Automated Speech Recognition shows superhuman performance for adult English speech on a range of benchmarks, but disappoints when fed children's speech. This has long sat in the way of child-robot interaction. Recent evolutions in data-driven speech recognition, including the availability of Transformer architectures and unprecedented volumes of training data, might mean a breakthrough for child speech recognition and social robot applications aimed at children. We revisit a study on child speech recognition from 2017 and show that indeed performance has increased, with newcomer OpenAI Whisper doing markedly better than leading commercial cloud services. While transcription is not perfect yet, the best model recognises 60.3% of sentences correctly barring small grammatical differences, with sub-second transcription time running on a local GPU, showing potential for usable autonomous child-robot speech interactions.

As KGs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modelling techniques. The original work proposed the Weisfeiler-Lehman (WL) kernel to improve the quality of the representations. However, in this work, we show both formally and empirically that the WL kernel does little to improve walk embeddings in the context of a single KG. As an alternative to the WL kernel, we propose five different strategies to extract information complementary to basic random walks. We compare these walks on several benchmark datasets to show that the \emph{n-gram} strategy performs best on average on node classification tasks and that tuning the walk strategy can result in improved predictive performances.

The latest issue of the IEEE Robotics & Automation Magazine features a special report on open-source robotics hardware and its impact in the field. We've seen how, over the last several years, open source software--platforms like the Robot Operating System (ROS), Gazebo, and OpenCV, among others--has played a huge role in helping researchers and companies build robots better and faster. Can the same thing happen with robot hardware? It's already happening, says robotics researcher and RAM editor-in-chief Bram Vanderborght, who explains that building hardware has gotten much easier thanks to things like 3D printers, laser cutters, modular open electronics kits, and other rapid prototyping and fabrication techniques. And while "open-source robotics hardware is taking longer to catch on" compared to open-source robotics software, he notes that "several impressive examples exist, taking advantage of benefits of those novel rapid prototyping possibilities."

It is one of the most terrifying robots ever made. Students have developed a 3D-printed scorpion to demonstrate the'intuitive and complex mechatronic functions' of the technology - and it can even stab people with its tail The Scorpion Hexapod is designed with six-legs that moves in all directions, responds to interactions and has a tail that leaves a'mark' when it attacks. Students have developed a 3D-printed scorpion to demonstrate the'intuitive and complex mechatronic functions' of the technology. The Scorpion Hexapod is designed with six-legs that moves in all directions, responds to interactions and has a tail that leaves a'mark' if it attacks The system was designed with different moves and a few auto responses to interaction, although it can be controlled through a computer. The system was designed with different moves and a few auto responses to interaction, although it can be controlled through a computer. It can walk in all directions, step over elevated surfaces and perform movements a real scorpion would such as, move its claws and strike its tail.