Search for: All records

Understanding human perceptions of robot performance is crucial for designing socially intelligent robots that can adapt to human expectations. Current approaches often rely on surveys, which can disrupt ongoing human–robot interactions. As an alternative, we explore predicting people’s perceptions of robot performance using non-verbal behavioral cues and machine learning techniques. We contribute the SEAN TOGETHER Dataset consisting of observations of an interaction between a person and a mobile robot in Virtual Reality, together with perceptions of robot performance provided by users on a 5-point scale. We then analyze how well humans and supervised learning techniques can predict perceived robot performance based on different observation types (like facial expression and spatial behavior features). Our results suggest that facial expressions alone provide useful information, but in the navigation scenarios that we considered, reasoning about spatial features in context is critical for the prediction task. Also, supervised learning techniques outperformed humans’ predictions in most cases. Further, when predicting robot performance as a binary classification task on unseen users’ data, the F1-Score of machine learning models more than doubled that of predictions on a 5-point scale. This suggested good generalization capabilities, particularly in identifying performance directionality over exact ratings. Based on these findings, we conducted a real-world demonstration where a mobile robot uses a machine learning model to predict how a human who follows it perceives it. Finally, we discuss the implications of our results for implementing these supervised learning models in real-world navigation. Our work paves the path to automatically enhancing robot behavior based on observations of users and inferences about their perceptions of a robot. 

In Human–Robot Interaction, researchers typically utilize in-person studies to collect subjective perceptions of a robot. In addition, videos of interactions and interactive simulations (where participants control an avatar that interacts with a robot in a virtual world) have been used to quickly collect human feedback at scale. How would human perceptions of robots compare between these methodologies? To investigate this question, we conducted a 2x2 between-subjects study (N=160), which evaluated the effect of the interaction environment (Real vs. Simulated environment) and participants’ interactivity during human-robot encounters (Interactive participation vs. Video observations) on perceptions about a robot (competence, discomfort, social presentation, and social information processing) for the task of navigating in concert with people. We also studied participants’ workload across the experimental conditions. Our results revealed a significant difference in the perceptions of the robot between the real environment and the simulated environment. Furthermore, our results showed differences in human perceptions when people watched a video of an encounter versus taking part in the encounter. Finally, we found that simulated interactions and videos of the simulated encounter resulted in a higher workload than real-world encounters and videos thereof. Our results suggest that findings from video and simulation methodologies may not always translate to real-world human–robot interactions. In order to allow practitioners to leverage learnings from this study and future researchers to expand our knowledge in this area, we provide guidelines for weighing the tradeoffs between different methodologies. 

Recent work in Human-Robot Interaction (HRI) has shown that robots can leverage implicit communicative signals from users to understand how they are being perceived during interactions. For example, these signals can be gaze patterns, facial expressions, or body motions that reflect internal human states. To facilitate future research in this direction, we contribute the REACT database, a collection of two datasets of human-robot interactions that display users’ natural reactions to robots during a collaborative game and a photography scenario. Further, we analyze the datasets to show that interaction history is an important factor that can influence human reactions to robots. As a result, we believe that future models for interpreting implicit feedback in HRI should explicitly account for this history. REACT opens up doors to this possibility in the future. 

We interviewed 8 individuals from industry and academia to better understand how they valued different aspects of social robot navigation. Interviewees were asked to rank the importance of 10 measures commonly used to evaluate social navigation policies. Interviewees were then asked open-ended questions about social navigation, and how they think about evaluating the challenges they face. Our interviews with industry and academic experts in social navigation revealed that avoiding collisions was the only universally important measure. Beyond the safety consideration of avoiding collisions, roboticists have varying priorities regarding social navigation. Given the high priority interviewees placed on safety, we recommend that social navigation approaches should first aim to ensure safety. Once safety is ensured, we recommend that each social navigation algorithm be evaluated using the measures most relevant to the intended application domain. 

