Human-robot Teams Research Articles

The Journey or the Destination: The Impact of Transparency and Goal Attainment on Trust in Human-Robot Teams

As robots gain autonomy, human-robot task delegation can become more goal-oriented; specifying what to do rather than how. This can lead to unexpected robot behaviour. We investigated the effect of transparency and outcome on the perceived trustworthiness of a robot that deviates from the expected manner to reach a delegated goal. Participants (N = 82) engaged in a virtual military mission as a Human-Robot Team using a 2x2 between-subjects design (low vs. high transparency, positive vs. negative outcome). Participants received training on the expected manner to reach the mission’s goal. In the actual mission, the robot deviated from the planned path. We manipulated whether the robot explained its deviation and whether the outcome was better or worse than the original plan. Results showed that transparency contributed to higher and more stable levels of trust, without increasing subjective workload. While the robot’s deviation led to a violation of trust in the low transparency condition, trust remained stable in the high transparency condition, indicating a buffering effect of transparency on trust in case of unexpected behaviour. The impact of outcome on trust was consistent across transparency conditions. Our findings underscore the role of transparency as a tool for fostering human-robot trust.

Embracing Levin’s Legacy: Advancing Socio-Technical Learning and Development in Human-Robot Team Design Through STS Approaches

AbstractThis paper investigates the synergy between Levin’s theories on technology transfer as a socio-technical learning and developmental process (TLD process), and what we learnt about socio-technical systems (STS) theories in a case study developing human robot solutions for the construction sector. Levin’s extensive work highlights the significance of technology transfer as a means for organizational development. His TLD process emphasizes the intricate interplay between technology, organizational change, and learning and highlights the importance of incorporating cultural knowledge and skills into the technological transfer process. Contemporary STS views developed through our own work are introduced to complement and extend Levin’s theories by providing a systemic lens to understand the broader socio-technical context in which technology transfer occurs. To illustrate the synergies and potential challenges from Levin’s theories of technology transfer with contemporary STS concepts, we use a qualitative study of a unique case about the design and development of human-robot teams (HRTs) for construction tasks. Our findings reveal that while Levin’s theories provide a valuable foundation for understanding technology transfer and organizational change, contemporary socio-technical systems face unique challenges in the context of AI-driven human-robot teams, where intelligent robots also contribute to the socio-technical learning process. Moreover, the rapidly evolving nature of technology and innovations could exponentially impact on multidisciplinary design teams, stakeholder participation and inter-organizational dynamics. The discussions suggest an extension of co-generative learning to incorporate ‘collaborative intelligence’ between human-robot teams enabled by artificial intelligence (AI). Consequently, we suggest that Levin’s theories of technology transfer, developed before the rapid application of AI, may not have fully considered further social challenges caused by the introduction of autonomous systems such as AI-driven HRT systems. We extend Levin’s important work by suggesting that addressing such challenges requires ongoing dialogue and collaboration among researchers, practitioners, and policymakers with different disciplinary backgrounds to develop robust and reliable socio-technical systems frameworks to navigate the complexities of robotics and AI in today’s rapidly evolving technological landscape.

Robot learning on the job: Human-in-the-loop autonomy and learning during deployment

With the rapid growth of computing powers and recent advances in deep learning, we have witnessed impressive demonstrations of novel robot capabilities in research settings. Nonetheless, these learning systems exhibit brittle generalization and require excessive training data for practical tasks. To harness the capabilities of state-of-the-art robot learning models while embracing their imperfections, we present Sirius, a principled framework for humans and robots to collaborate through a division of work. In this framework, partially autonomous robots are tasked with handling a major portion of decision-making where they work reliably; meanwhile, human operators monitor the process and intervene in challenging situations. Such a human–robot team ensures safe deployments in complex tasks. Further, we introduce a new learning algorithm to improve the policy’s performance on the data collected from the task executions. The core idea is re-weighing training samples with approximated human trust and optimizing the policies with weighted behavioral cloning. We evaluate Sirius in simulation and on real hardware, showing that Sirius consistently outperforms baselines over a collection of contact-rich manipulation tasks, achieving an 8% boost in simulation and 27% on real hardware than the state-of-the-art methods in policy success rate, with twice faster convergence and 85% memory size reduction. Videos and more details are available at https://ut-austin-rpl.github.io/sirius/ .

