Large language models (LLMs) have shown promise in table Question Answering (Table QA). However, extending these capabilities to multi-table QA remains challenging due to unreliable schema linking across complex tables. Existing methods based on semantic similarity work well only on simplified hand-crafted datasets and struggle to handle complex, real-world scenarios with numerous and diverse columns. To address this, we propose a graph-based framework that leverages human-curated relational knowledge to explicitly encode schema links and join paths. Given a natural language query, our method searches on graph to construct interpretable reasoning chains, aided by pruning and sub-path merging strategies to enhance efficiency and coherence. Experiments on both standard benchmarks and a realistic, large-scale dataset demonstrate the effectiveness of our approach. To our knowledge, this is the first multi-table QA system applied to truly complex industrial tabular data.

Deploying autonomous robots in safety-critical domains requires architectures that ensure operational effectiveness and safety compliance. In this paper, we contribute the Safe-ROS architecture for developing reliable and verifiable autonomous robots in such domains. It features two distinct subsystems: (1) an intelligent control system that is responsible for normal/routine operations, and (2) a Safety System consisting of Safety Instrumented Functions (SIFs) that provide formally verifiable independent oversight. We demonstrate Safe-ROS on an AgileX Scout Mini robot performing autonomous inspection in a nuclear environment. One safety requirement is selected and instantiated as a SIF. To support verification, we implement the SIF as a cognitive agent, programmed to stop the robot whenever it detects that it is too close to an obstacle. We verify that the agent meets the safety requirement and integrate it into the autonomous inspection. This integration is also verified, and the full deployment is validated in a Gazebo simulation, and lab testing. We evaluate this architecture in the context of the UK nuclear sector, where safety and regulation are crucial aspects of deployment. Success criteria include the development of a formal property from the safety requirement, implementation, and verification of the SIF, and the integration of the SIF into the operational robotic autonomous system. Our results demonstrate that the Safe-ROS architecture can provide safety verifiable oversight while deploying autonomous robots in safety-critical domains, offering a robust framework that can be extended to additional requirements and various applications.

-- Collaborative robots (cobots) increasingly operate alongside humans, demanding robust real-time safeguarding. Current safety standards (e.g., ISO 10218, ANSI/RIA 15.06, ISO/TS 15066) require risk assessments but offer limited guidance for real-time responses. We propose a virtual fencing approach that detects and predicts human motion, ensuring safe cobot operation. Safety and performance tradeoffs are modeled as an optimization problem and solved via sequential quadratic programming. Experimental validation shows that our method minimizes operational pauses while maintaining safety, providing a modular solution for human-robot collaboration. I. INTRODUCTION Cobots, short for collaborative robots, have gained significant traction in various fields, such as manufacturing, assembly, service, education, and healthcare, due to their ability to seamlessly interact with humans while ensuring their physical and mental well-being [1]-[3].

The Single-Turn Crescendo Attack (STCA), first introduced in Aqrawi and Abbasi [2024], is an innovative method designed to bypass the ethical safeguards of text-to-text AI models, compelling them to generate harmful content. This technique leverages a strategic escalation of context within a single prompt, combined with trust-building mechanisms, to subtly deceive the model into producing unintended outputs. Extending the application of STCA to text-to-image models, we demonstrate its efficacy by compromising the guardrails of a widely-used model, DALL-E 3, achieving outputs comparable to outputs from the uncensored model Flux Schnell, which served as a baseline control. This study provides a framework for researchers to rigorously evaluate the robustness of guardrails in text-to-image models and benchmark their resilience against adversarial attacks.

Understanding is a crucial yet elusive concept in artificial intelligence (AI). This work proposes a framework for analyzing understanding based on the notion of composability. Given any subject (e.g., a person or an AI), we suggest characterizing its understanding of an object in terms of its ability to process (compose) relevant inputs into satisfactory outputs from the perspective of a verifier. This highly universal framework can readily apply to non-human subjects, such as AIs, non-human animals, and institutions. Further, we propose methods for analyzing the inputs that enhance output quality in compositions, which we call catalysts. We show how the structure of a subject can be revealed by analyzing its components that act as catalysts and argue that a subject's learning ability can be regarded as its ability to compose inputs into its inner catalysts. Finally we examine the importance of learning ability for AIs to attain general intelligence. Our analysis indicates that models capable of generating outputs that can function as their own catalysts, such as language models, establish a foundation for potentially overcoming existing limitations in AI understanding.

