Manuel Giuliani

Two people walk into a bar: dynamic multi-party social interaction with a robot agent

We introduce a humanoid robot bartender that is capable of dealing with multiple customers in a dynamic, multi-party social setting. The robot system incorporates state-of-the-art components for computer vision, linguistic processing, state management, high-level reasoning, and robot control. In a user evaluation, 31 participants interacted with the bartender in a range of social situations. Most customers successfully obtained a drink from the bartender in all scenarios, and the factors that had the greatest impact on subjective satisfaction were task success and dialogue efficiency.

Integrating language, vision and action for human robot dialog systems

Developing a robot system that can interact directly with a human instructor in a natural way requires not only highly-skilled sensorimotor coordination and action planning on the part of the robot, but also the ability to understand and communicate with a human being in many modalities. A typical application of such a system is interactive assembly for construction tasks. A human communicator sharing a common view of the work area with the robot system instructs the latter by speaking to it in the same way that he would communicate with a human partner.

Comparing task-based and socially intelligent behaviour in a robot bartender

We address the question of whether service robots that interact with humans in public spaces must express socially appropriate behaviour. To do so, we implemented a robot bartender which is able to take drink orders from humans and serve drinks to them. By using a high-level automated planner, we explore two different robot interaction styles: in the task only setting, the robot simply fulfils its goal of asking customers for drink orders and serving them drinks; in the socially intelligent setting, the robot additionally acts in a manner socially appropriate to the bartender scenario, based on the behaviour of humans observed in natural bar interactions. The results of a user study show that the interactions with the socially intelligent robot were somewhat more efficient, but the two implemented behaviour settings had only a small influence on the subjective ratings. However, there were objective factors that influenced participant ratings: the overall duration of the interaction had a positive influence on the ratings, while the number of system order requests had a negative influence. We also found a cultural difference: German participants gave the system higher pre-test ratings than participants who interacted in English, although the post-test scores were similar.

Designing and Evaluating a Social Gaze-Control System for a Humanoid Robot

This paper describes a context-dependent social gaze-control system implemented as part of a humanoid social robot. The system enables the robot to direct its gaze at multiple humans who are interacting with each other and with the robot. The attention mechanism of the gaze-control system is based on features that have been proven to guide human attention: nonverbal and verbal cues, proxemics, the visual field of view, and the habituation effect. Our gaze-control system uses Kinect skeleton tracking together with speech recognition and SHORE-based facial expression recognition to implement the same features. As part of a pilot evaluation, we collected the gaze behavior of 11 participants in an eye-tracking study. We showed participants videos of two-person interactions and tracked their gaze behavior. A comparison of the human gaze behavior with the behavior of our gaze-control system running on the same videos shows that it replicated human gaze behavior 89% of the time.

KVP: A knowledge of volumes approach to robot task planning

Robot task planning is an inherently challenging problem, as it covers both continuous-space geometric reasoning about robot motion and perception, as well as purely symbolic knowledge about actions and objects. This paper presents a novel “knowledge of volumes” framework for solving generic robot tasks in partially known environments. In particular, this approach (abbreviated, KVP) combines the power of symbolic, knowledge-level AI planning with the efficient computation of volumes, which serve as an intermediate representation for both robot action and perception. While we demonstrate the effectiveness of our framework in a bimanual robot bartender scenario, our approach is also more generally applicable to tasks in automation and mobile manipulation, involving arbitrary numbers of manipulators.

How can i help you': comparing engagement classification strategies for a robot bartender

A robot agent existing in the physical world must be able to understand the social states of the human users it interacts with in order to respond appropriately. We compared two implemented methods for estimating the engagement state of customers for a robot bartender based on low-level sensor data: a rule-based version derived from the analysis of human behaviour in real bars, and a trained version using supervised learning on a labelled multimodal corpus. We first compared the two implementations using cross-validation on real sensor data and found that nearly all classifier types significantly outperformed the rule-based classifier. We also carried out feature selection to see which sensor features were the most informative for the classification task, and found that the position of the head and hands were relevant, but that the torso orientation was not. Finally, we performed a user study comparing the ability of the two classifiers to detect the intended user engagement of actual customers of the robot bartender; this study found that the trained classifier was faster at detecting initial intended user engagement, but that the rule-based classifier was more stable.

Combining unsupervised learning and discrimination for 3D action recognition

Previous work on 3D action recognition has focused on using hand-designed features, either from depth videos or 2D videos. In this work, we present an effective way to combine unsupervised feature learning with discriminative feature mining. Unsupervised feature learning allows us to extract spatio-temporal features from unlabeled video data. With this, we can avoid the cumbersome process of designing feature extraction by hand. We propose an ensemble approach using a discriminative learning algorithm, where each base learner is a discriminative multi-kernel-learning classifier, trained to learn an optimal combination of joint-based features. Our evaluation includes a comparison to state-of-the-art methods on the MSRAction 3D dataset, where our method, abbreviated EnMkl, outperforms earlier methods. Furthermore, we analyze the efficiency of our approach in a 3D action recognition system. HighlightsWe deal with recognizing 3D human actions by combining two ideas: unsupervised feature learning and discriminative feature mining.We are the first work to use unsupervised learning to represent 3D depth video data.We propose an ensemble approach with a discriminative multi-kernel learning algorithm to model 3D human actions.

Action Recognition Using Ensemble Weighted Multi-Instance Learning

This paper deals with recognizing human actions in depth video data. Current state-of-the-art action recognition methods use hand-designed features, which are difficult to produce and time-consuming to extend to new modalities. In this paper, we propose a novel, 3.5D representation of a depth video for action recognition. A 3.5D graph of the depth video consists of a set of nodes that are the joints of the human body. Each joint is represented by a set of spatio-temporal features, which are computed by an unsupervised learning approach. However, if occlusions occur, the 3D positions of the joints are noisy which increases the intra-class variations in action classes. To address this problem, we propose the Ensemble Weighted Multi-Instance Learning approach (EnwMi) for the action recognition task. It considers the class imbalance and intra-class variations. We formulate the action recognition task with depth videos as a weighted multi-instance problem. We further integrate an ensemble learning method into the weighted multi-instance learning framework. Our approach is evaluated on Microsoft Research Action3D dataset, and the results show that it outperforms state-of-the-art methods.

Social behavior recognition using body posture and head pose for human-robot interaction

Robots that interact with humans in everyday situations, need to be able to interpret the nonverbal social cues of their human interaction partners. We show that humans use body posture and head pose as social signals to initiate and terminate interaction when ordering drinks at a bar. For that, we record and analyze 108 interactions of humans interacting with a human bartender. Based on these findings, we train a Hidden Markov Model (HMM) using automatic body posture and head pose estimation. With this model, the bartender robot of the project JAMES can recognize typical social behaviors of human customers. Evaluation shows a recognition rate of 82.9 % for all implemented social behaviors and in particular a recognition rate of 91.2 % for bartender attention requests, which will allow the robot to interact with multiple humans in a robust and socially appropriate way.

MultiML: a general purpose representation language for multimodal human utterances

We present MultiML, a markup language for the annotation of multimodal human utterances. MultiML is able to represent input from several modalities, as well as the relationships between these modalities. Since MultiML separates general parts of representation from more context-specific aspects, it can easily be adapted for use in a wide range of contexts. This paper demonstrates how speech and gestures are described with MultiML, showing the principles - including hierarchy and underspecification - that ensure the quality and extensibility of MultiML. As a proof of concept, we show how MultiML is used to annotate a sample human-robot interaction in the domain of a multimodal joint-action scenario.