TIP: A trust inference and propagation model in multi-human multi-robot teams

Trust is a crucial factor for effective human–robot teaming. Existing literature on trust modeling predominantly focuses on dyadic human-autonomy teams where one human agent interacts with one robot. There is little, if not no, research on trust modeling in teams consisting of multiple human and robotic agents. To fill this important research gap, we present the Trust Inference and Propagation (TIP) model to model and estimate human trust in multi-human multi-robot teams. In a multi-human multi-robot team, we postulate that there exist two types of experiences that a human agent has with a robot: direct and indirect experiences. The TIP model presents a novel mathematical framework that explicitly accounts for both types of experiences. To evaluate the model, we conducted a human-subject experiment with 15 pairs of participants (N=30\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$N=30$$\\end{document}). Each pair performed a search and detection task with two drones. Results show that our TIP model successfully captured the underlying trust dynamics and significantly outperformed a baseline model. To the best of our knowledge, the TIP model is the first mathematical framework for computational trust modeling in multi-human multi-robot teams.

Human-Robot Team Performance Compared to Full Robot Autonomy in 16 Real-World Search and Rescue Missions: Adaptation of the DARPA Subterranean Challenge

Human-Robot Team Performance Compared to Full Robot Autonomy in 16 Real-World Search and Rescue Missions: Adaptation of the DARPA Subterranean Challenge

Sociotechnical considerations on developing human robot teaming solutions for construction: a case study

This research advocates for a paradigm shift in the exploration of human–robot teaming solutions for construction automation, by focusing on an integrated view of sociotechnical systems (STS) that recognize the inter-dependencies among actors at various levels when tracing how innovative ideas about intelligent robotic technologies translate into practice in the construction sector. Through a qualitative case study, the paper examines industry and organizational considerations for developing and adopting robotic technologies, leadership vision, mediation, and change management to propose integrative strategies to enhance expectations, acceptance, and deployment of intelligent technologies in human–robot teams (HRTs). This study contributes to research in construction robotics at three organizational levels—macro, meso, and micro. The Integrated Human–Robot Teaming Framework and associated workplan schema offer guidance for navigating human–robot teaming complexities. The study recommends adopting STS principles in planning and deploying robotics applications for construction, emphasizing the integration of multiple elements across the lifecycle. Active leadership and mediation emerge as critical elements in navigating complex networks, ensuring successful outcomes in the dynamic construction environment.

Effect of human emotional responses on human-robot team pty in construction

Human-robot collaboration (HRC) is expected to improve construction productivity by integrating robotic capabilities with human expertise. However, the effects of HRC on human emotions are unclear despite their critical impacts on human performance during HRC. This paper examined the inter-relationship between robots' parameters, like movement speed, and emotional responses, during HRC for a construction task. Eighteen participants were observed as they experience various conditions of robots' parameters during a bricklaying task with an arm-type collaborative robot in a laboratory setting. Their brainwaves (i.e., electroencephalogram (EEG) signals) were monitored using an EEG headset to identify emotional responses. Results showed significant emotional variations due to robots' parameters, which could affect the estimated productivity of human-robot teams. This paper demonstrated the emotional changes caused by the robots' parameters during HRC for construction tasks, highlighting the importance of considering emotions as a way to balance the emotional well-being of people and the high productivity of human-robot teams.