We present an approach for predictive braking of a four-wheeled vehicle on a nonplanar road. Our main contribution is a methodology to consider friction and road contact safety on general smooth road geometry. We use this to develop an active safety system to preemptively reduce vehicle speed for upcoming road geometry, such as off-camber turns. Our system may be used for human-driven or autonomous vehicles and we demonstrate it with a simulated ADAS scenario. We show that loss of control due to driver error on nonplanar roads can be mitigated by our approach.

As factories continue to evolve into collaborative spaces with multiple robots working together with human supervisors in the loop, ensuring safety for all actors involved becomes critical. Currently, laser-based light curtain sensors are widely used in factories for safety monitoring. While these conventional safety sensors meet high accuracy standards, they are difficult to reconfigure and can only monitor a fixed user-defined region of space. Furthermore, they are typically expensive. Instead, we leverage a controllable depth sensor, programmable light curtains (PLC), to develop an inexpensive and flexible real-time safety monitoring system for collaborative robot workspaces. Our system projects virtual dynamic safety envelopes that tightly envelop the moving robot at all times and detect any objects that intrude the envelope. Furthermore, we develop an instrumentation algorithm that optimally places (multiple) PLCs in a workspace to maximize the visibility coverage of robots. Our work enables fence-less human-robot collaboration, while scaling to monitor multiple robots with few sensors. We analyze our system in a real manufacturing testbed with four robot arms and demonstrate its capabilities as a fast, accurate, and inexpensive safety monitoring solution.

The growing use of robots in urban environments has raised concerns about potential safety hazards, especially in public spaces where humans and robots may interact. In this paper, we present a system for safe human-robot interaction that combines an infrared (IR) camera with a wearable marker and airflow potential field. IR cameras enable real-time detection and tracking of humans in challenging environments, while controlled airflow creates a physical barrier that guides humans away from dangerous proximity to robots without the need for wearable devices. A preliminary experiment was conducted to measure the accuracy of the perception of safety barriers rendered by controlled air pressure. In a second experiment, we evaluated our approach in an imitation scenario of an interaction between an inattentive person and an autonomous robotic system. Experimental results show that the proposed system significantly improves a participant's ability to maintain a safe distance from the operating robot compared to trials without the system.

Passenger aircraft with AI co-pilots could be flying travellers to their destinations in the future, says Tim Clark, president of airline Emirates. He told CNBC: 'You might see a one-pilot aircraft. Could the aircraft be flown on a fully automated basis? Yes it could, technology is right up there now. '[But passengers] like to think there are two pilots up there.

Developing safety and efficiency applications for Connected and Automated Vehicles (CAVs) require a great deal of testing and evaluation. The need for the operation of these systems in critical and dangerous situations makes the burden of their evaluation very costly, possibly dangerous, and time-consuming. As an alternative, researchers attempt to study and evaluate their algorithms and designs using simulation platforms. Modeling the behavior of drivers or human operators in CAVs or other vehicles interacting with them is one of the main challenges of such simulations. While developing a perfect model for human behavior is a challenging task and an open problem, we present a significant augmentation of the current models used in simulators for driver behavior. In this paper, we present a simulation platform for a hybrid transportation system that includes both human-driven and automated vehicles. In addition, we decompose the human driving task and offer a modular approach to simulating a large-scale traffic scenario, allowing for a thorough investigation of automated and active safety systems. Such representation through Interconnected modules offers a human-interpretable system that can be tuned to represent different classes of drivers. Additionally, we analyze a large driving dataset to extract expressive parameters that would best describe different driving characteristics. Finally, we recreate a similarly dense traffic scenario within our simulator and conduct a thorough analysis of various human-specific and system-specific factors, studying their effect on traffic network performance and safety.