Mars exploration requires precise and reliable terrain models to ensure safe rover navigation across its unpredictable and often hazardous landscapes. Stereoscopic vision serves a critical role in the rover's perception, allowing scene reconstruction by generating precise depth maps through stereo matching. State-of-the-art Martian planetary exploration uses traditional local block-matching, aggregates cost over square windows, and refines disparities via smoothness constraints. However, this method often struggles with low-texture images, occlusion, and repetitive patterns because it considers only limited neighbouring pixels and lacks a wider understanding of scene context. This paper uses Semi-Global Matching (SGM) with superpixel-based refinement to mitigate the inherent block artefacts and recover lost details. The approach balances the efficiency and accuracy of SGM and adds context-aware segmentation to support more coherent depth inference. The proposed method has been evaluated in three datasets with successful results: In a Mars analogue, the terrain maps obtained show improved structural consistency, particularly in sloped or occlusion-prone regions. Large gaps behind rocks, which are common in raw disparity outputs, are reduced, and surface details like small rocks and edges are captured more accurately. Another two datasets, evaluated to test the method's general robustness and adaptability, show more precise disparity maps and more consistent terrain models, better suited for the demands of autonomous navigation on Mars, and competitive accuracy across both non-occluded and full-image error metrics. This paper outlines the entire terrain modelling process, from finding corresponding features to generating the final 2D navigation maps, offering a complete pipeline suitable for integration in future planetary exploration missions.

With the advent of 6G, Open Radio Access Network (O-RAN) architectures are evolving to support intelligent, adaptive, and automated network orchestration. This paper proposes a novel Edge AI and Network Service Orchestration framework that leverages Large Language Model (LLM) agents deployed as O-RAN rApps. The proposed LLM-agent-powered system enables interactive and intuitive orchestration by translating the user's use case description into deployable AI services and corresponding network configurations. The LLM agent automates multiple tasks, including AI model selection from repositories (e.g., Hugging Face), service deployment, network adaptation, and real-time monitoring via xApps. We implement a prototype using open-source O-RAN projects (OpenAirInterface and FlexRIC) to demonstrate the feasibility and functionality of our framework. Our demonstration showcases the end-to-end flow of AI service orchestration, from user interaction to network adaptation, ensuring Quality of Service (QoS) compliance. This work highlights the potential of integrating LLM-driven automation into 6G O-RAN ecosystems, paving the way for more accessible and efficient edge AI ecosystems.

Making the Artificial Intelligent So where to start? Is it even possible to go from wetware to... "No diet will remove all the fat from your body because the brain is entirely fat. Brain imaging techniques (the new phrenology?!) Pretending we know more than we do is not the way forward... ...especially at high speed This is our chance to change what it means to be human Adjacent Possible "Chance favours only the prepared mind" Between 30% and 50% of all scientific discoveries are accidental in some sense sagacious "Scientists are not passive recipients of the unexpected; rather, they actively create the conditions for discovering the unexpected" Kevin Dunbar and Jonathan Fugelsang "premature mystery reduction" Is it any wonder people are worried? Technology and AI have the potential to become an intimate part of our brains, bodies and lives and that's why I call it... how we think about technology ...and so nurture two of the factors that make humans intelligent Empathy frame I believe we can Re Curiosity Narrowcasting "My primary goal of hacking was the intellectual curiosity, the seduction of adventure" Kevin Mitnick By extending our empathy and developing our curiosity we will be more.... Rather than AI being feared, it may be something that could change the fundamental nature of what it is to be human; akin to Prometheus taking fire from the gods.

Police are investigating a reported mid-air collision between a drone and a British Airways jet from Geneva that was approaching London's Heathrow Airport. BA said the Airbus A320 was not damaged when the object hit the nose of the plane, which landed safely with no injuries reported to anyone on board. Since April last year there have been 25 near misses between aircraft and drones, figures from the UK Airprox Board suggest. A dozen of these were denoted "Class A" which indicates there was a serious risk of collision. The Heathrow incident comes only weeks after the British Airline Pilots Association called for rules governing the use of drones to be enforced more strictly.