This paper presents a novel high-level task planning and optimal coordination framework for autonomous masonry construction, using a team of heterogeneous aerial robotic workers, consisting of agents with separate skills for brick placement and mortar application. This introduces new challenges in scheduling and coordination, particularly due to the mortar curing deadline required for structural bonding and ensuring the safety constraints among UAVs operating in parallel. To address this, an automated pipeline generates the wall construction plan based on the available bricks while identifying static structural dependencies and potential conflicts for safe operation. The proposed framework optimizes UAV task allocation and execution timing by incorporating dynamically coupled precedence deadline constraints that account for the curing process and static structural dependency constraints, while enforcing spatio-temporal constraints to prevent collisions and ensure safety. The primary objective of the scheduler is to minimize the overall construction makespan while minimizing logistics, traveling time between tasks, and the curing time to maintain both adhesion quality and safe workspace separation. The effectiveness of the proposed method in achieving coordinated and time-efficient aerial masonry construction is extensively validated through Gazebo simulated missions. The results demonstrate the framework's capability to streamline UAV operations, ensuring both structural integrity and safety during the construction process.

With the widespread application of LLM-based dialogue systems in daily life, quality assurance has become more important than ever. Recent research has successfully introduced methods to identify unexpected behaviour in single-turn scenarios. However, multi-turn dialogue testing remains underexplored, with the Oracle problem in multi-turn testing posing a persistent challenge for dialogue system developers and researchers. In this paper, we propose MORTAR, a MetamORphic multi-TuRn diAlogue testing appRoach, which mitigates the test oracle problem in the assessment of LLM-based dialogue systems. MORTAR automates the generation of follow-up question-answer (QA) dialogue test cases with multiple dialogue-level perturbations and metamorphic relations. MORTAR employs a novel knowledge graph-based dialogue information model which effectively generates perturbed dialogue test datasets and detects bugs of multi-turn dialogue systems in a low-cost manner. The proposed approach does not require an LLM as a judge, eliminating potential of any biases in the evaluation step. According to the experiment results on multiple LLM-based dialogue systems and comparisons with single-turn metamorphic testing approaches, MORTAR explores more unique bugs in LLM-based dialogue systems, especially for severe bugs that MORTAR detects up to four times more unique bugs than the most effective existing metamorphic testing approach.

Cyber-Physical Systems (CPSs) are increasingly prevalent across various industrial and daily-life domains, with applications ranging from robotic operations to autonomous driving. With recent advancements in artificial intelligence (AI), learning-based components, especially AI controllers, have become essential in enhancing the functionality and efficiency of CPSs. However, the lack of interpretability in these AI controllers presents challenges to the safety and quality assurance of AI-enabled CPSs (AI-CPSs). Existing methods for improving the safety of AI controllers often involve neural network repair, which requires retraining with additional adversarial examples or access to detailed internal information of the neural network. Hence, these approaches have limited applicability for black-box policies, where only the inputs and outputs are accessible during operation. To overcome this, we propose MORTAR, a runtime action repair framework designed for AI-CPSs in this work. MORTAR begins by constructing a prediction model that forecasts the quality of actions proposed by the AI controller. If an unsafe action is detected, MORTAR then initiates a repair process to correct it. The generation of repaired actions is achieved through an optimization process guided by the safety estimates from the prediction model. We evaluate the effectiveness of MORTAR across various CPS tasks and AI controllers. The results demonstrate that MORTAR can efficiently improve task completion rates of AI controllers under specified safety specifications. Meanwhile, it also maintains minimal computational overhead, ensuring real-time operation of the AI-CPSs.

In a first for UK construction, a three-bedroom house in Everingham, East Yorkshire is being built with help of a robot bricklayer rather human labourers. Built by York-based firm Construction Automation, the machine is capable of setting down all the bricks, blocks and mortar -- and can even'build around corners'. Construction on the house began on September 28 this year -- and is expected to be completed in around three weeks after'teething problems' caused a week's delay. Built by York-based firm Construction Automation, the machine (pictured) is capable of setting down all the bricks, blocks and mortar -- and can even'build around corners' 'It is the first house in the UK to be built by a robot,' Construction Automation director and founder David Longbottom told the BBC. He added that, after extensive research, the firm was certain that there was'no house-building robot in use like this.'

Robotics have a mixed history in construction. Some work, especially in prefabricated building offsite, while others have not been successful, particularly when used onsite. However, that may be changing as more equipment companies are exploring the use of robotic technology and applying it to construction. One of the technologies that has shown promise is in the use of robotic arms and gantry equipment for 3D printing of concrete walls. From one of the first, if not the first, completed buildings constructed in this method, an office building in Dubai, to the research work being done by Chinese and U.S. companies as well as others in the European Union, building onsite using what is referred to as additive manufacturing techniques is moving rapidly.

A searing hot laser capable of cutting through aircrafts in seconds has been demonstrated for the first time by the Ministry of Defence. The research will feed into the Dragonfire programme - a strategy intended to create a laser capable of becoming an alternative to missiles. The idea is to take down drones and cut through the hulls of aircraft and armoured vehicles in a more efficient manner. The technology is not yet ready to deploy, with another five to ten years of research ahead of it to perfect the system. The MoD said: 'It won't be a thing of sleek, space age beauty, looking more like a fridge on a truck than a thing of science fiction!

Cognitive agents operating in complex and dynamic domains benefit from significant goal management. Operations on goals include formulation, selection, change, monitoring and delegation in addition to goal achievement. Here we model these operations as transformations on goals. An agent may observe events that affect the agent’s ability to achieve its goals. Hence goal transformations allow unachievable goals to be converted into similar achievable goals. This paper examines an implementation of goal change within a cognitive architecture. We introduce goal transformation at the metacognitive level as well as goal transformation in an automated planner and discuss the costs and benefits of each approach. We evaluate goal change in the MIDCA architecture using a resource-restricted planning domain, demonstrating a performance benefit due to goal operations.

The Brand AI can analyse this liquid big data using its machine learning capabilities to create dynamic real-time personalised actionable insights seamlessly across a customer's physical and digital experience – it is the heartbeat of the retailer's invisible omni-channel offering. For example, the Brand AI can advise in-store sales staff in advance what specific products a customer wants or needs that particular day to help personalise this human interaction, provide on the spot guidance and critical feedback about products available immediately to drive a purchasing decision, or tailor in-store digital experiences such as virtual reality or media walls to create genuine moments of customer delight. In addition, the AI can capture the customer's emotional and physical reactions via wearables to these experiences (such as a raised heartbeat when seeing a new product for the first time); such insights can then be explored later by the customer (including socially with family and friends) using the AI on the retailer's integrated digital channel to sustain their retention. A further opportunity for using Brand AI is its potential ability to streamline inventory management to improve the customer experience and reduce operating risk.