FABRIC: A Framework for the Design and Evaluation of Collaborative Robots with Extended Human Adaptation

A limitation for collaborative robots (cobots) is their lack of ability to adapt to human partners, who typically exhibit an immense diversity of behaviors. We present an autonomous framework as a cobot’s real-time decision-making mechanism to anticipate a variety of human characteristics and behaviors, including human errors, toward a personalized collaboration. Our framework handles such behaviors in two levels: 1) short-term human behaviors are adapted through our novel Anticipatory Partially Observable Markov Decision Process (A-POMDP) models, covering a human’s changing intent (motivation), availability, and capability; 2) long-term changing human characteristics are adapted by our novel Adaptive Bayesian Policy Selection (ABPS) mechanism that selects a short-term decision model, e.g., an A-POMDP, according to an estimate of a human’s workplace characteristics, such as her expertise and collaboration preferences. To design and evaluate our framework over a diversity of human behaviors, we propose a pipeline where we first train and rigorously test the framework in simulation over novel human models. Then, we deploy and evaluate it on our novel physical experiment setup that induces cognitive load on humans to observe their dynamic behaviors, including their mistakes, and their changing characteristics such as their expertise. We conduct user studies and show that our framework effectively collaborates non-stop for hours and adapts to various changing human behaviors and characteristics in real-time. That increases the efficiency and naturalness of the collaboration with a higher perceived collaboration, positive teammate traits, and human trust. We believe that such an extended human-adaptation is a key to the long-term use of cobots.

A dichotomic approach to adaptive interaction for socially assistive robots

Socially assistive robotics (SAR) aims at designing robots capable of guaranteeing social interaction to human users in a variety of assistance scenarios that range, e.g., from giving reminders for medications to monitoring of Activity of Daily Living, from giving advices to promote an healthy lifestyle to psychological monitoring. Among possible users, frail older adults deserve a special focus as they present a rich variability in terms of both alternative possible assistive scenarios (e.g., hospital or domestic environments) and caring needs that could change over time according to their health conditions. In this perspective, robot behaviors should be customized according to properly designed user models. One of the long-term research goals for SAR is the realization of robots capable of, on the one hand, personalizing assistance according to different health-related conditions/states of users and, on the other, adapting behaviors according to heterogeneous contexts as well as changing/evolving needs of users. This work proposes a solution based on a user model grounded on the international classification of functioning, disability and health (ICF) and a novel control architecture inspired by the dual-process theory. The proposed approach is general and can be deployed in many different scenarios. In this paper, we focus on a social robot in charge of the synthesis of personalized training sessions for the cognitive stimulation of older adults, customizing the adaptive verbal behavior according to the characteristics of the users and to their dynamic reactions when interacting. Evaluations with a restricted number of users show good usability of the system, a general positive attitude of users and the ability of the system to capture users personality so as to adapt the content accordingly during the verbal interaction.

Brain computer interface to distinguish between self and other related errors in human agent collaboration

When a human and machine collaborate on a shared task, ambiguous events might occur that could be perceived as an error by the human partner. In such events, spontaneous error-related potentials (ErrPs) are evoked in the human brain. Knowing whom the human perceived as responsible for the error would help a machine in co-adaptation and shared control paradigms to better adapt to human preferences. Therefore, we ask whether self- and agent-related errors evoke different ErrPs. Eleven subjects participated in an electroencephalography human-agent collaboration experiment with a collaborative trajectory-following task on two collaboration levels, where movement errors occurred as trajectory deviations. Independently of the collaboration level, we observed a higher amplitude of the responses on the midline central Cz electrode for self-related errors compared to observed errors made by the agent. On average, Support Vector Machines classified self- and agent-related errors with 72.64% accuracy using subject-specific features. These results demonstrate that ErrPs can tell if a person relates an error to themselves or an external autonomous agent during collaboration. Thus, the collaborative machine will receive more informed feedback for the error attribution that allows appropriate error identification, a possibility for correction, and avoidance in future actions.

Application of 5G network combined with AI robots in personalized nursing in China: A literature review

The medical and healthcare industry is currently developing into digitization. Attributed to the rapid development of advanced technologies such as the 5G network, cloud computing, artificial intelligence (AI), and big data, and their wide applications in the medical industry, the medical model is shifting into an intelligent one. By combining the 5G network with cloud healthcare platforms and AI, nursing robots can effectively improve the overall medical efficacy. Meanwhile, patients can enjoy personalized medical services, the supply and the sharing of medical and healthcare services are promoted, and the digital transformation of the healthcare industry is accelerated. In this paper, the application and practice of 5G network technology in the medical industry are introduced, including telecare, 5G first-aid remote medical service, and remote robot applications. Also, by combining application characteristics of AI and development requirements of smart healthcare, the overall planning, intelligence, and personalization of the 5G network in the medical industry, as well as opportunities and challenges of its application in the field of nursing are discussed. This paper provides references to the development and application of 5G network technology in the field of medical service.