Unlocking underrepresented use-cases for large language model-driven human-robot task planning

Large language models (LLM) are now the de facto task planners for Embodied AI (EAI) systems. This shift can be attributed to LLMs' powerful, emergent properties which enable their adaptation to downstream tasks with minimal to no fine tuning via prompting. However, we find that LLM-driven task planning is not a solved problem. In this work we measure the extent to which these models can be adapted to complex and domain-specific task planning via few-shot prompting. Additionally, we contribute quantitative and qualitative analysis on prompt robustness. Lastly, to meet the challenges of adapting EAI systems to real-world, industrial domains, we adopt a human-in-the-loop approach to guarantee safe and interpretable task planning and execution. We successfully demonstrate co-located, human-robot teaming where an Augmented Reality (AR) headset mediates information exchanged between an EAI agent and human operator for a variety of inspection tasks. To our knowledge the use of an AR headset for multimodal grounding and the application of EAI to industrial tasks are novel contributions within Embodied AI research.

Generating Pattern-Based Conventions for Predictable Planning in Human-Robot Collaboration

For humans to effectively work with robots, they must be able to predict the actions and behaviors of their robot teammates rather than merely react to them. While there are existing techniques enabling robots to adapt to human behavior, there is a demonstrated need for methods that explicitly improve humans’ ability to understand and predict robot behavior at multi-task timescales. In this work, we propose a method leveraging the innate human propensity for pattern recognition in order to improve team dynamics in human-robot teams and to make robots more predictable to the humans that work with them. Patterns are a cognitive tool that humans use and rely on often, and the human brain is in many ways primed for pattern recognition and usage. We propose Pattern-Aware Convention-setting for Teaming (PACT), an entropy-based algorithm that identifies and imposes appropriate patterns over a robot’s planner or policy over long time horizons. These patterns are autonomously generated and chosen via an algorithmic process that considers human-perceptible features and characteristics derived from the tasks to be completed, and as such, produces behavior that is easier for humans to identify and predict. Our evaluation shows that PACT contributes to significant improvements in team dynamics and teammate perceptions of the robot, as compared to robots that utilize traditionally ‘optimal’ plans and robots utilizing unoptimized patterns.

HOTSPOT: An ad hoc teamwork platform for mixed human-robot teams

HOTSPOT: An ad hoc teamwork platform for mixed human-robot teams

Enhancing human–robot collaborative transportation through obstacle-aware vibrotactile warning and virtual fixtures

Transporting large and heavy objects can benefit from Human–Robot Collaboration (HRC), increasing the contribution of robots to our daily tasks and addressing challenges arising from labor shortages. This strategy typically positions the human collaborator as the leader, with the robot assuming the follower role. However, when transporting large objects, the operator’s situational awareness can be compromised as the objects may occlude different parts of the environment, weakening the human leader’s decision-making capacity and leading to failure due to collision. This paper proposes a situational awareness framework for collaborative transportation to face this challenge. The framework integrates a multi-modal haptic-based Obstacle Feedback Module with two units. The first unit consists of a warning module that alerts the operator through a haptic belt with four vibrotactile devices that provide feedback about the location and proximity of the obstacles. The second unit implements virtual fixtures as hard constraints for mobility. The warning feedback and the virtual fixtures act online based on the information given by two Lidars mounted on a mobile manipulator to detect the obstacles in the surroundings. By enhancing the operator’s awareness of the environment, the proposed module improves the safety of the human–robot team in collaborative transportation scenarios by preventing collisions. Experiments with 16 non-expert subjects in four feedback modalities during four scenarios report an objective evaluation thanks to quantitative metrics and subjective evaluations based on user-level experiences. The results reveal the strengths and weaknesses of the implemented feedback modalities while providing solid evidence of the increased situational awareness of the operator when the two haptic units are employed.

Optimizing Human-Robot Teaming Performance through Q-Learning-Based Task Load Adjustment and Physiological Data Analysis.

