Deep transformer models excel at multi-label text classification but often violate domain logic that experts consider essential, an issue of particular concern in safety-critical applications. We propose a hybrid neuro-symbolic framework that integrates Answer Set Programming (ASP) with transformer-based learning on the Aviation Safety Reporting System (ASRS) corpus. Domain knowledge is formalized as weighted ASP rules and validated using the Clingo solver. These rules are incorporated in two complementary ways: (i) as rule-based data augmentation, generating logically consistent synthetic samples that improve label diversity and coverage; and (ii) as a fuzzy-logic regularizer, enforcing rule satisfaction in a differentiable form during fine-tuning. This design preserves the interpretability of symbolic reasoning while leveraging the scalability of deep neural architectures. We further tune per-class thresholds and report both standard classification metrics and logic-consistency rates. Compared to a strong Binary Cross-Entropy (BCE) baseline, our approach improves micro- and macro-F1 scores and achieves up to an 86% reduction in rule violations on the ASRS test set. To the best of our knowledge, this constitutes the first large-scale neuro-symbolic application to ASRS reports that unifies ASP-based reasoning, rule-driven augmentation, and differentiable transformer training for trustworthy, safety-critical NLP.

Charlie Kirk suspect's motive revealed as vile political messages surface after his arrest: Live updates Charlie Kirk'killer' identified as Tyler Robinson after assassination in Utah Haunting Trump costume worn by Charlie Kirk'assassin' Transgender Team USA cyclist celebrates Charlie Kirk's murder in disgusting posts I've analyzed Charlie Kirk's guards' mysterious hand signals. As a top cop I know exactly what they're doing... JAN MOIR: For a moment the cheery mask slipped, the game face had gone. Everything we know about Charlie Kirk'assassin' Tyler Robinson's parents Matt and Amber Trump reveals crucial tip-off that led to arrest of Charlie Kirk's alleged assassin Insiders reveal all the details from Nina Dobrev and Shaun White's break up... as they call off engagement after five years together Inspiring bravery of Charlie Kirk's devastated widow Erika as she waves to supporters on her husband's final journey Go inside the killing that has rocked America - on Daily Mail's podcast The Assassination of Charlie Kirk McDonald's fans disgusted by what customer thinks is'parasite' found in Filet-O-Fish I ran a mile every day for 100 days - here's how it completely changed my body Two people were injured after a fire was detected on board a United Airlines flight, forcing the plane to make an emergency landing. United Flight 32 was headed from Japan to the Philippines when the crew was alerted that flames had erupted in the aircraft's cargo hold just 50 minutes into the trip. The plane carrying 142 passengers and crew was still over Japan when its pilots turned back and landed at Kansai International Airport near Osaka around 6am ET.

Large Language Models (LLMs) pre-trained on internet-scale datasets have shown impressive capabilities in code understanding, synthesis, and general purpose question-and-answering. Key to their performance is the substantial prior knowledge acquired during training and their ability to reason over extended sequences of symbols, often presented in natural language. In this work, we aim to harness the extensive long-term reasoning, natural language comprehension, and the available prior knowledge of LLMs for increased resilience and adaptation in autonomous mobile robots. We introduce REAL, an approach for REsilience and Adaptation using LLMs. REAL provides a strategy to employ LLMs as a part of the mission planning and control framework of an autonomous robot. The LLM employed by REAL provides (i) a source of prior knowledge to increase resilience for challenging scenarios that the system had not been explicitly designed for; (ii) a way to interpret natural-language and other log/diagnostic information available in the autonomy stack, for mission planning; (iii) a way to adapt the control inputs using minimal user-provided prior knowledge about the dynamics/kinematics of the robot. We integrate REAL in the autonomy stack of a real multirotor, querying onboard an offboard LLM at 0.1-1.0 Hz as part the robot's mission planning and control feedback loops. We demonstrate in real-world experiments the ability of the LLM to reduce the position tracking errors of a multirotor under the presence of (i) errors in the parameters of the controller and (ii) unmodeled dynamics. We also show (iii) decision making to avoid potentially dangerous scenarios (e.g., robot oscillates) that had not been explicitly accounted for in the initial prompt design.

The unmanned aerial vehicles (UAVs) technology, which is moving towards full autonomous flight, requires operation under uncertainties due to dynamic environments, interaction with humans, system faults, and even malicious cyber attacks. Ensuring security and safety is the first step to making the solutions using such systems certifiable and scalable. In this paper, we introduce an autopilot framework called "Multi-level Adaptive Safety Control" (MASC) for the resilient control of autonomous UAVs under large uncertainties and employ it for engine-out automatic landing under severe weather conditions. A. MASC Architecture In 2009, an Airbus A320 passenger plane (US Airways flight 1549) lost both engines minutes after take-off from LaGuardia airport in New York City due to severe bird strikes [1]. Captain Sullenberger safely landed the plane in the nearby Hudson River. Inspired by this story, we aim to equip UAVs with the capability of human pilots to determine if the current mission is still possible after a severe system failure. If not, the mission is re-planned so that it can be accomplished using the remaining capabilities. This is achieved by the proposed autopilot framework, MASC, which is capable of performing safe maneuvers that are traditionally reserved for human pilots.

To certify UAV operations in populated areas, risk mitigation strategies -- such as Emergency Landing (EL) -- must be in place to account for potential failures. EL aims at reducing ground risk by finding safe landing areas using on-board sensors. The first contribution of this paper is to present a new EL approach, in line with safety requirements introduced in recent research. In particular, the proposed EL pipeline includes mechanisms to monitor learning based components during execution. This way, another contribution is to study the behavior of Machine Learning Runtime Monitoring (MLRM) approaches within the context of a real-world critical system. A new evaluation methodology is introduced, and applied to assess the practical safety benefits of three MLRM mechanisms. The proposed approach is compared to a default mitigation strategy (open a parachute when a failure is detected), and appears to be much safer.

FBI agents have arrested a Hollywood man, accusing him of recklessly operating a drone and crashing it into a Los Angeles Police Department helicopter earlier this year. The collision damaged the chopper's fuselage and required the LAPD pilot to make an emergency landing following the September encounter. The drone, which authorities say was operated by Andrew Rene Hernandez, then tumbled from the sky and crashed into a vehicle. Hernandez, 22, was arrested Thursday and charged with unsafe operation of an unmanned aircraft after an investigation by the FBI, the LAPD and the Federal Aviation Administration. The potentially deadly collision occurred Sept. 18 after Los Angeles police officers responding to a predawn burglary call at a Hollywood pharmacy requested air support.

It's been a tough year or so for Air Force maintainers. High-profile aircraft failures plagued the service recently, including emergency landings of C-5 cargo aircraft, the grounding of the B-1 bomber fleet, and the loss of a C-130 propeller in mid-flight. The immediate causes of these accidents vary, the but root cause is the same: age. The average age of an Air Force aircraft is 28 years, and many planes are significantly older. Crews fly still fly the B-52 bomber, after all, with its average age of 56.

First, I offer you a review of the movie "Sully" -- and don't worry, there aren't any spoilers. Because you know how the story goes: Birds hit plane. Pilot, nicknamed "Sully," lands plane on Hudson. So how do you make a movie out of something when everyone knows how it turns out? Yes, you can bring up the success of the film "Titanic," but it's not like there was actual footage of that disaster on YouTube.