Claire chatted to Christine Evers from University of Southampton about helping robots understand the world around them through sound. Christine Evers is an Associate Professor in Computer Science and Director of the Centre for Robotics at the University of Southampton. Her research pushes the boundaries of machine listening, enabling robots to make sense of life in sound. Her current focus is embedding our understanding of the human auditory process into deep-learning audio architectures. This bio-inspired approach moves away from massive, internet-scale models toward compute-efficient and inherently interpretable systems - opening the door to a new generation of embodied auditory intelligence.

Abstract--As long-endurance and seafloor-resident AUVs become more capable, there is an increasing need for extended, real-time interpretation of seafloor imagery to enable adaptive missions and optimise communication efficiency. Although offline image analysis methods are well established, they rely on access to complete datasets and human-labelled examples to manage the strong influence of environmental and operational conditions on seafloor image appearance--requirements that cannot be met in real-time settings. T o address this, we introduce an online clustering framework (OCF) capable of interpreting seafloor imagery without supervision, that is designed to operate in real-time on continuous data streams in a scalable, adaptive, and self-consistent manner . The method enables the efficient review and consolidation of common patterns across the entire data history in constant time by identifying and maintaining a set of representative samples that capture the evolving feature distribution, supporting dynamic cluster merging and splitting without reprocessing the full image history. We evaluate the framework on three diverse seafloor image datasets, analysing the impact of different representative sampling strategies on both clustering accuracy and computational cost. The OCF achieves the highest average F1 score of 0.68 across the three datasets among all comparative online clustering approaches, with a standard deviation of 3% across three distinct survey trajectories, demonstrating its superior clustering capability and robustness to trajectory variation. In addition, it maintains consistently lower and bounded computational time as the data volume increases. Compared to offline clustering methods, it strikes a favourable balance between accuracy and efficiency. These properties are beneficial for generating survey data summaries and supporting informative path planning in long-term, persistent autonomous marine exploration.

It has been 113 years since the Titanic sank beneath the waves, claiming the lives of more than 1,500 passengers and crew. But new evidence has finally cleared the tragedy's Scottish scapegoat: First Officer William Murdoch. For years, Officer Murdoch has been accused of taking bribes, abandoning his post, and was even depicted shooting a passenger in the James Cameron movie. Now, more than a century later, 3D scans show that Officer Murdoch did not flee his position, but died while helping passengers escape until the very end. Deep sea scanning company Magellan has snapped 715,000 photos of the Titanic wreck 12,500 feet beneath the Atlantic.

The RMS Titanic sank in the North Atlantic Ocean on April 15, 1912, after colliding with an iceberg during her maiden voyage from Southampton to New York. More than 1,500 people died when the ship, which was carrying 2,224 passengers and crew, sank under the command of Captain Edward Smith. Some of the wealthiest people in the world were on board, including property tycoon John Jacob Astor IV, great grandson of John Jacob Astor, founder of the Waldorf Astoria Hotel. Millionaire Benjamin Guggenheim, heir to his family's mining business, also perished, along with Isidor Straus, the German-born co-owner of Macy's department store. The ship was the largest afloat at the time and was designed in such a way that it was meant to be'unsinkable'.

In a world and industry which is becoming more commercialised, over sanitised, robotic, structured and predictable, Tyler's greatest strength is the opposite to all of that." That's quite the sell for Southampton's 19-year-old midfield star Tyler Dibling, especially given his basic Premier League career numbers amount to 25 appearances, 1540 minutes played, two goals and zero assists. But that gushing description from one senior source at the club, speaking to BBC Sport anonymously, hints at an emerging talent interesting a host of top clubs and why there are some unsubstantiated reports of a 100m price tag on his head. With the Saints facing an immediate relegation back to the Championship, Dibling's future is likely to be one of the summer's more interesting sagas, with Manchester United, Arsenal, Tottenham and Bayern Munich all reportedly chasing his signature. Another source close to the club suggested Southampton turned down previously unreported bids of 35m from Tottenham and 30m from RB Leipzig in January, with the club valuing Dibling at 55m at the start of the winter window. Southampton have not commented on those rumours, but what is known is that Dibling is one of the lowest paid players in Southampton's squad and has a deal that expires in 2027, after Southampton triggered a 12-month extension option. He signed his last contract in December 2023, when he had played just five minutes of senior football. The England Under-21 international has so far resisted the club's offers of a new deal in what has been a breakthrough season for him, despite a wretched campaign which could still see Southampton relegated with the Premier League's lowest ever points total. His dribbles completed per game (2.34) and fouls won per game (2.57) place him in the top 10. "He's the most fearless player I've ever worked with," former Saints Under-21 head coach Adam Asghar tells BBC Sport. "He's totally unique to anything I've seen before.