Evaluation of Goal Recognition Systems on Unreliable Data and Uninspectable Agents

Goal or intent recognition, where one agent recognizes the goals or intentions of another, can be a powerful tool for effective teamwork and improving interaction between agents. Such reasoning can be challenging to perform, however, because observations of an agent can be unreliable and, often, an agent does not have access to the reasoning processes and mental models of the other agent. Despite this difficulty, recent work has made great strides in addressing these challenges. In particular, two Artificial Intelligence (AI)-based approaches to goal recognition have recently been shown to perform well: goal recognition as planning, which reduces a goal recognition problem to the problem of plan generation; and Combinatory Categorical Grammars (CCGs), which treat goal recognition as a parsing problem. Additionally, new advances in cognitive science with respect to Theory of Mind reasoning have yielded an approach to goal recognition that leverages analogy in its decision making. However, there is still much unknown about the potential and limitations of these approaches, especially with respect to one another. Here, we present an extension of the analogical approach to a novel algorithm, Refinement via Analogy for Goal Reasoning (RAGeR). We compare RAGeR to two state-of-the-art approaches which use planning and CCGs for goal recognition, respectively, along two different axes: reliability of observations and inspectability of the other agent's mental model. Overall, we show that no approach dominates across all cases and discuss the relative strengths and weaknesses of these approaches. Scientists interested in goal recognition problems can use this knowledge as a guide to select the correct starting point for their specific domains and tasks.

Communication Models in Human–Robot Interaction: An Asymmetric MODel of ALterity in Human–Robot Interaction (AMODAL-HRI)

We argue for an interdisciplinary approach that connects existing models and theories in Human–Robot Interaction (HRI) to traditions in communication theory. In this article, we review existing models of interpersonal communication and interaction models that have been applied and developed in the contexts of HRI and social robotics. We argue that often, symmetric models are proposed in which the human and robot agents are depicted as having similar ways of functioning (similar capabilities, components, processes). However, we argue that models of human–robot interaction or communication should be asymmetric instead. We propose an asymmetric interaction model called AMODAL-HRI (an Asymmetric MODel of ALterity in Human–Robot Interaction). This model is based on theory on joint action, common robot architectures and cognitive architectures, and Kincaid’s model of communication. On the basis of this model, we discuss key differences between humans and robots that influence human expectations regarding interacting with robots, and identify design implications.

Neural-network-based Memory for a Social Robot

Many recent studies have shown that behaviors and interaction logic for social robots can be learned automatically from natural examples of human-human interaction by machine learning algorithms, with minimal input from human designers [1--4]. In this work, we exceed the capabilities of the previous approaches by giving the robot memory . In earlier work, the robot's actions were decided based only on a narrow temporal window of the current interaction context. However, human behaviors often depend on more temporally distant events in the interaction history. Thus, we raise the question of whether (and how) an automated behavior learning system can learn a memory representation of interaction history within a simulated camera shop scenario. An analysis of the types of memory-setting and memory-dependent actions that occur in the camera shop scenario is presented. Then, to create more examples of such actions for evaluating a shopkeeper robot behavior learning system, an interaction dataset is simulated. A Gated Recurrent Unit (GRU) neural network architecture is applied in the behavior learning system, which learns a memory representation for performing memory-dependent actions. In an offline evaluation, the GRU system significantly outperformed a without-memory baseline system at generating appropriate memory-dependent actions. Finally, an analysis of the GRU architecture's memory representation is presented.

Quantifying teaching behavior in robot learning from demonstration

Learning from demonstration allows for rapid deployment of robot manipulators to a great many tasks, by relying on a person showing the robot what to do rather than programming it. While this approach provides many opportunities, measuring, evaluating, and improving the person’s teaching ability has remained largely unexplored in robot manipulation research. To this end, a model for learning from demonstration is presented here that incorporates the teacher’s understanding of, and influence on, the learner. The proposed model is used to clarify the teacher’s objectives during learning from demonstration, providing new views on how teaching failures and efficiency can be defined. The benefit of this approach is shown in two experiments ([Formula: see text] and [Formula: see text], respectively), which highlight the difficulty teachers have in providing effective demonstrations, and show how [Formula: see text]–180% improvement in teaching efficiency can be achieved through evaluation and feedback shaped by the proposed framework, relative to unguided teaching.

First-in-human study of the safety and viability of intraocular robotic surgery

Microsurgery of the retina would be dramatically improved by instruments that offer supra-human precision. Here, we report the results of a first-in-human study of remotely controlled robot-assisted retinal surgery performed through a telemanipulation device. Specifically, 12 patients requiring dissection of the epiretinal or inner limiting membrane over the macula were randomly assigned to either undergo robot-assisted-surgery or manual surgery, under general anaesthesia. We evaluated surgical success, duration of surgery and amount of retinal microtrauma as a proxy for safety. Surgical outcomes were equally successful in the robotic-surgery and manual-surgery groups. Differences in the amount of retinal microtrauma between the two groups were statistically insignificant, yet dissection took longer with robotic surgery (median time, 4 min 5 s) than with manual surgery (1 min 20 s). We also show the feasibility of using the robot to inject recombinant tissue plasminogen activator under the retina to displace sight-threatening haemorrhage in three patients under local anaesthesia. A safe and viable robotic system for intraocular surgery would enable precise and minimally traumatic delivery of gene therapy or cell therapy to the retina.