Deploying robots in-the-wild is critical for studying human-robot interaction, since human behavior varies between lab settings and public settings. Though robots that have been used in-the-wild exist, many of these robots are proprietary, expensive, or unavailable. We introduce Shutter, a low-cost, flexible social robot platform for in-the-wild experiments on human-robot interaction. Our demonstration will include a Shutter robot, which consists of a 4-DOF arm with a face screen, and a Kinect sensor. We will demonstrate two different interactions with Shutter: a photo-taking interaction and an embodied explanations interaction. Both interactions have been publicly deployed on the Shutter system. 

Recent research in robot learning suggests that implicit human feedback is a low-cost approach to improving robot behavior without the typical teaching burden on users. Because implicit feedback can be difficult to interpret, though, we study different methods to collect fine-grained labels from users about robot performance across multiple dimensions, which can then serve to map implicit human feedback to performance values. In particular, we focused on understanding the effects of annotation order and frequency on human perceptions of the self-annotation process and the usefulness of the labels for creating data-driven models to reason about implicit feedback. Our results demonstrate that different annotation methods can influence perceived memory burden, annotation difficulty, and overall annotation time. Based on our findings, we conclude with recommendations to create future implicit feedback datasets in Human-Robot Interaction. 

We propose a demonstration of the Social Environment for Autonomous Navigation with Virtual Reality (VR) for advancing research in Human-Robot Interaction. In our demonstration, a user controls a virtual avatar in simulation and performs directed navigation tasks with a mobile robot in a warehouse environment. Our demonstration shows how researchers can leverage the immersive nature of VR to study robot navigation from a user-centered perspective in densely populated environments while avoiding physical safety concerns common with operating robots in the real world. This is important for studying interactions with robots driven by algorithms that are early in their development lifecycle. 

While neural network binary classifiers are often evaluated on metrics such as Accuracy and F1-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques have been adopted to optimize certain confusion matrix based metrics, it is challenging or impossible in some cases to generalize the techniques to other metrics. Adversarial learning approaches have also been proposed to optimize networks via confusion matrix based metrics, but they tend to be much slower than common training methods. In this work, we propose a unifying approach to training neural network binary classifiers that combines a differentiable approximation of the Heaviside function with a probabilistic view of the typical confusion matrix values using soft sets. Our theoretical analysis shows the benefit of using our method to optimize for a given evaluation metric, such as F1-Score, with soft sets, and our extensive experiments show the effectiveness of our approach in several domains. 

We study two approaches for predicting an appropriate pose for a robot to take part in group formations typical of social human conversations subject to the physical layout of the surrounding environment. One method is model-based and explicitly encodes key geometric aspects of conversational formations. The other method is data-driven. It implicitly models key properties of spatial arrangements using graph neural networks and an adversarial training regimen. We evaluate the proposed approaches through quantitative metrics designed for this problem domain and via a human experiment. Our results suggest that the proposed methods are effective at reasoning about the environment layout and conversational group formations. They can also be used repeatedly to simulate conversational spatial arrangements despite being designed to output a single pose at a time. However, the methods showed different strengths. For example, the geometric approach was more successful at avoiding poses generated in nonfree areas of the environment, but the data-driven method was better at capturing the variability of conversational spatial formations. We discuss ways to address open challenges for the pose generation problem and other interesting avenues for future work. 

We study conversational group detection in varied social scenes using a message-passing Graph Neural Network (GNN) in combination with the Dominant Sets clustering algorithm. Our approach first describes a scene as an interaction graph, where nodes encode individual features and edges encode pairwise relationship data. Then, it uses a GNN to predict pairwise affinity values that represent the likelihood of two people interacting together, and computes non-overlapping group assignments based on these affinities. We evaluate the proposed approach on the Cocktail Party and MatchNMingle datasets. Our results suggest that using GNNs to leverage both individual and relationship features when computing groups is beneficial, especially when more features are available for each individual.