An official website of the United States government
For robots to seamlessly interact with humans, we first need to make sure that humans and robots understand one another. Diverse algorithms have been developed to enable robots to learn from humans (i.e., transferring information from humans to robots). In parallel, visual, haptic, and auditory communication interfaces have been designed to convey the robot’s internal state to the human (i.e., transferring information from robots to humans). Prior research often separates these two directions of information transfer, and focuses primarily on either learning algorithms or communication interfaces. By contrast, in this survey we take an interdisciplinary approach to identify common themes and emerging trends that close the loop between learning and communication. Specifically, we survey state-of-the-art methods and outcomes for communicating a robot’s learning back to the human teacher during human-robot interaction. This discussion connects human-in-the-loop learning methods and explainable robot learning with multimodal feedback systems and measures of human-robot interaction. We find that—when learning and communication are developed together—the resulting closed-loop system can lead to improved human teaching, increased human trust, and human-robot co-adaptation. The paper includes a perspective on several of the interdisciplinary research themes and open questions that could advance how future robots communicate their learning to everyday operators. Finally, we implement a selection of the reviewed methods in a case study where participants kinesthetically teach a robot arm. This case study documents and tests an integrated approach for learning in ways that can be communicated, conveying this learning across multimodal interfaces, and measuring the resulting changes in human and robot behavior.
more »
« less
Modeling Haptic Communication in Cooperative Teams
A means to communicate by touch is established when two humans grasp a common rigid object, and such communication is thought to play a role in the superior performance two humans acting together are able to demonstrate over either agent acting alone. But the superior performance demonstrated by dyads, whether in making point-to-point movements or tracking unpredictable targets, is strictly empirical to date. Mechanistic accounts for the performance improvement and explanations relying on haptic communication have been lacking. In this paper we develop a model of haptic communication across a linkage connecting two agents that provides an explicit means for the dyad to achieve a higher loop gain than either agent acting alone and higher than the two agents acting together without haptic feedback. We show that haptic communication closes an additional feedback loop through the linkage and the sensorimotor control systems of both agents. This feedback loop contributes a new factor to the loop gain and thus a definitive mechanism for the dyad to improve performance. Our model predicts higher internal forces with haptic communication, which have previously been observed. Additional testable hypotheses emerge from the model and create a promising future means to transfer human-human dyad behaviors to human-robot teams.
more »
« less
- Award ID(s):
- 1825931
- PAR ID:
- 10293805
- Date Published:
- Journal Name:
- 2021 IEEE World Haptics Conference
- Page Range / eLocation ID:
- 433 to 438
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract The extent to which hand dominance may influence how each agent contributes to inter-personal coordination remains unknown. In the present study, right-handed human participants performed object balancing tasks either in dyadic conditions with each agent using one hand (left or right), or in bimanual conditions where each agent performed the task individually with both hands. We found that object load was shared between two hands more asymmetrically in dyadic than single-agent conditions. However, hand dominance did not influence how two hands shared the object load. In contrast, hand dominance was a major factor in modulating hand vertical movement speed. Furthermore, the magnitude of internal force produced by two hands against each other correlated with the synchrony between the two hands’ movement in dyads. This finding supports the important role of internal force in haptic communication. Importantly, both internal force and movement synchrony were affected by hand dominance of the paired participants. Overall, these results demonstrate, for the first time, that pairing of one dominant and one non-dominant hand may promote asymmetrical roles within a dyad during joint physical interactions. This appears to enable the agent using the dominant hand to actively maintain effective haptic communication and task performance.more » « less
-
As humans and robots start to collaborate in close proximity, robots are tasked to perceive, comprehend, and anticipate human partners' actions, which demands a predictive model to describe how humans collaborate with each other in joint actions. Previous studies either simplify the collaborative task as an optimal control problem between two agents or do not consider the learning process of humans during repeated interaction. This idyllic representation is thus not able to model human rationality and the learning process. In this paper, a bounded-rational and game-theoretical human cooperative model is developed to describe the cooperative behaviors of the human dyad. An experiment of a joint object pushing collaborative task was conducted with 30 human subjects using haptic interfaces in a virtual environment. The proposed model uses inverse optimal control (IOC) to model the reward parameters in the collaborative task. The collected data verified the accuracy of the predicted human trajectory generated from the bounded rational model excels the one with a fully rational model. We further provide insight from the conducted experiments about the effects of leadership on the performance of human collaboration.more » « less
-
Abstract Automation is pervasive, and humans often collaborate with it to perform various tasks. With technological advancements, it has become increasingly important to understand the characteristics of complex teams composed of multiple humans and multiple agents. In this study, we examined various team-level metrics in multioperator, multiagent teams, including trust, communication, and task completion time (TCT). We conducted a human subjects experiment with 30 teams, each consisting of 2 human and 2 agent players, performing collaborative block-moving tasks. Each team completed 10 trials under 3 agent reliability pairing conditions: perfect (both agents had 100% reliability), mixed (1 agent had 100%, the other 50%), and imperfect (both agents had 50% reliability). Humans searched for target-colored blocks and issued commands to the agents, which followed predetermined logic to move the blocks to the drop zone. Participants’ trust ratings for each teammate and for the team were collected after each trial. From the experimental data, we quantified several team metrics: team-level trust in each referent (each teammate and the team), divergence of trust in each referent, team communication frequency, commands per block delivery, divergence of team communication, and TCT. We evaluated the effect of agent reliability pairing on each of these metrics and explored the associations between them. The results indicate strong interdependence: Shorter TCT is associated with higher team-level trust in team, greater agreement in trust ratings, and more effective, convergent communication patterns shared by the humans. This study offers important guidelines for evaluating human–agent teams at a higher, team-level perspective.more » « less
-
Enabling efficient communication in artificial agents brings us closer to machines that can cooperate with each other and with human partners. Hand-engineered approaches have substantial limitations, leading to increased interest in methods for communication to emerge autonomously between artificial agents. Most of the research in the field explores unsituated communication in one-step referential tasks. The tasks are not temporally interactive and lack time pressures typically present in natural communication and language learning. In these settings, agents can successfully learn what to communicate but not when or whether to communicate. Here, we extend the literature by assessing emergence of communication between reinforcement learning agents in a temporally interactive, cooperative task of navigating a gridworld environment. We show that, through multi-step interactions, agents develop just-in-time messaging protocols that enable them to successfully solve the task. With memory—which provides flexibility around message timing—agent pairs converge to a look-ahead communication protocol, finding an optimal solution to the task more quickly than without memory. Lastly, we explore situated communication, enabling the acting agent to choose when and whether to communicate. With the opportunity cost of forgoing an action to communicate, the acting agent learns to solicit information sparingly, in line with the Gricean Maxim of quantity. Our results point towards the importance of studying language emergence through situated communication in multi-step interactions.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Conference Paper:
- https://doi.org/10.1109/WHC49131.2021.9517210
