Mirokaï is designed to be helpful, engaging and enchanting. Have you ever wished robots could do more than just follow instructions? Born from the creative minds at Paris-based startup Enchanted Tools, Mirokaï isn't just another humanoid robot. It's designed to be helpful, engaging and, honestly, a bit enchanting. With its blend of advanced artificial intelligence, storytelling and a dash of charm, Mirokaï turns ordinary moments into something a little more memorable.

Shoplifting poses a significant challenge for retailers, resulting in billions of dollars in annual losses. Traditional security measures often fall short, highlighting the need for intelligent solutions capable of detecting shoplifting behaviors in real time. This paper frames shoplifting detection as an anomaly detection problem, focusing on the identification of deviations from typical shopping patterns. We introduce PoseLift, a privacy-preserving dataset specifically designed for shoplifting detection, addressing challenges such as data scarcity, privacy concerns, and model biases. PoseLift is built in collaboration with a retail store and contains anonymized human pose data from real-world scenarios. By preserving essential behavioral information while anonymizing identities, PoseLift balances privacy and utility. We benchmark state-of-the-art pose-based anomaly detection models on this dataset, evaluating performance using a comprehensive set of metrics. Our results demonstrate that pose-based approaches achieve high detection accuracy while effectively addressing privacy and bias concerns inherent in traditional methods. As one of the first datasets capturing real-world shoplifting behaviors, PoseLift offers researchers a valuable tool to advance computer vision ethically and will be publicly available to foster innovation and collaboration. The dataset is available at https://github.com/TeCSAR-UNCC/PoseLift.

In this paper, we present the service robot MARLIN and its integration with the K4R platform, a cloud system for complex AI applications in retail. At its core, this platform contains so-called semantic digital twins, a semantically annotated representation of the retail store. MARLIN continuously exchanges data with the K4R platform, improving the robot's capabilities in perception, autonomous navigation, and task planning. We exploit these capabilities in a retail intralogistics scenario, specifically by assisting store employees in stocking shelves. We demonstrate that MARLIN is able to update the digital representation of the retail store by detecting and classifying obstacles, autonomously planning and executing replenishment missions, adapting to unforeseen changes in the environment, and interacting with store employees. Experiments are conducted in simulation, in a laboratory environment, and in a real store. We also describe and evaluate a novel algorithm for autonomous navigation of articulated tractor-trailer systems. The algorithm outperforms the manufacturer's proprietary navigation approach and improves MARLIN's navigation capabilities in confined spaces.

Industries frequently adjust their facilities network by opening new branches in promising areas and closing branches in areas where they expect low profits. In this paper, we examine a particular class of facility location problems. Our objective is to minimize the loss of sales resulting from the removal of several retail stores. However, estimating sales accurately is expensive and time-consuming. To overcome this challenge, we leverage Monte Carlo Tree Search (MCTS) assisted by a surrogate model that computes evaluations faster. Results suggest that MCTS supported by a fast surrogate function can generate solutions faster while maintaining a consistent solution compared to MCTS that does not benefit from the surrogate function.

Tracking of inventory and rearrangement of misplaced items are some of the most labor-intensive tasks in a retail environment. While there have been attempts at using vision-based techniques for these tasks, they mostly use planogram compliance for detection of any anomalies, a technique that has been found lacking in robustness and scalability. Moreover, existing systems rely on human intervention to perform corrective actions after detection. In this paper, we present Co-AD, a Concept-based Anomaly Detection approach using a Vision Transformer (ViT) that is able to flag misplaced objects without using a prior knowledge base such as a planogram. It uses an auto-encoder architecture followed by outlier detection in the latent space. Co-AD has a peak success rate of 89.90% on anomaly detection image sets of retail objects drawn from the RP2K dataset, compared to 80.81% on the best-performing baseline of a standard ViT auto-encoder. To demonstrate its utility, we describe a robotic mobile manipulation pipeline to autonomously correct the anomalies flagged by Co-AD. This work is ultimately aimed towards developing autonomous mobile robot solutions that reduce the need for human intervention in retail store management.

This robot will be a household must-have that will be doing chores for millions of Americans by the end of the decade, an expert claims. Geordie Rose, founder of Vancouver-based Sanctuary AI, has created a human-sized bot called Phoenix who has already worked in two retail stores, bagging merchandise and cleaning, he told DailyMail.com. And he believes that within 10 years Phoenix or his predecessor will be capable of doing any jobs or chores a human can. The Phoenix android is already capable of doing chores such as cleaning and tidying and even filling the fridge - and is able to'learn' new skills just like a human. The robot's flexible hands enable it to perform human tasks - and it has a sense of'touch' Rose said: 'General-purpose robots must be able to sense, understand, and act on the world the same way we do.

An autonomous retail store management system entails inventory tracking, store monitoring, and anomaly correction. Recent attempts at autonomous retail store management have faced challenges primarily in perception for anomaly detection, as well as new challenges arising in mobile manipulation for executing anomaly correction. Advances in each of these areas along with system integration are necessary for a scalable solution in this domain.

Is AI the face of the new Brick-and-Mortar market? Artificial Intelligence's business applications are undergoing unprecedented growth as a new evolving reality. Therefore, giving AI its due credit stands to reason on a two-fold basis. Firstly – AI helps your retail business improve the bottom line and increase productivity. Secondly, customers are actively looking for a value-added experience from physical stores apart from a high-quality product.

You can get the most significant demographic statistics about your clients and fix the ideal product placements with facial recognition technologies. When the device detects a customer, the merchant can examine their activity in the store by tracking their movements. Businesses can use facial recognition can be used to provide tailored, contextual experiences across digital and physical channels for customers. According to Verified Market Research, Facial Recognition Market is projected to reach USD 10.2 Billion by 2028. Facial recognition is slowly making its way into our lives.

The covid-19 implications coupled with customer expectations have raised the need to go digital. As a result, retail stores have become experience centers than just store outlets in the digital transformation era. To provide an engaging customer experience and boost the marketing strategy, facial recognition has brought a whole new level of advancement in AI technologies. The Allied Market Research Report states that the "facial recognition market will reach $16.74 billion by 2030." And don't you find it fascinating if shoppers pay the bill at check-out by just representing a face, not any card or wallet?