The transition to Industry 4.0 and 5.0 underscores the need for integrating humans into manufacturing processes, shifting the focus towards customization and personalization rather than traditional mass production. However, human performance during task execution may vary. To ensure high human-robot teaming (HRT) performance, it is crucial to predict performance without negatively affecting task execution. Therefore, to predict performance indirectly, significant factors affecting human performance, such as engagement and task load (i.e., amount of cognitive, physical, and/or sensory resources required to perform a particular task), must be considered. Hence, we propose a framework to predict and maximize the HRT performance. For the prediction of task performance during the development phase, our methodology employs features extracted from physiological data as inputs. The labels for these predictions-categorized as accurate performance or inaccurate performance due to high/low task load-are meticulously crafted using a combination of the NASA TLX questionnaire, records of human performance in quality control tasks, and the application of Q-Learning to derive task-specific weights for the task load indices. This structured approach enables the deployment of our model to exclusively rely on physiological data for predicting performance, thereby achieving an accuracy rate of 95.45% in forecasting HRT performance. To maintain optimized HRT performance, this study further introduces a method of dynamically adjusting the robot's speed in the case of low performance. This strategic adjustment is designed to effectively balance the task load, thereby enhancing the efficiency of human-robot collaboration.

Risk-based performance assessment from fully manual to human-robot teaming in pressurized tank inspection operations

The use of robotics in the process industry has shown a stable, increasing trend, according to survey reports, reducing the exposure of operators to critical operations, mainly during maintenance. Moving from full manual (FM) to human-robot teaming (HRT) operations is expected to reduce the risks for operators and increase operational efficiency. The methods used to assess system performances require an adaptation. Traditional risk assessment techniques are no longer adapted to analyze the new way of working; the previous methods proposed for HRT systems have been criticized for their fragmentation, complexity, and lack of validation.This study proposed an integrated framework, including the qualitative and quantitative stages, to investigate the risk-based system performance and compare the full manual and human-robot teaming scenarios in pressurized tank inspection operations. The outputs demonstrated that the integrated framework worked for FM and HRT system performance assessment, considering multiple element types and their interdependencies, generating knowledge that can be exploited to reduce the system's risk and choose among different operational alternatives.

Exploring a GPT-based large language model for variable autonomy in a VR-based human-robot teaming simulation.

In a rapidly evolving digital landscape autonomous tools and robots are becoming commonplace. Recognizing the significance of this development, this paper explores the integration of Large Language Models (LLMs) like Generative pre-trained transformer (GPT) into human-robot teaming environments to facilitate variable autonomy through the means of verbal human-robot communication. In this paper, we introduce a novel simulation framework for such a GPT-powered multi-robot testbed environment, based on a Unity Virtual Reality (VR) setting. This system allows users to interact with simulated robot agents through natural language, each powered by individual GPT cores. By means of OpenAI's function calling, we bridge the gap between unstructured natural language input and structured robot actions. A user study with 12 participants explores the effectiveness of GPT-4 and, more importantly, user strategies when being given the opportunity to converse in natural language within a simulated multi-robot environment. Our findings suggest that users may have preconceived expectations on how to converse with robots and seldom try to explore the actual language and cognitive capabilities of their simulated robot collaborators. Still, those users who did explore were able to benefit from a much more natural flow of communication and human-like back-and-forth. We provide a set of lessons learned for future research and technical implementations of similar systems.

An Evaluation Framework of Human-Robot Teaming for Navigation Among Movable Obstacles via Virtual Reality-Based Interactions

An Evaluation Framework of Human-Robot Teaming for Navigation Among Movable Obstacles via Virtual Reality-Based Interactions

Autonomous Policy Explanations for Effective Human-Machine Teaming

Policy explanation, a process for describing the behavior of an autonomous system, plays a crucial role in effectively conveying an agent's decision-making rationale to human collaborators and is essential for safe real-world deployments. It becomes even more critical in effective human-robot teaming, where good communication allows teams to adapt and improvise successfully during uncertain situations by enabling value alignment within the teams. This thesis proposal focuses on improving human-machine teaming by developing novel human-centered explainable AI (xAI) techniques that empower autonomous agents to communicate their capabilities and limitations via multiple modalities, teach and influence human teammates' behavior as decision-support systems, and effectively build and manage trust in HRI systems.

