Abstract
Aspired to build intelligent agents that can assist humans in daily life, researchers and engineers, both from academia and industry, have kept advancing the state-of-the-art in domestic robotics. With the rapid advancement of both hardware (e.g., high performance computing, smaller and cheaper sensors) and software (e.g., deep learning techniques and computational intelligence technologies), robotic products have become available to ordinary household users. For instance, domestic robots have assisted humans in various daily life scenarios to provide: (1) physical assistance such as floor vacuuming; (2) social assistance such as chatting; and (3) education and cognitive assistance such as offering partnerships. Crucial to the success of domestic robots is their ability to understand and carry out designated tasks from human users via natural and intuitive human-like interactions, because ordinary users usually have no expertise in robotics. To investigate whether and to what extent existing domestic robots can participate in intuitive and natural interactions, we survey existing domestic robots in terms of their interaction ability, and discuss the state-of-the-art research on multi-modal human–machine interaction from various domains, including natural language processing and multi-modal dialogue systems. We relate domestic robot application scenarios with state-of-the-art computational techniques of human–machine interaction, and discuss promising future directions towards building more reliable, capable and human-like domestic robots.
Highlights
With the rapid advancement in machine learning and computational intelligence models, faster Internet connection and increasingly affordable hardware, robotic products have become affordable household goods
“perception” and “action” functions are imperfect, we discover that the “understanding” and “interacting” functions are even more behind our expectation in most of the domestic robotic applications
In terms of the applications of the detection methods, the state-of-the-art object detection methods have achieved satisfactory performances in their accuracy, computational cost and processing speed. Both the one-stage and the two-stage methods have been widely integrated in the perception part of the domestic robotic systems (e.g., [27,28]), such as autonomous navigation [29], pedestrian detection [30], manipulation [31] and other robotic applications [32]
Summary
With the rapid advancement in machine learning and computational intelligence models, faster Internet connection and increasingly affordable hardware, robotic products have become affordable household goods. Commercial domestic robots are usually not equipped with the most advanced computational intelligence models. The techniques are often evaluated with pre-defined tasks or datasets which are the abstraction but cannot cover all the scenarios from real life Applying such models to robotic products risks user experiences and safety, as the models might encounter unexpected interactions with users which will lead to unexpected and unstable system performance. Even when some computational intelligence models shows impressive performances on some challenges in domestic robotics, robotic products on the market are still limited to the old-fashioned techniques due to various reasons from different perspectives. To identify the potential technologies in computational intelligence to be used in the domestic robots and its gap to the state-of-the-art CI models;.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
