Abstract
In open-ended domains, robots must continuously learn new object categories. When the training sets are created offline, it is not possible to ensure their representativeness with respect to the object categories and features the system will find when operating online. In the Bag of Words model, visual codebooks are usually constructed from training sets created offline. This might lead to non-discriminative visual words and, as a consequence, to poor recognition performance. This paper proposes a visual object recognition system which concurrently learns in an incremental and online fashion both the visual object category representations as well as the codebook words used to encode them. The codebook is defined using Gaussian Mixture Models which are updated using new object views. The approach contains similarities with the human visual object recognition system: evidence suggests that the development of recognition capabilities occurs on multiple levels and is sustained over large periods of time. Results show that the proposed system with concurrent learning of object categories and codebooks is capable of learning more categories, requiring less examples, and with similar accuracies, when compared to the classical Bag of Words approach using codebooks constructed offline.

Abstract

Abstract
Humans tend to organize their knowledge into hierarchies, because searches are efficient when proceeding downward in the tree-like structures. Similarly, many autonomous robots also contain some form of hierarchical knowledge. They may learn knowledge from their experiences through interaction with human users. However, it is difficult to find a common ground between robots and humans in a low level experience. Thus, their interaction must take place at the semantic level rather than at the perceptual level, and robots need to organize perceptual experiences into hierarchies for themselves. This paper presents an unsupervised method to build view-based perceptual hierarchies using hierarchical Nearest Neighbor Graphs (hNNGs), which combine most of the interesting features of both Nearest Neighbor Graphs (NNGs) and self-balancing trees. An incremental construction algorithm is developed to build and maintain the perceptual hierarchies. The paper describes the details of the data representations and the algorithms of hNNGs.

Abstract
Intelligent service robots should be able to improve their knowledge from accumulated experiences through continuous interaction with the environment, and in particular with humans. A human user may guide the process of experience acquisition, teaching new concepts, or correcting insufficient or erroneous concepts through interaction. This paper reports on work towards interactive learning of objects and robot activities in an incremental and open-ended way. In particular, this paper addresses human-robot interaction and experience gathering. The robot's ontology is extended with concepts for representing human-robot interactions as well as the experiences of the robot. The human-robot interaction ontology includes not only instructor teaching activities but also robot activities to support appropriate feedback from the robot. Two simplified interfaces are implemented for the different types of instructions including the teach instruction, which triggers the robot to extract experiences. These experiences, both in the robot activity domain and in the perceptual domain, are extracted and stored in memory, and they are used as input for learning methods. The functionalities described above are completely integrated in a robot architecture, and are demonstrated in a PR2 robot. © 2014 IEEE.

Abstract
Object representation is one of the most challenging tasks in robotics because it must provide reliable information in real-time to enable the robot to physically interact with the objects in its environment. To ensure robustness, a global object descriptor must be computed based on a unique and repeatable object reference frame. Moreover, the descriptor should contain enough information enabling to recognize the same or similar objects seen from different perspectives. This paper presents a new object descriptor named Global Orthographic Object Descriptor (GOOD) designed to be robust, descriptive and efficient to compute and use. We propose a novel sign disambiguation method, for computing a unique reference frame from the eigenvectors obtained through Principal Component Analysis of the point cloud of the target object view captured by a 3D sensor. Three principal orthographic projections and their distribution matrices are computed by exploiting the object reference frame. The descriptor is finally obtained by concatenating the distribution matrices in a sequence determined by entropy and variance features of the projections. Experimental results show that the overall classification performance obtained with GOOD is comparable to the best performances obtained with the state-of-the-art descriptors. Concerning memory and computation time, GOOD clearly outperforms the other descriptors. Therefore, GOOD is especially suited for real-time applications. The estimated object's pose is precise enough for real-time object manipulation tasks.

Abstract
This manuscript evaluates the usage of fused cross-spectral images in a monocular visual odometry approach. Fused images are obtained through a Discrete Wavelet Transform (DWT) scheme, where the best setup is empirically obtained by means of a mutual information based evaluation metric. The objective is to have a flexible scheme where fusion parameters are adapted according to the characteristics of the given images. Visual odometry is computed from the fused monocular images using an off the shelf approach. Experimental results using data sets obtained with two different platforms are presented. Additionally, comparison with a previous approach as well as with monocular-visible/infrared spectra are also provided showing the advantages of the proposed scheme.