English
Related papers

Related papers: Virtual Adversarial Humans finding Hazards in Robo…

200 papers

Artificial intelligence is known as the most effective technological field for rapid developments shaping the future of the world. Even today, it is possible to see intense use of intelligence systems in all fields of the life. Although…

Machine Learning · Computer Science 2019-10-16 Utku Kose

Including human analysis has the potential to positively affect the robustness of Deep Neural Networks and is relatively unexplored in the Adversarial Machine Learning literature. Neural network visual explanation maps have been shown to be…

Machine Learning · Computer Science 2023-08-28 Ryan McCoppin , Marla Kennedy , Platon Lukyanenko , Sean Kennedy

High-risk industries like nuclear and aviation use real-time monitoring to detect dangerous system conditions. Similarly, Large Language Models (LLMs) need monitoring safeguards. We propose a real-time framework to predict harmful AI…

Artificial Intelligence · Computer Science 2025-05-21 Maheep Chaudhary , Fazl Barez

Learning from human feedback is a popular approach to train robots to adapt to user preferences and improve safety. Existing approaches typically consider a single querying (interaction) format when seeking human feedback and do not…

Robotics · Computer Science 2026-01-16 Yashwanthi Anand , Nnamdi Nwagwu , Kevin Sabbe , Naomi T. Fitter , Sandhya Saisubramanian

Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to…

Machine Learning · Computer Science 2018-03-28 Tegjyot Singh Sethi , Mehmed Kantardzic , Lingyu Lyua , Jiashun Chen

Recent advancements in robotics have increased the possibilities for integrating robotic systems into human-involved workplaces, highlighting the need to examine and optimize human-robot coordination in collaborative settings. This study…

Robotics · Computer Science 2025-11-26 Róisín Keenan , Joost C. Dessing

Operational safety at mission-critical work sites is a top priority given the complex and hazardous nature of daily tasks. This paper presents the Human-Agent Risk Navigation and Event Safety System (HARNESS), a modular AI framework…

As Artificial Intelligence (AI) increasingly supports human decision-making, its vulnerability to adversarial attacks grows. However, the existing adversarial analysis predominantly focuses on fully autonomous AI systems, where decisions…

Human-Computer Interaction · Computer Science 2025-09-29 Shutong Fan , Lan Zhang , Xiaoyong Yuan

This paper addresses the problem of evaluating learning systems in safety critical domains such as autonomous driving, where failures can have catastrophic consequences. We focus on two problems: searching for scenarios when learned agents…

This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and…

Ensuring human safety is of paramount importance in warehouse environments that feature mixed traffic of human workers and autonomous mobile robots (AMRs). Current approaches often treat humans as generic dynamic obstacles, leading to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Maximilian Haug , Christian Stippel , Lukas Pscherer , Benjamin Schwendinger , Ralph Hoch , Angel Gaydarov , Sebastian Schlund , Thilo Sauter

Robots will bring search and rescue (SaR) in disaster response to another level, in case they can autonomously take over dangerous SaR tasks from humans. A main challenge for autonomous SaR robots is to safely navigate in cluttered…

Robotics · Computer Science 2025-05-07 Karlo Rado , Mirko Baglioni , Anahita Jamshidnejad

Self-adaptive robots operate in dynamic, unpredictable environments where unaddressed uncertainties can lead to safety violations and operational failures. However, systematically identifying and analyzing these uncertainties, including…

Robotics · Computer Science 2026-05-06 Hassan Sartaj , Jalil Boudjadar , Mirgita Frasheri , Shaukat Ali , Peter Gorm Larsen

Evaluating the decision-making system is indispensable in developing autonomous vehicles, while realistic and challenging safety-critical test scenarios play a crucial role. Obtaining these scenarios is non-trivial, thanks to the…

Robotics · Computer Science 2024-08-08 Kunkun Hao , Yonggang Luo , Wen Cui , Yuqiao Bai , Jucheng Yang , Songyang Yan , Yuxi Pan , Zijiang Yang

During the conceptual and prototype design stage of an industrial product, it is crucial to take assembly/disassembly and maintenance operations in advance. A well-designed system should enable relatively easy access of operating…

Robotics · Computer Science 2012-06-08 Liang Ma , Ruina Ma , Damien Chablat , Fouad Bennis

Human-robot interaction frequently involves physical proximity or contact. In human-human settings, people flexibly accept, reject, or tolerate such approaches depending on the relationship and context. We explore the design of a robot's…

Robotics · Computer Science 2025-11-03 Tomoko Yonezawa , Hirotake Yamazoe , Atsuo Fujino , Daigo Suhara , Takaya Tamamoto , Yuto Nishiguchi

As robots become increasingly prominent in diverse industrial settings, the desire for an accessible and reliable system has correspondingly increased. Yet, the task of meaningfully assessing the feasibility of introducing a new robotic…

Robotics · Computer Science 2023-05-26 Minh Q. Tram , Joseph M. Cloud , William J. Beksi

In predictive process monitoring, predictive models are vulnerable to adversarial attacks, where input perturbations can lead to incorrect predictions. Unlike in computer vision, where these perturbations are designed to be imperceptible to…

Machine Learning · Computer Science 2024-11-22 Alexander Stevens , Jari Peeperkorn , Johannes De Smedt , Jochen De Weerdt

Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Nandish Chattopadhyay , Abdul Basit , Bassem Ouni , Muhammad Shafique

AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks. We present HAICOSYSTEM, a framework examining AI agent safety within diverse and complex social…