When encountering a robot in the wild, it is not inherently clear to human users what the robot's capabilities are. When encountering misunderstandings or problems in spoken interaction, robots often just apologize and move on, without additional effort to make sure the user understands what happened. We set out to compare the effect of two speech based capability communication strategies (proactive, reactive) to a robot without such a strategy, in regard to the user's rating of and their behavior during the interaction. For this, we conducted an in-person user study with 120 participants who had three speech-based interactions with a social robot in a restaurant setting. Our results suggest that users preferred the robot communicating its capabilities proactively and adjusted their behavior in those interactions, using a more conversational interaction style while also enjoying the interaction more.

To control the lower-limb exoskeleton robot effectively, it is essential to accurately recognize user status and environmental conditions. Previous studies have typically addressed these recognition challenges through independent models for each task, resulting in an inefficient model development process. In this study, we propose a Multitask learning approach that can address multiple recognition challenges simultaneously. This approach can enhance data efficiency by enabling knowledge sharing between each recognition model. We demonstrate the effectiveness of this approach using Gait phase recognition (GPR) and Terrain classification (TC) as examples, the most conventional recognition tasks in lower-limb exoskeleton robots. We first created a high-performing GPR model that achieved a Root mean square error (RMSE) value of 2.345 $\pm$ 0.08 and then utilized its knowledge-sharing backbone feature network to learn a TC model with an extremely limited dataset. Using a limited dataset for the TC model allows us to validate the data efficiency of our proposed Multitask learning approach. We compared the accuracy of the proposed TC model against other TC baseline models. The proposed model achieved 99.5 $\pm$ 0.044% accuracy with a limited dataset, outperforming other baseline models, demonstrating its effectiveness in terms of data efficiency. Future research will focus on extending the Multitask learning framework to encompass additional recognition tasks.

Goal Recognition is the task of discerning the correct intended goal that an agent aims to achieve, given a set of goal hypotheses, a domain model, and a sequence of observations (i.e., a sample of the plan executed in the environment). Existing approaches assume that goal hypotheses comprise a single conjunctive formula over a single final state and that the environment dynamics are deterministic, preventing the recognition of temporally extended goals in more complex settings. In this paper, we expand goal recognition to temporally extended goals in Fully Observable Non-Deterministic (FOND) planning domain models, focusing on goals on finite traces expressed in Linear Temporal Logic (LTLf) and Pure Past Linear Temporal Logic (PLTLf). We develop the first approach capable of recognizing goals in such settings and evaluate it using different LTLf and PLTLf goals over six FOND planning domain models. Empirical results show that our approach is accurate in recognizing temporally extended goals in different recognition settings.

Saliency mechanisms play an important role when visual recognition must be performed in cluttered scenes. We propose a computational defi- nition of saliency that deviates from existing models by equating saliency to discrimination. In particular, the salient attributes of a given visual class are defined as the features that enable best discrimination between that class and all other classes of recognition interest. It is shown that this definition leads to saliency algorithms of low complexity, that are scalable to large recognition problems, and is compatible with existing models of early biological vision. Experimental results demonstrating success in the context of challenging recognition problems are also pre- sented.

Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios it is important that goal recognition algorithms can recognize goals of an observed agent as fast as possible and with minimal domain knowledge. Hence, in this paper, we propose a hybrid method for online goal recognition that combines a symbolic planning landmark based approach and a data-driven goal recognition approach and evaluate it in a real-world cooking scenario. The empirical results show that the proposed method is not only significantly more efficient in terms of computation time than the state-of-the-art but also improves goal recognition performance. Furthermore, we show that the utilized planning landmark based approach, which was so far only evaluated on artificial benchmark domains, achieves also good recognition performance when applied to a real-world cooking scenario.

An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on observations of the user's actions and state of the environment. In this work, we investigate the application of two state-of-the-art, planning-based plan recognition approaches in a real-world setting. So far, these approaches were only evaluated in artificial settings in combination with agents that act perfectly rational. We show that such approaches have difficulties when used to recognize the goals of human subjects, because human behaviour is typically not perfectly rational. To overcome this issue, we propose an extension to the existing approaches through a classification-based method trained on observed behaviour data. We empirically show that the proposed extension not only outperforms the purely planning-based- and purely data-driven goal recognition methods but is also able to recognize the correct goal more reliably, especially when only a small number of observations were seen. This substantially improves the usefulness of hybrid goal recognition approaches for intelligent assistance systems, as recognizing a goal early opens much more possibilities for supportive reactions of the system.

We propose a statistical procedure to characterize and extract features from a waveform that can be applied as a pre-processing signal stage in a pattern recognition task using Artificial Neural Networks. Such a procedure is based on measuring a 30-parameters set of moments and cumulants from the waveform, its derivative, and its integral. The technique is presented as an extension of the Statistical Signal Characterization method existing in the literature. As a testing methodology, we used the procedure to distinguish a pulse-like signal from different versions of itself with frequency spectrum alterations or deformations. The recognition task was performed by single feed-forward back-propagation networks trained for the case Sinc-, Gaussian-, and Chirp-pulse waveform. Because of the success obtained in these examples, we can conclude that the proposed extended statistical signal characterization method is an effective tool for pattern-recognition applications. In particular, we can use it as a fast pre-processing stage in embedded systems with limited memory or computational capability.

The recent progress in deep learning has given rise to a non-invasive and effective approach for animal biometrics. These modern techniques allow researchers to track animal individuals on a large-scale image database. Typical approaches are suited to a closed-set recognition problem, which is to identify images of known objects only. However, such approaches are not scalable because they mis-classify images of unknown objects. To recognize the images of unknown objects as ‘unknown’, a framework should be able to deal with the open set recognition scenario. This paper proposes a fully automatic, vision-based identification framework capable of recognizing shark individuals including those that are unknown. The framework first detects and extracts the shark from the original image. After that, we develop a deep network to transform the extracted image to an embedding vector in latent space. The proposed network consists of the Visual Geometry Group-UNet (VGG-UNet) and a modified Visual Geometry Group-16 (VGG-16) network. The VGG-UNet is utilized to detect shark bodies, and the modified VGG-16 is used to learn embeddings of shark individuals. For the recognition task, our framework learns a decision boundary using a one-class support vector machine (OSVM) for each shark included in the training phase using a few embedding vectors belonging to them, then it determines whether a new shark image is recognized as belonging to a known shark individual. Our proposed network can recognize shark individuals with high accuracy and can effectively deal with the open set recognition problem with shark images.

I was stunned by projects such as GitHub Copilot, Deepfake, and AI bots playing Alpha Go with complex strategies even professional players couldn't understand. I thought we were almost there to reach artificial general intelligence (AGI). I thought it was the great leap of AGI. Today's neural network lacks in many ways to human brains. Machine learning (including deep learning) can solve a particular recognition problem. Yet, intelligence is more of a generative problem.