Datasets for object detection often do not account for enough variety of glasses, due to their transparent and reflective properties. Specifically, open-vocabulary object detectors, widely used in embodied robotic agents, fail to distinguish subclasses of glasses. This scientific gap poses an issue to robotic applications that suffer from accumulating errors between detection, planning, and action execution. The paper introduces a novel method for the acquisition of real-world data from RGB-D sensors that minimizes human effort. We propose an auto-labeling pipeline that generates labels for all the acquired frames based on the depth measurements. We provide a novel real-world glass object dataset that was collected on the Neuro-Inspired COLlaborator (NICOL), a humanoid robot platform. The data set consists of 7850 images recorded from five different cameras. We show that our trained baseline model outperforms state-of-the-art open-vocabulary approaches. In addition, we deploy our baseline model in an embodied agent approach to the NICOL platform, on which it achieves a success rate of 81% in a human-robot bartending scenario.

We investigate the use of Large Language Models (LLMs) to equip neural robotic agents with human-like social and cognitive competencies, for the purpose of open-ended human-robot conversation and collaboration. We introduce a modular and extensible methodology for grounding an LLM with the sensory perceptions and capabilities of a physical robot, and integrate multiple deep learning models throughout the architecture in a form of system integration. The integrated models encompass various functions such as speech recognition, speech generation, open-vocabulary object detection, human pose estimation, and gesture detection, with the LLM serving as the central text-based coordinating unit. The qualitative and quantitative results demonstrate the huge potential of LLMs in providing emergent cognition and interactive language-oriented control of robots in a natural and social manner.

Robotic platforms that can efficiently collaborate with humans in physical tasks constitute a major goal in robotics. However, many existing robotic platforms are either designed for social interaction or industrial object manipulation tasks. The design of collaborative robots seldom emphasizes both their social interaction and physical collaboration abilities. To bridge this gap, we present the novel semi-humanoid NICOL, the Neuro-Inspired COLlaborator. NICOL is a large, newly designed, scaled-up version of its well-evaluated predecessor, the Neuro-Inspired COmpanion (NICO). NICOL adopts NICO's head and facial expression display and extends its manipulation abilities in terms of precision, object size, and workspace size. Our contribution in this paper is twofold -- firstly, we introduce the design concept for NICOL, and secondly, we provide an evaluation of NICOL's manipulation abilities by presenting a novel extension for an end-to-end hybrid neuro-genetic visuomotor learning approach adapted to NICOL's more complex kinematics. We show that the approach outperforms the state-of-the-art Inverse Kinematics (IK) solvers KDL, TRACK-IK and BIO-IK. Overall, this article presents for the first time the humanoid robot NICOL, and contributes to the integration of social robotics and neural visuomotor learning for humanoid robots.

SYDNEY: Though artificial intelligence is evolving quickly, consumers remain wary of the technology and prefer chatbots to stay simple with guided options, according to an Australian expert. Douglas Nicol, founder of On Message – Australia's first messaging agency – explained that the public at large is yet to catch up with the enthusiasm of marketers for futuristic chat solutions. In fact, consumers expect simpler chatbot formats which directly address their issues, rather than showcase the latest and greatest AI technology. "There is an innate fear amongst Australian consumers of machines and what machines can do to us in the future," Nicol told the Mumbrella MSIX conference in Sydney. "So the question is how do you navigate this world, because the world of artificial intelligence is changing everything."

"We move from being kings of process to kings of decisions," Douglas Nicol founder of chatbot service On Message said about the artificial intelligence opportunities for marketers at an IAA and Mumbrella panel discussion this morning. "My criticism of the world of marketing is we have become too obsessed by process so consequently we've lost sight of our jobs as marketers. I think AI is always best in terms of the problems it solves and I think the exciting think in the marketing world is it takes away a lot of the process and allows us to focus on our jobs." Nicol was speaking at the'Artificial intelligence just got real' panel held by the International Advertising Association (IAA) and Mumbrella on how AI promises to change marketing along with almost every other industry. Kirsten Riolo, the director of social exchange at researcher Ipsos, agreed with Nicol on AI's impact on business: "A lot of the grunt work is being assisted by these machine learning tools. It enables us to take on the issues and really tease them out. "For us it means we are able to put our researcher hats on and think more around what are the problems we are working on with our clients," she continued. "We can use machine learning to get through the datasets, to get to the issue and work more around strategic issues at play than spending inordinate amounts of time on data" Asia Pacific technical executive for IBM Watson, Dev Mookerjee, said the changes occurring in marketing have already been seen in consumer behaviour, citing how Uber and AirBnB have been embraced despite initial privacy and safety concerns. "I have just come to a new city, with no idea about the city," Mookerjee said. "I have got into the car of a person I've never before met, I trust this person who takes me to someone else's house – who I've never met before and I'm going to live in that person's house.