Wang

专题命中安全训练：safety(abstract)

Comments 12 pages, 13 figures. arXiv admin note: substantial text overlap with arXiv:2012.10261

2207.02281 2022-07-07 cs.CV 50%

BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection

Asiegbu Miracle Kanu-Asiegbu, Ram Vasudevan, Xiaoxiao Du

专题命中安全训练：safety(abstract)

Comments Accepted in Workshop on Safe Learning for Autonomous Driving, co-located with the International Conference on Machine Learning (ICML 20222)

2204.12106 2022-06-29 eess.SY cs.SY 50%

Razumikhin and Krasovskii Approaches for Safe Stabilization

Wei Ren, Raphael M. Jungers, Dimos V. Dimarogonas

专题命中安全训练：safety(abstract)

Comments 15 pages, 12 figures, accepted as Regular Paper by Automatica

2206.12348 2022-06-27 cs.RO cs.SY eess.SY 50%

MPC-based Imitation Learning for Safe and Human-like Autonomous Driving

Flavia Sofia Acerbo, Jan Swevers, Tinne Tuytelaars, Tong Duy Son

专题命中安全训练：safety(abstract)

Comments Accepted at the 1st Workshop on Safe Learning for Autonomous Driving (SL4AD), co-located with the 39th International Conference on Machine Learning (ICML 2022)

2105.07620 2022-05-19 cs.RO 50%

APPL: Adaptive Planner Parameter Learning

Xuesu Xiao, Zizhao Wang, Zifan Xu, Bo Liu, Garrett Warnell, Gauraang Dhamankar, Anirudh Nair, Peter Stone

专题命中安全训练：safety(abstract)

2009.14509 2022-05-10 cs.RO 50%

Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning

Qiaoyun Wu, Xiaoxi Gong, Kai Xu, Dinesh Manocha, Jingxuan Dong, Jun Wang

专题命中安全训练：safety(abstract)

Comments accepted by IEEE Robotics and Automation Letters

2204.04555 2022-04-12 math.OC cs.RO 50%

Trust-based Rate-Tunable Control Barrier Functions for Non-Cooperative Multi-Agent Systems

Hardik Parwana, Dimitra Panagou

专题命中安全训练：safety(abstract)

Comments Submitted to a conference for review

2203.14924 2022-03-29 eess.SY cs.SY 50%

Sandboxing (AI-based) Unverified Controllers in Stochastic Games: An Abstraction-based Approach with Safe-visor Architecture

Bingzhuo Zhong, Hongpeng Cao, Majid Zamani, Marco Caccamo

专题命中安全训练：safety(abstract)

2203.14473 2022-03-29 cs.DB 50%

Towards Dynamic and Safe Configuration Tuning for Cloud Databases

Xinyi Zhang, Hong Wu, Yang Li, Jian Tan, Feifei Li, Bin Cui

专题命中安全训练：safety(abstract)

2203.03017 2022-03-08 cs.RO 50%

A Composable Framework for Policy Design, Learning, and Transfer Toward Safe and Efficient Industrial Insertion

Rui Chen, Chenxi Wang, Tianhao Wei, Changliu Liu

专题命中安全训练：safety(abstract)

2203.01807 2022-03-04 cs.RO 50%

Quadrotor Formation Flying Resilient to Abrupt Vehicle Failures via a Fluid Flow Navigation Function

Matthew Romano, Harshvardhan Uppaluru, Hossein Rastgoftar, Ella Atkins

专题命中安全训练：safety(abstract)

Comments Submitted to IROS 2022

2109.07673 2022-03-03 eess.SY cs.MA cs.RO cs.SY 50%

Back to the Future: Efficient, Time-Consistent Solutions in Reach-Avoid Games

Dennis R. Anthony, Duy P. Nguyen, David Fridovich-Keil, Jaime F. Fisac

专题命中安全训练：safety(abstract)

Comments accepted to ICRA 2022

2109.09041 2022-01-04 cs.RO cs.SY eess.SY 50%

Online Distributed Trajectory Planning for Quadrotor Swarm with Feasibility Guarantee using Linear Safe Corridor

Jungwon Park, Dabin Kim, Gyeong Chan Kim, Dahyun Oh, H. Jin Kim

专题命中安全训练：safety(abstract)

Comments 8 pages, RA-L 2022 under review

2112.02441 2021-12-07 math.OC stat.ML 50%

DNN-based Policies for Stochastic AC OPF

Sarthak Gupta, Sidhant Misra, Deepjyoti Deka, Vassilis Kekatos

专题命中安全训练：safety(abstract)

2110.00054 2021-10-29 cs.CV 50%

Learning to Predict Trustworthiness with Steep Slope Loss

Yan Luo, Yongkang Wong, Mohan S. Kankanhalli, Qi Zhao

专题命中安全训练：trustworthy(abstract)

Comments NeurIPS 2021

1. 安全训练 3317 篇

Multi-robot task allocation for safe planning against stochastic hazard dynamics

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

Safe and Efficient Manoeuvring for Emergency Vehicles in Autonomous Traffic using Multi-Agent Proximal Policy Optimisation

Personalized Dose Guidance using Safe Bayesian Optimization

Deep Deterministic Policy Gradient to Minimize the Age of Information in Cellular V2X Communications

Generating Safe Autonomous Decision-Making in ROS

Towards a Digital Highway Code using Formal Modelling and Verification of Timed Automata

A Universal Framework for Generalized Run Time Assurance with JAX Automatic Differentiation

Explainability of Deep Learning models for Urban Space perception

MACE: Multi-Agent Autonomous Collaborative Exploration of Unknown Environments

Safe Perception -- A Hierarchical Monitor Approach

Perspectives on the System-level Design of a Safe Autonomous Driving Stack

Adversary Detection and Resilient Control for Multi-Agent Systems

Safe Human-Robot Collaborative Transportation via Trust-Driven Role Adaptation

Safe Drone Flight with Time-Varying Backup Controllers

Multi-agent systems with CBF-based controllers -- collision avoidance and liveness from instability

BiPOCO: Bi-Directional Trajectory Prediction with Pose Constraints for Pedestrian Anomaly Detection

Razumikhin and Krasovskii Approaches for Safe Stabilization

MPC-based Imitation Learning for Safe and Human-like Autonomous Driving

APPL: Adaptive Planner Parameter Learning

Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning

Trust-based Rate-Tunable Control Barrier Functions for Non-Cooperative Multi-Agent Systems

Sandboxing (AI-based) Unverified Controllers in Stochastic Games: An Abstraction-based Approach with Safe-visor Architecture

Towards Dynamic and Safe Configuration Tuning for Cloud Databases

A Composable Framework for Policy Design, Learning, and Transfer Toward Safe and Efficient Industrial Insertion

Quadrotor Formation Flying Resilient to Abrupt Vehicle Failures via a Fluid Flow Navigation Function

Back to the Future: Efficient, Time-Consistent Solutions in Reach-Avoid Games

Online Distributed Trajectory Planning for Quadrotor Swarm with Feasibility Guarantee using Linear Safe Corridor

DNN-based Policies for Stochastic AC OPF

Learning to Predict Trustworthiness with Steep Slope Loss