Imitation of Human Motion by Low Degree-of-Freedom Simulated Robots and Human Preference for Mappings Driven by Spinal, Arm, and Leg Activity

The Social Robot in Rehabilitation and Assistance: What Is the Future?

This commentary aims to address the field of social robots both in terms of the global situation and research perspectives. It has four polarities. First, it revisits the evolutions in robotics, which, starting from collaborative robotics, has led to the diffusion of social robots. Second, it illustrates the main fields in the employment of social robots in rehabilitation and assistance in the elderly and handicapped and in further emerging sectors. Third, it takes a look at the future directions of the research development both in terms of clinical and technological aspects. Fourth, it discusses the opportunities and limits, starting from the development and clinical use of social robots during the COVID-19 pandemic to the increase of ethical discussion on their use.

A Task-Learning Strategy for Robotic Assembly Tasks from Human Demonstrations

In manufacturing, traditional task pre-programming methods limit the efficiency of human-robot skill transfer. This paper proposes a novel task-learning strategy, enabling robots to learn skills from human demonstrations flexibly and generalize skills under new task situations. Specifically, we establish a markerless vision capture system to acquire continuous human hand movements and develop a threshold-based heuristic segmentation algorithm to segment the complete movements into different movement primitives (MPs) which encode human hand movements with task-oriented models. For movement primitive learning, we adopt a Gaussian mixture model and Gaussian mixture regression (GMM-GMR) to extract the optimal trajectory encapsulating sufficient human features and utilize dynamical movement primitives (DMPs) to learn for trajectory generalization. In addition, we propose an improved visuo-spatial skill learning (VSL) algorithm to learn goal configurations concerning spatial relationships between task-relevant objects. Only one multioperation demonstration is required for learning, and robots can generalize goal configurations under new task situations following the task execution order from demonstration. A series of peg-in-hole experiments demonstrate that the proposed task-learning strategy can obtain exact pick-and-place points and generate smooth human-like trajectories, verifying the effectiveness of the proposed strategy.

A review of recent research in social robotics

Research in social robotics has a different emphasis from research in robotics for factory, military, hospital, home (vacuuming), aerial (drone), space, and undersea applications. A social robot is one whose purpose is to serve a person in a caring interaction rather than to perform a mechanical task. Both because of its newness and because of its narrower psychological rather than technological emphasis, research in social robotics tends currently to be concentrated in a single journal and single annual conference. This review categorizes such a research into three areas: (1) Affect, Personality and Adaptation; (2) Sensing and Control for Action; and (3 Assistance to the Elderly and Handicapped. Current application is primarily for children's toys and devices to comfort the elderly and handicapped, as detailed in Section 'Toys and the market for social robots in general'.