Konstantinos E. Papoutsakis

Hobbit, a care robot supporting independent living at home

One option to address the challenge of demographic transition is to build robots that enable aging in place. Falling has been identified as the most relevant factor to cause a move to a care facility. The Hobbit project combines research from robotics, gerontology, and human-robot interaction to develop a care robot which is capable of fall prevention and detection as well as emergency detection and handling. Moreover, to enable daily interaction with the robot, other functions are added, such as bringing objects, offering reminders, and entertainment. The interaction with the user is based on a multimodal user interface including automatic speech recognition, text-to-speech, gesture recognition, and a graphical touch-based user interface. We performed controlled laboratory user studies with a total of 49 participants (aged 70 plus) in three EU countries (Austria, Greece, and Sweden). The collected user responses on perceived usability, acceptance, and affordability of the robot demonstrate a positive reception of the robot from its target user group. This article describes the principles and system components for navigation and manipulation in domestic environments, the interaction paradigm and its implementation in a multimodal user interface, the core robot tasks, as well as the results from the user studies, which are also reflected in terms of lessons we learned and we believe are useful to fellow researchers. We present a care robot for aging in place by means of fall prevention/detection.Detailed description of sensor set-up, hardware, and the multimodal user interface.Detailed description of major software components and implemented robot tasks.Proof-of-concept user study (49 user) on usability, acceptance, and affordability.

Integrating tracking with fine object segmentation

We present a novel method for on-line, joint object tracking and segmentation in a monocular video captured by a possibly moving camera. Our goal is to integrate tracking and fine segmentation of a single, previously unseen, potentially non-rigid object of unconstrained appearance, given its segmentation in the first frame of an image sequence as the only prior information. To this end, we tightly couple an existing kernel-based object tracking method with Random Walker-based image segmentation. Bayesian inference mediates between tracking and segmentation, enabling effective data fusion of pixel-wise spatial and color visual cues. The fine segmentation of an object at a certain frame provides tracking with reliable initialization for the next frame, closing the loop between the two building blocks of the proposed framework. The effectiveness of the proposed methodology is evaluated experimentally by comparing it to a large collection of state of the art tracking and video-based object segmentation methods on the basis of a data set consisting of several challenging image sequences for which ground truth data is available.

Object tracking and segmentation in a closed loop

We introduce a new method for integrated tracking and segmentation of a single non-rigid object in an monocular video, captured by a possibly moving camera. A closed-loop interaction between EM-like color-histogram-based tracking and Random Walker-based image segmentation is proposed, which results in reduced tracking drifts and in fine object segmentation. More specifically, pixel-wise spatial and color image cues are fused using Bayesian inference to guide object segmentation. The spatial properties and the appearance of the segmented objects are exploited to initialize the tracking algorithm in the next step, closing the loop between tracking and segmentation. As confirmed by experimental results on a variety of image sequences, the proposed approach efficiently tracks and segments previously unseen objects of varying appearance and shape, under challenging environmental conditions.

Gesture Recognition Supporting the Interaction of Humans with Socially Assistive Robots

We propose a new approach for vision-based gesture recognition to support robust and efficient human robot interaction towards developing socially assistive robots. The considered gestural vocabulary consists of five, user specified hand gestures that convey messages of fundamental importance in the context of human-robot dialogue. Despite their small number, the recognition of these gestures exhibits considerable challenges. Aiming at natural, easy-to-memorize means of interaction, users have identified gestures consisting of both static and dynamic hand configurations that involve different scales of observation (from arms to fingers) and exhibit intrinsic ambiguities. Moreover, the gestures need to be recognized regardless of the multifaceted variability of the human subjects performing them. Recognition needs to be performed online, in continuous video streams containing other irrelevant/unmodeled motions. All the above need to be achieved by analyzing information acquired by a possibly moving RGBD camera, in cluttered environments with considerable light variations. We present a gesture recognition method that addresses the above challenges, as well as promising experimental results obtained from relevant user trials.

Developing visual competencies for socially assistive robots: the HOBBIT approach

In this paper, we present our approach towards developing visual competencies for socially assistive robots within the framework of the HOBBIT project. We show how we integrated several vision modules using a layered architectural scheme. Our goal is to endow the mobile robot with visual perception capabilities so that it can interact with the users. We present the key modules of independent motion detection, object detection, body localization, person tracking, head pose estimation and action recognition and we explain how they serve the goal of natural integration of robots in social environments.

