Generating emotional bodily expressions for culturally competent robots has been gaining increased attention to enhance the engagement and empathy between robots and humans in a multi-culture society. In this paper, we propose an incremental learning model for selecting the user's representative or habitual emotional behaviors which place emphasis on individual users' cultural traits identified through long term interaction. Furthermore, a transformation model is proposed to convert the obtained emotional behaviors into a specific robot's motion space. To validate the proposed approach, the models were evaluated by two example scenarios of interaction. The experimental results confirmed that the proposed approach endows a social robot with the capability to learn emotional behaviors from individual users, and to generate its emotional bodily expressions. It was also verified that the imitated robot motions are rated emotionally acceptable by the demonstrator and recognizable by the subjects from the same cultural background with the demonstrator.

In this paper, we focus on large-scale environment monitoring by utilizing a fully decentralized team of mobile robots. The robots utilize the resource constrained-decentralized active sensing scheme to select the most informative (uncertain) locations to observe while conserving allocated resources (battery, travel distance, etc.). We utilize a distributed Gaussian process (GP) framework to split the computational load over our fleet of robots. Since each robot is individually generating a model of the environment, there may be conflicting predictions for test locations. Thus, in this paper, we propose an algorithm for aggregating individual prediction models into a single globally consistent model that can be used to infer the overall spatial dynamics of the environment. To make a prediction at a previously unobserved location, we propose a novel gating network for a mixture-of-experts model wherein the weight of an expert is determined by the responsibility of the expert over the unvisited location. The benefit of posing our problem as a centralized fusion with a distributed GP computation approach is that the robots never communicate with each other, individually optimize their own GP models based on their respective observations, and off-load all their learnt models on the base station only at the end of their respective mission times. We demonstrate the effectiveness of our approach using publicly available datasets.

We propose a homing constrained bi-objective optimization variant of budget-limited informative path planning for monitoring a spatio-temporal environment. The objective function consists of weighted combination of two components: model performance which must be maximized and travel distance which must be bounded by the maximum operational range. Besides this, we have additional constraints that guarantee that the robots will return to home (base station) upon completion of their respective missions. Optimizing over this objective function is essentially NP-hard owing to the conflicting constituents. Moreover, the appropriate choice of weights and additional homing guarantees further adds to complications. We employ Gaussian Process (GP) model [1] which is highly data driven i.e., the larger the amount of training data, the better the model performance. However, owing to limited resources, a robot can only collect a limited amount of training samples. Thus, with the introduction of our bi-objective cost function, it becomes possible to plan budget-limited (e.g., battery, flight time, travel distance etc.) informative tours using autonomous mobile robots to effectively select only the most informative (uncertain) locations from the environment. In this work, we develop an algorithm to autonomously choose the appropriate weights for the components based on available resources while ensuring homing and maintaining model quality. We perform simulations to verify the effectiveness of our proposed objective function on the publicly available Ozone Concentration dataset gathered from USA.

Cultural differences may influence interactions between humans with different social norms and cultural traits, incurring different emotional and behavioral responses. The same applies to human-robot interaction (HRI). We believe that controlling robot emotions based on the cultural context can help robots adapt to humans from culturally diverse backgrounds. Such culturally aligned robots are expected to be easily accepted by humans as part of daily life. In this paper, we aim at investigating the role of culture in representing robot emotions which are injected by humans during its early stage of development and subject to change through their own experience thereafter. Several public data sets of pictures labeled with affective ratings by Indian, American, and European subjects are presented to social humanoid Pepper robots. The result shows that robots can learn to behave socially in alignment with an individual's cultural background. Moreover, we have demonstrated that robots under the effect of different cultures can generate different behavioral responses to the same stimuli, which is considered one of the most important issues in socially assitive robotics.

Toward a global picture of the radiation exposure of an area, particularly for fast emergency response, a UAV based exploration method is proposed. Without a priori knowledge of the radiation field, it is difficult to select the region of interest (ROI) which includes all radiation sources. For the case of a single radiation source, a greedy algorithm may localize the source by finding the maximum radiation value. However, when multiple sources generate a hotspot in a cumulative manner, the hotspot position does not coincide with one of the source positions. Therefore, we propose an efficient exploration method to quickly localize the radiation sources using the following procedures: (1) ROI selection using topographic maps with specific radiation level selection methods and (2) source localization estimating the number of sources and their positions with incremental variational Bayes inference of Gaussian mixtures. Under three different conditions according to the number of sources and their positions, we have shown that the proposed model can reduce the ROI and significantly improve the estimation accuracy than existing methods.

