In this article, a unified motion modeling approach for the 3-D snake robot is proposed, which enables motion prediction of all kinds of gaits generated by the backbone curve method on the ground. More specifically, the motion of the snake robot is novelly decomposed into two components, namely, the curve component and the shift component, which are explicitly related to the backbone curve's parameters and control's input. Considering the actual behavior of snake robots, a nonslip assumption is made to facilitate the modeling approach. Based on that, the ground-contacting points of the robot's links during shift control are conveniently analyzed, which helps to determine the moving direction of the curve components. Finally, with ground contacting points and backbone curve parameters determined, the characteristics of the two components, as well as the motion model, are successfully obtained. Utilizing this modeling approach, the widely used gaits, such as sidewinding, crawler, and S-pedal, are successfully modeled and then carefully analyzed to predict the movement of the snake robot with arbitrary given control input. Three groups of experiments are conducted, with the collected results showing the satisfactory accuracy of the obtained models. Compared with existing methods, the proposed modeling approach achieves a much more precise prediction, both in the direction and magnitude of snake robot motions.

Mobile robot path planning refers to the design of the safely collision-free path with shortest distance and least time-consuming from the starting point to the end point by a mobile robot autonomously. In this paper, a systematic review of mobile robot path planning techniques is presented. Firstly, path planning is classified into global path planning and local path planning according to the mastery of environmental information. In the global path planning, environment modeling methods and path evaluation method are introduced. The methods of environment modeling include grid method, topology method, geometric feature method and mixed representation method. In the local path planning, we introduce the sensors commonly used in the detection environment, including laser radar and visual sensor. Next, according to the characteristics of algorithms, mobile robot path planning algorithms are divided into three categories: classical algorithms, bionic algorithms and artificial intelligence algorithms. Among the classical algorithms, we introduce the cell decomposition method, sampling based method, graph search algorithm, artificial potential field method and dynamic window method. In the algorithm based on bionics, we introduce genetic algorithm, ant colony algorithm, gray wolf algorithm, etc. in detail. In artificial intelligence algorithm, we introduce neural network algorithm and fuzzy logic. Finally, we compare the key technologies of mobile robot path planning in the form of graphs and charts based on the classification statistics of the collected literature to provide references for future research.

Due to the head swinging and the body winding, the self-localization and path following for snake-like robots based on vision are very challenging. In this paper, a novel pantilt compensation method and curve parameter compensation path following controller are proposed to solve these problems, which can achieve high-precision path following. More specifically, to realize real-time positioning of the snakelike robot, a camera-mounted pan-tilt is equipped on the head of the snake-like robot, and the Apritag detection is used after the angle between the Apriltag plane and the camera plane being compensated. Then, due to the modeling approximation, the snake-like robot with a simplified controller usually deviates from the desired path, so a curve parameter compensation path following controller is proposed to eliminate the deviation and improve the following accuracy. Finally, the experiments show that with proposed methods, the snake-like robot can converge to the desired path stably and accurately.

Categorizing a patient's intentions during clinical interactions in general and within motivational interviewing specifically may improve decision making in clinical treatments.Within this paper, we propose a method that models the temporal flow of a conversation and the transition between topics by using domain adaptation on a clinical dialogue corpus comprising Motivational Interviewing (MI) sessions.We deploy Bi-LSTM and topic models jointly to learn theme shifts across different time stages within these hour-long MI sessions to assess the patient's intent to change their habits or to sustain them respectively.Our experiments show promising results and improvements after considering temporality in the classification task over our baseline.This result confirms and extends related literature that has manually identified that certain phases within MI sessions are more predictive of patient outcomes than others.

Representation learning methods, such as deep autoencoders, have received sustained attention due to their ability to effectively learn meaningful representations for a variety of applications. While these learning approaches are able to derive representations from any source signal (e.g., images, language, or voice signals) and encourage the separation in dominating factor domains, they broadly treat factors of variation pertaining to nuisances (e.g., recording conditions, gender of speaker, accent etc.) no different from often subtle more interesting factors, such as paralinguistic target variables (e.g., voice quality and phonetic vowels). In paralinguistic speech analyses, nuisance variables (e.g. gender and accent of speakers) often dominate acoustic subtleties that pertain for example to the affect or well-being of the speaker. In this work, we seek to capture nuisance-free embeddings by learning two separate orthogonal representations: one representation specialized to capture nuisance factors and one that improves the representation of the target. We propose unsupervised and (semi-) supervised orthogonal autoencoders that allow us to learn informative representations of paralinguistic and phonetic targets while removing the effect of the nuisance - gender. Overall, our proposed model outperforms state-of-the-art approaches and shows improved target representations.

Motivational Interviewing (MI) is a widely disseminated and effective therapeutic approach for behavioral disorder treatment. Over the past decade, MI research has identified client language as a central mediator between therapist skills and subsequent behavior change. Specifically, in-session client language referred to as change talk (CT; personal arguments for change) or sustain talk (ST; personal argument against changing the status quo) has been directly related to post-session behavior change. Despite the prevalent use of MI and extensive studies of MI underlying mechanisms, most existing studies focus on the linguistic aspect of MI, especially of client change talk and sustain talk and how they as a mediator influence the outcome of MI. In this study, we perform statistical analyses on acoustic behavior descriptors to test their discriminatory powers. Then we utilize multimodality by combining acoustic features with linguistic features to improve the accuracy of client change talk prediction. Lastly, we investigate into our trained model to understand what features inform the model about client utterance class and gain insights into the nature of MISC codes.