Pradip Pramanick

Providing explanations of a robot’s behavior is a key enabler of trust in robots. Such explanations should be intuitive to people who are not experts in robotics. Prior research suggests that using multiple modalities to deliver explanations improves clarity. However, current methods for generating multimodal explanations neither assess nor ensure the coherence of the information across modalities. Here, we present an experiment to understand the effect of possible incoherence in multimodal explanations. We perform a user study asking participants to observe a series of robot failures and predict the reason for failure when provided with a controlled variation of multimodal explanations. Specifically, we present a methodology to compare incoherent and coherent explanations, aiming to understand their impact on perceiving robot failures.

Interaction ruptures in human-robot interaction (HRI) refer to scenarios when seamless interactions are disrupted. Such ruptures can be directly observed by the robot at times, e.g., not responding to a human utterance. However, often the ruptures could be more passive and subtle and require an analysis of the human’s behavior. In this work, we focus on detecting such ruptures by analyzing multimodal information in a face-to-face interaction setting. More specifically, this paper describes the PRISCA team’s participation in the ERR@HRI Challenge 2024, which was recently proposed to benchmark multimodal learning approaches to interaction rupture detection in HRI. Central to our approach is a feature-fusion strategy for multimodal representation learning, where we train a neural network with separate recurrent layers that act as temporal encoders to learn modality-specific representations. Our approach was ranked 3rd in the ERR@HRI challenge. We present detailed experimentation on the released dataset from the challenge and a thorough analysis of the results. We further discuss the limitations of current approaches and implications for future works. Code will be made available at https://github.com/pradippramanick/prisca-errhri/.

Social robots in our daily surroundings, like personal guides, waiter robots, home helpers, assistive robots, telepresence/teleoperation robots etc., are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most sought-after qualities that a robot can possess. However, there is no specific aspect and/or feature that defines socially acceptable behavior and it largely depends on the situation, application, and society. In this article, we investigate one such social behavior for collocated robots. Imagine a group of people is interacting with each other and we want to join the group. We as human beings do it in a socially acceptable manner, i.e., within the group, we do position ourselves in such a way that we can participate in the group activity without disturbing/obstructing anybody. To possess such a quality, first, a robot needs to determine the formation of the group and then determine a position for itself, which we humans do implicitly. There are many theories which study group formations and proxemics; one such theory is F-formation which could be utilized for this purpose. As the types of formations can be very diverse, detecting the social groups is not a trivial task. In this article, we provide a comprehensive survey of the existing work on social interaction and group detection using f-formation for robotics and other applications. We also put forward a novel holistic survey framework combining some of the possibly more important concerns and modules relevant to this problem. We define taxonomies based on methods, camera views, datasets, detection capabilities and scale, evaluation approaches, and application areas. We discuss certain open challenges and limitations in current literature along with possible future research directions based on this framework. In particular, we discuss the existing methods/techniques and their relative merits and demerits, applications, and provide a set of unsolved but relevant problems in this domain.

Natural language serves as the primary mode of communication when an intelligent agent with a physical presence engages with human beings. While a plethora of research focuses on natural language understanding (NLU), encompassing endeavors such as sentiment analysis, intent prediction, question answering, and summarization, the scope of NLU directed at situations necessitating tangible actions by an embodied agent remains limited. The inherent ambiguity and incompleteness inherent in natural language present challenges for intelligent agents striving to decipher human intention. To tackle this predicament head-on, we introduce a novel system known as task and argument grounding for Embodied agents (tagE). At its core, our system employs an inventive neural network model designed to extract a series of tasks from complex task instructions expressed in natural language. Our proposed model adopts an encoder-decoder framework enriched with nested decoding to effectively extract tasks and their corresponding arguments from these intricate instructions. These extracted tasks are then mapped (or grounded) to the robot’s established collection of skills, while the arguments find grounding in objects present within the environment. To facilitate the training and evaluation of our system, we have curated a dataset featuring complex instructions. The results of our experiments underscore the prowess of our approach, as it outperforms robust baseline models.

The usage of automatic speech recognition (ASR) systems are becoming omnipresent ranging from personal assistant to chatbots, home, and industrial automation systems, etc. Modern robots are also equipped with ASR capabilities for interacting with humans as speech is the most natural interaction modality. However, ASR in robots faces additional challenges as compared to a personal assistant. Being an embodied agent, a robot must recognize the physical entities around it and therefore reliably recognize the speech containing the description of such entities. However, current ASR systems are often unable to do so due to limitations in ASR training, such as generic datasets and open-vocabulary modeling. Also, adverse conditions during inference, such as noise, accented, and far-field speech makes the transcription inaccurate. In this work, we present a method to incorporate a robot’s visual information into an ASR system and improve the recognition of a spoken utterance containing a visible entity. Specifically, we propose a new decoder biasing technique to incorporate the visual context while ensuring the ASR output does not degrade for incorrect context. We achieve a 59% relative reduction in WER from an unmodified ASR system.

Robotic task instructions often involve a referred object that the robot must locate (ground) within the environment. While task intent understanding is an essential part of natural language understanding, less effort is made to resolve ambiguity that may arise while grounding the task. Existing works use vision-based task grounding and ambiguity detection, suitable for a fixed view and a static robot. However, the problem magnifies for a mobile robot, where the ideal view is not known beforehand. Moreover, a single view may not be sufficient to locate all the object instances in the given area, which leads to inaccurate ambiguity detection. Human intervention is helpful only if the robot can convey the kind of ambiguity it is facing. In this article, we present DoRO (Disambiguation of Referred Object), a system that can help an embodied agent to disambiguate the referred object by raising a suitable query whenever required. Given an area where the intended object is, DoRO finds all the instances of the object by aggregating observations from multiple views while exploring & scanning the area. It then raises a suitable query using the information from the grounded object instances. Experiments conducted with the AI2Thor simulator show that DoRO not only detects the ambiguity more accurately but also raises verbose queries with more accurate information from the visual-language grounding.