Who’s in charge here? A survey on Trustworthy AI in Variable Autonomy Robotic Systems

This paper surveys the Variable Autonomy (VA) robotics literature that considers two contributory elements to Trustworthy AI: transparency and explainability. These elements should play a crucial role when designing and adopting robotic systems, especially in VA where poor or untimely adjustments of the system’s level of autonomy can lead to errors, control conflicts, user frustration and ultimate disuse of the system. Despite this need, transparency and explainability is, to the best of our knowledge, mostly overlooked in VA robotics literature or is not considered explicitly. In this paper, we aim to present and examine the most recent contributions to the VA literature concerning transparency and explainability. In addition, we propose a way of thinking about VA by breaking these two concepts down based on: the mission of the human-robot team; who the stakeholder is; what needs to be made transparent or explained; why they need it; and how it can be achieved. Last, we provide insights and propose ways to move VA research forward. Our goal with this paper is to raise awareness and inter-community discussions among the Trustworthy AI and the VA robotics communities.

Use of cross‐training in human–robot collaborative rescue

AbstractHuman–robot collaboration has been widely used in postdisaster investigation and rescue. Human–robot team training is a good way to improve the team rescue efficiency and safety; two common training methods, namely, procedural training and cross‐training, are explored in this study. Currently, relatively few studies have explored the impact of cross‐training on human–robot collaboration in rescue tasks. Cross‐training will be novel to most rescuers and as such, an evaluation of cross‐training in comparison with more conventional procedural training is warranted. This study investigated the effects of these two training methods on rescue performance, situation awareness and workload. Forty‐two participants completed a path‐planning and a photo‐taking task in an unfamiliar simulated postdisaster environment. The rescue performance results showed that cross‐training method had significant advantages over procedural training for human–robot collaborative rescue tasks. During the training process, compared with procedural training, participants were more likely to achieve excellent photo‐taking performance after cross‐training; after training, the length of the route planned by the cross‐training group was significantly shorter than that of the procedural‐training group. In addition, procedural‐training marginal significantly increased the emotion demand, which proves that cross‐training can well control the emotions of the operators and make them more involved in the rescue task. The study also found that arousal level increased significantly after the first cross‐training session, and decreased to the same level as procedural training after multiple sessions. These results contribute to the application of cross‐training in human–robot collaborative rescue teams.

Meaningful human control and variable autonomy in human-robot teams for firefighting.

Introduction: Humans and robots are increasingly collaborating on complex tasks such as firefighting. As robots are becoming more autonomous, collaboration in human-robot teams should be combined with meaningful human control. Variable autonomy approaches can ensure meaningful human control over robots by satisfying accountability, responsibility, and transparency. To verify whether variable autonomy approaches truly ensure meaningful human control, the concept should be operationalized to allow its measurement. So far, designers of variable autonomy approaches lack metrics to systematically address meaningful human control. Methods: Therefore, this qualitative focus group (n = 5 experts) explored quantitative operationalizations of meaningful human control during dynamic task allocation using variable autonomy in human-robot teams for firefighting. This variable autonomy approach requires dynamic allocation of moral decisions to humans and non-moral decisions to robots, using robot identification of moral sensitivity. We analyzed the data of the focus group using reflexive thematic analysis. Results: Results highlight the usefulness of quantifying the traceability requirement of meaningful human control, and how situation awareness and performance can be used to objectively measure aspects of the traceability requirement. Moreover, results emphasize that team and robot outcomes can be used to verify meaningful human control but that identifying reasons underlying these outcomes determines the level of meaningful human control. Discussion: Based on our results, we propose an evaluation method that can verify if dynamic task allocation using variable autonomy in human-robot teams for firefighting ensures meaningful human control over the robot. This method involves subjectively and objectively quantifying traceability using human responses during and after simulations of the collaboration. In addition, the method involves semi-structured interviews after the simulation to identify reasons underlying outcomes and suggestions to improve the variable autonomy approach.

Fast scheduling of human-robot teams collaboration on synchronised production-logistics tasks in aircraft assembly

Fast scheduling of human-robot teams collaboration on synchronised production-logistics tasks in aircraft assembly