Consensus building is inherently challenging due to the diverse opinions held by stakeholders. Effective facilitation is crucial to support the consensus building process and enable efficient group decision making. However, the effectiveness of facilitation is often constrained by human factors such as limited experience and scalability. In this research, we propose a Parallel Thinking-based Facilitation Agent (PTFA) that facilitates online, text-based consensus building processes. The PTFA automatically collects textual posts and leverages large language models (LLMs) to perform all of the six distinct roles of the well-established Six Thinking Hats technique in parallel thinking. To illustrate the potential of PTFA, a pilot study was carried out and PTFA's ability in idea generation, emotional probing, and deeper analysis of ideas was demonstrated. Furthermore, a comprehensive dataset that contains not only the conversational content among the participants but also between the participants and the agent is constructed for future study.

Medical procedures such as venipuncture and cannulation are essential for nurses and require precise skills. Learning this skill, in turn, is a challenge for educators due to the number of teachers per class and the complexity of the task. The study aims to help students with skill acquisition and alleviate the educator's workload by integrating generative AI methods to provide real-time feedback Figure 1: AI providing feedback on performed procedure on medical procedures such as venipuncture and cannulation.

Tokyo, Japan – Japanese scientists have developed a technique to attach self-healing, living skin to a robot face and make it "smile". The scientists, led by professor Shoji Takeuchi at the University of Tokyo's Biohybrid Systems Laboratory, connected cultured skin tissue in the likeness of a human face to an actuator – an external mechanical device – using "anchors" that mimic skin ligaments. In a video released by the team, the scientists can be seen manipulating the skin into a smile without causing the tissue to bunch, tear or get stuck in place. Previous efforts to attach tissue made from human cells to a solid surface would result in the skin being damaged when in motion. While Takeuchi's fleshy pink blob bears greater resemblance to a children's animated character than a human face, researchers hope the breakthrough will pave the way to realistic humanoids in the future.

With the increasing prevalence and diversity of robots interacting in the real world, there is need for flexible, on-the-fly planning and cooperation. Large Language Models are starting to be explored in a multimodal setup for communication, coordination, and planning in robotics. Existing approaches generally use a single agent building a plan, or have multiple homogeneous agents coordinating for a simple task. We present a decentralised, dialogical approach in which a team of agents with different abilities plans solutions through peer-to-peer and human-robot discussion. We suggest that argument-style dialogues are an effective way to facilitate adaptive use of each agent's abilities within a cooperative team. Two robots discuss how to solve a cleaning problem set by a human, define roles, and agree on paths they each take. Each step can be interrupted by a human advisor and agents check their plans with the human. Agents then execute this plan in the real world, collecting rubbish from people in each room. Our implementation uses text at every step, maintaining transparency and effective human-multi-robot interaction.

Machine learning has played a pivotal role in advancing physics, with deep learning notably contributing to solving complex classification problems such as jet tagging in the field of jet physics. In this experiment, we aim to harness the full potential of neural networks while acknowledging that, at times, we may lose sight of the underlying physics governing these models. Nevertheless, we demonstrate that we can achieve remarkable results obscuring physics knowledge and relying completely on the model's outcome. We introduce JetLOV, a composite comprising two models: a straightforward multilayer perceptron (MLP) and the well-established LundNet. Our study reveals that we can attain comparable jet tagging performance without relying on the pre-computed LundNet variables. Instead, we allow the network to autonomously learn an entirely new set of variables, devoid of a priori knowledge of the underlying physics. These findings hold promise, particularly in addressing the issue of model dependence, which can be mitigated through generalization and training on diverse data sets.