Hobbit: Providing Fall Detection and Prevention for the Elderly in the Real World

We present the robot developed within the Hobbit project, a socially assistive service robot aiming at the challenge of enabling prolonged independent living of elderly people in their own homes. We present the second prototype (Hobbit PT2) in terms of hardware and functionality improvements following first user studies. Our main contribution lies within the description of all components developed within the Hobbit project, leading to autonomous operation of 371 days during field trials in Austria, Greece, and Sweden. In these field trials, we studied how 18 elderly users (aged 75 years and older) lived with the autonomously interacting service robot over multiple weeks. To the best of our knowledge, this is the first time a multifunctional, low-cost service robot equipped with a manipulator was studied and evaluated for several weeks under real-world conditions. We show that Hobbit’s adaptive approach towards the user increasingly eased the interaction between the users and Hobbit. We provide lessons learned regarding the need for adaptive behavior coordination, support during emergency situations, and clear communication of robotic actions and their consequences for fellow researchers who are developing an autonomous, low-cost service robot designed to interact with their users in domestic contexts. Our trials show the necessity to move out into actual user homes, as only there can we encounter issues such as misinterpretation of actions during unscripted human-robot interaction.

Temporal Action Co-Segmentation in 3D Motion Capture Data and Videos

Given two action sequences, we are interested in spotting/co-segmenting all pairs of sub-sequences that represent the same action. We propose a totally unsupervised solution to this problem. No a-priori model of the actions is assumed to be available. The number of common sub-sequences may be unknown. The sub-sequences can be located anywhere in the original sequences, may differ in duration and the corresponding actions may be performed by a different person, in different style. We treat this type of temporal action co-segmentation as a stochastic optimization problem that is solved by employing Particle Swarm Optimization (PSO). The objective function that is minimized by PSO capitalizes on Dynamic Time Warping (DTW) to compare two action sub-sequences. Due to the generic problem formulation and solution, the proposed method can be applied to motion capture (i.e., 3D skeletal) data or to conventional RGB videos acquired in the wild. We present extensive quantitative experiments on standard data sets as well as on data sets we introduced in this paper. The obtained results demonstrate that the proposed method achieves a remarkable increase in co-segmentation quality compared to all tested state of the art methods.

Evaluating Method Design Options for Action Classification based on Bags of Visual Words

The Bags of Visual Words (BoVWs) framework has been applied successfully to several computer vision tasks. In this work we are particularly interested on its application to the problem of action recognition/classification. The key design decisions for a method that follows the BoVWs framework are (a) the visual features to be employed, (b) the size of the codebook to be used for representing a certain action and (c) the classifier applied to the developed representation to solve the classification task. We perform several experiments to investigate a variety of options regarding all the aforementioned design parameters. We also propose a new feature type and we suggest a method that determines automatically the size of the codebook. The experimental results show that our proposals produce results that are competitive to the outcomes of state of the art methods.

A graph-based approach for detecting common actions in motion capture data and videos

Abstract We present a novel solution to the problem of detecting common actions in time series of motion capture data and videos. Given two action sequences, our method discovers all pairs of common subsequences, i.e. subsequences that represent the same or similar action. This is achieved in a completely unsupervised manner, i.e., without any prior knowledge of the type of actions, their number and their duration. These common subsequences (commonalities) may be located anywhere in the original sequences, may differ in duration and may be performed under different conditions e.g., by a different actor. The proposed method performs a very efficient graph-based search on the matrix of pairwise distances of frames of the two sequences. This search is supported by an objective function that captures the trade off between the similarity of the common subsequences and their lengths. The proposed method has been evaluated quantitatively on challenging datasets and in comparison to state of the art approaches. The obtained results demonstrate that the proposed method outperforms the state of the art methods both in the quality of the obtained solutions and in computational performance.

A Framework for Online Segmentation and Classification of Modeled Actions Performed in the Context of Unmodeled Ones

In this paper, we propose a discriminative framework for online simultaneous segmentation and classification of modeled visual actions that can be performed in the context of other unknown actions. To this end, we employ Hough transform to vote in a 3D space for the begin point, the end point, and the label of the segmented part of the input stream. A support vector machine is used to model each class and to suggest putative labeled segments on the timeline. To identify the most plausible segments among the putative ones, we apply a dynamic programming algorithm, which maximizes the likelihood for label assignment in linear time. The performance of our method is evaluated on synthetic as well as on real data (Weizmann, TUM Kitchen, UTKAD, and Berkeley Multimodal Human Action databases). Extensive quantitative results obtained on a number of standard data sets demonstrate that the proposed approach is of comparable accuracy with the state-of-the-art approaches for online stream segmentation and classification when all performed actions are known, and performs considerably better in the presence of unmodeled actions.