We present a robot cognitive framework based on (a) a memory-like architecture; and (b) the notion of “context”. We posit that relying solely on machine learning techniques may not be the right approach for a long-term, continuous knowledge acquisition. Since we are interested in long-term human-robot interaction, we focus on a scenario where a robot “remembers” relevant events happening in the environment. By visually sensing its surroundings, the robot is expected to infer and remember snapshots of events, and recall specific past events based on inputs and contextual information from humans. Using a COTS vision frameworks for the experiment, we show that the robot is able to form “memories” and recall related events based on cues and the context given during the human-robot interaction process.

An unsupervised attention-path planning algorithm is proposed and applied to large unknown area classification with small field-of-view cameras. Attention-path planning is formulated as the sequential feature selection problem that greedily finds a sequence of attentions to obtain more informative observations, yielding faster training and higher accuracies. In order to find the near-optimal attention-path, adaptive submodular optimization is employed, where the objective function for the internal belief is adaptive submodular and adaptive monotone. First, the amount of information of attention areas is modeled as the dissimilarity variance among the environment data set. With this model, the information gain function is defined as a function of variance reduction that has been shown to be submodular and monotone in many cases. Furthermore, adapting to increasing numbers of observations, each information gain for attention areas is iteratively updated by discarding the non-informative prior knowledge, enabling to maximize the expected information gain. The effectiveness of the proposed algorithm is verified through experiments that can significantly enhance the environment classification accuracy, with reduced number of limited field of view observations.

Our paper newly presents unsupervised feature representation method for very low-resolution (VLR) images called informative census transform (ICT) based on statistical analysis of CT binary features and submodular optimization. A new cost function is designed to measure the informativeness of each binary feature: (1) an individual informativeness of features to represent unlabeled image dataset and (2) relative informativeness between binary features to represent different binary features. Therefore, we considered informativeness of binary feature according to two relationship (1) between feature space and image space, and (2) between different features within same feature space. Moreover, two constraints are designed by considering sub-modular characteristics to guarantee theoretical performance and fast optimization via simple greedy algorithm. Experimental results show that the proposed ICT features with two constraints outperforms the traditional CT features in terms of recognition performance and computational cost at VLR problem.

This paper proposes a new attention-path planning algorithm that allows robots with limited sensing coverage to identify an unknown entity efficiently. Our focus is placed on how to plan optimal sequences of views to access more useful information needed to understand the entity. The adaptive submodular optimization technique guaranteed to achieve near-optimal performance is used to maximize the expected information gain. We verified the validity of the proposed approach to the face recognition problem through preliminary experiments.

This paper presents an adaptive object classification based on incremental feature extraction / representation and a hierarchical feature classifier that offers plasticity to accommodate variant input dimension and reduces forgetting problem of previously learned information. The proposed feature representation method applies incremental prototype generation with a cortex-like mechanism to conventional feature representation method to enable an incremental reflection of various object characteristics in learning process. A classifier based on a hierarchical generative model recognizes various objects with variant feature dimensions during the learning process. Experimental results show that the adaptive object classification model successfully classifies an object class against background with enhanced stability and flexibility.

We propose an autonomous blind spot monitoring method using a morphology-based saliency map (SM) model and the method of combining scale invariant feature transform (SIFT) with mean-shift tracking algorithm. The proposed method decides a region of interest (ROI) which includes the blind spot from the successive image frames obtained by side-view cameras. Topology information of the salient areas obtained from the SM model is used to detect a candidate of dangerous situations in the ROI, and the SIFT algorithm is considered for verifying whether the localized candidate area contains an automobile. We developed a modified mean-shift algorithm to track the detected automobile in a blind spot area. The modified mean-shift algorithm uses the orientation probability histogram for tracking the automobile around the localized area. Experimental results show that the proposed algorithm successfully provides an alarm signal to the driver in a dangerous situations caused by approaching an automobile at side-view.