Accurate vision-based action recognition is crucial for developing autonomous robots that can operate safely and reliably in complex, real-world environments. In this work, we advance video-based recognition of indoor daily actions for robotic perception by leveraging vision-language models (VLMs) enriched with domain-specific knowledge. We adapt a prompt-learning framework in which class-level textual descriptions of each action are embedded as learnable prompts into a frozen pre-trained VLM backbone. Several strategies for structuring and encoding these textual descriptions are designed and evaluated. Experiments on the ETRI-Activity3D dataset demonstrate that our method, using only RGB video inputs at test time, achieves over 95\% accuracy and outperforms state-of-the-art approaches. These results highlight the effectiveness of knowledge-augmented prompts in enabling robust action recognition with minimal supervision.

Food has always played a vital role in video games. From Pac-Man's bonus fruits to Mario's magical mushrooms, it has provided everything from sustenance to supernatural abilities – and in games such as Cooking Mama and Overcooked, food preparation became a genre in its own right. Game developers, like the creators of cooking programmes and recipe books, have discovered that well-presented food is irresistible – even when we can't eat it. In the modern games industry, where detail and authenticity are paramount, the depiction of food has become an art form. Kaname Fujioka, executive director on Capcom's fantasy adventure, Monster Hunter: World, says: "We design the ingredients and recipes based around the grade of the food, as well as any seasonal events it may be tied to. Since we're unable to showcase the most important elements of food (taste and smell), we have to alter, exaggerate or potentially deform the visuals in a way that conveys that as best as possible. In order for players to believe that the visuals look'delicious', a lot of fine-tuning is done on details like the colour, lighting and softness."

At a café called Ratio in Shanghai, a revolving, jointed robot arm with two fingerlike prongs knows just how you like your latte. That's because customers can order via a mini-app on social media platform WeChat, specifying the level of sweetness and choosing between coffee beans. Plus, because it syncs with your social media profile, the barista never spells your name wrong. Robots in restaurants sound like a futuristic novelty. But in China, kitchen-side automation has long been routine for some restaurants, fast food chains, and cafeterias. What's more, robotics are being used to standardize a centuries-old cuisine, potentially shaping the taste buds of future generations.

Last week, Sony and Carnegie Mellon University announced a collaboration "on artificial intelligence (AI) and robotics research." Usually, these announcements pretty much just end there, with the implication being that giant corporation X will support academic research institution Y by funding ongoing research or a string of new initiatives. This Sony/CMU announcement is a bit more exciting because of how specific it is: The project will be about food. Researchers will focus on defining the domain of food ordering, preparation, and delivery. Initially, they will build upon existing manipulation robots and mobile robots, and will plan on developing new domain-specific robots for predefined food preparation items and for mobility in a limited confined space.

The collapse of low-skilled labor in America continues unabated, thanks in large part to the advancement of robotics, and with it, a wave of coming unrest like nations have not seen in a long, long time. As reported by CNBC, the fast-food industry, in particular, is poised for dramatic changes, with the introduction of electronic kiosks and robotic food preparation that one expert has projected will obliterate human workers in the industry by the mid-2020s. Grilling burgers may be fun on the Fourth of July, but less so if hot grease is your daily grind. The southern California start-up has built a robotic "kitchen assistant" called Flippy to do the hot, greasy and repetitive work of a fry cook. Flippy employs machine learning and computer vision to identify patties on a grill, track them as they cook, flip and then place them on a bun when they're done.

Last year, McKinsey launched a multi-year study to explore the potential impact of automation technologies on jobs, organizations and the future of work. "Can we look forward to vast improvements in productivity, freedom from boring work, and improved quality of life?," its initial article on the study asked, or "Should we fear threats to jobs, disruptions to organizations, and strains on the social fabric?" Most jobs involve a number of different tasks or activities. Some of these activities are more amenable to automation than others. But just because some of the activities have been automated, does not imply that the whole job has disappeared. To the contrary, automating parts of a job will often increase the productivity and quality of workers by complementing their skills with machines and computers, as well as by enabling them to focus on those aspects of the job that most need their attention.