Purpose: The rousing phenomenon of the ageing population is becoming a vital issue and demanding fulminant actions. Population ageing is a resultant of the enhanced health-care system, groovy antibiotics, medications and economic well-being. Old age leads to copious amounts of ailments. Aged people, owing to their reduced mobility and enervating disabilities, tend to rely upon caretakers and/or nursing personnel. With the increasing vogue of nuclear families in the society, the elderly are at the risk of being unveiled to emotional, physical and fiscal insecurities in the years to come. Caring for those seniors will be an enormous undertaking. Design/methodology/approach: There is a dire need for an intelligent assistive system to meet out the requirements of continuous holistic care and monitoring. Assistive robots and systems used for elderly care are studied. The design motivation for the robots, elderly–robot interaction capabilities and technology incorporated in the systems are examined meticulously. Findings: From the survey, it is suggested that the subsystems of an assistive robot revamped for better human–machine interactions will be a potential alternative to the human counterpart. Affirmable advancements in the robot design and interaction methodologies that would increase the holistic care and assistance for aged people are analyzed and listed. Originality/value: This paper reviews the available assistive technologies and suggests a synergistic model that can be adopted for the caring of the elderly.

Recent technological advancements have fostered human–robot coexistence in work and residential environments. The assistive robot must exhibit humane behavior and consistent care to become an integral part of the human habitat. Furthermore, the robot requires an adaptive unsupervised learning model to explore unfamiliar conditions and collaborate seamlessly. This paper introduces variants of the growing hierarchical self-organizing map (GHSOM)-based computational models for assistive robots, which constructs knowledge from unsupervised exploration-based learning. Traditional self-organizing map (SOM) algorithms have shortcomings, including finite neuron structure, user-defined parameters, and non-hierarchical adaptive architecture. The proposed models overcome these limitations and dynamically grow to form problem-dependent hierarchical feature clusters, thereby allowing associative learning and symbol grounding. Infants can learn from their surroundings through exploration and experience, developing new neuronal connections as they learn. They can also apply their prior knowledge to solve unfamiliar problems. With infant-like emergent behavior, the presented models can operate on different problems without modifications, producing new patterns not present in the input vectors and allowing interactive result visualization. The proposed models are applied to the color, handwritten digits clustering, finger identification, and image classification problems to evaluate their adaptiveness and infant-like knowledge building. The results show that the proposed models are the preferred generalized models for assistive robots.