In today's world, many patients with cognitive impairments and motor
dysfunction seek the attention of experts to perform specific conventional
therapies to improve their situation. However, due to a lack of
neurorehabilitation professionals, patients suffer from severe effects that
worsen their condition. In this paper, we present a technological approach for
a novel robotic neurorehabilitation training system. It relies on a combination
of a rehabilitation device, signal classification methods, supervised machine
learning models for training adaptation, training exercises, and socially
interactive agents as a user interface. Together with a professional, the
system can be trained towards the patient's specific needs. Furthermore, after
a training phase, patients are enabled to train independently at home without
the assistance of a physical therapist with a socially interactive agent in the
role of a coaching assistant.

本文介绍了一种新型机器人神经康复训练系统，结合了康复设备、信号分类方法、监督式机器学习模型以及社交互动代理人作为用户界面，能够根据患者特定需求进行训练并让患者进行独立康复训练。

采用社交互动智能体进行机器人神经康复训练

Employing Socially Interactive Agents for Robotic Neurorehabilitation Training

There has been an increasing interest in 3D indoor navigation, where a robot
in an environment moves to a target according to an instruction. To deploy a
robot for navigation in the physical world, lots of training data is required
to learn an effective policy. It is quite labour intensive to obtain sufficient
real environment data for training robots while synthetic data is much easier
to construct by rendering. Though it is promising to utilize the synthetic
environments to facilitate navigation training in the real world, real
environment are heterogeneous from synthetic environment in two aspects. First,
the visual representation of the two environments have significant variances.
Second, the houseplans of these two environments are quite different. Therefore
two types of information, i.e. visual representation and policy behavior, need
to be adapted in the reinforcement model. The learning procedure of visual
representation and that of policy behavior are presumably reciprocal. We
propose to jointly adapt visual representation and policy behavior to leverage
the mutual impacts of environment and policy. Specifically, our method employs
an adversarial feature adaptation model for visual representation transfer and
a policy mimic strategy for policy behavior imitation. Experiment shows that
our method outperforms the baseline by 19.47% without any additional human
annotations.

本文介绍了一种基于对抗特征调整模型的 3D 室内导航机器人训练方法，通过视觉特征的转换与行为策略的模仿来提高机器人在真实环境中的表现。实验证明该方法能够在不需要额外人工注释的情况下，比基线方法表现提高 19.47%。