Improved human–robot team performance through cross-training, an approach inspired by human team training practices

@article{Nikolaidis2015ImprovedHT,
  title={Improved human–robot team performance through cross-training, an approach inspired by human team training practices},
  author={Stefanos Nikolaidis and Przemyslaw A. Lasota and Ramya Ramakrishnan and Julie A. Shah},
  journal={The International Journal of Robotics Research},
  year={2015},
  volume={34},
  pages={1711 - 1730}
}
We design and evaluate a method of human–robot cross-training, a validated and widely used strategy for the effective training of human teams. Cross-training is an interactive planning method in which team members iteratively switch roles with one another to learn a shared plan for the performance of a collaborative task. We first present a computational formulation of the robot mental model, which encodes the sequence of robot actions necessary for task completion and the expectations of the… 
Human-robot mutual adaptation in collaborative tasks: Models and experiments
TLDR
The Bounded-Memory Adaptation Model is proposed, which is a probabilistic finite-state controller that captures human adaptive behaviors under a bounded-memory assumption, enabling the robot to guide adaptable participants towards a better way of completing the task.
Behavior Explanation as Intention Signaling in Human-Robot Teaming
  • Ze Gong, Yu Zhang
  • Computer Science
    2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)
  • 2018
TLDR
This work proposes an approach to explaining robot behavior as intention signaling using natural language sentences and proves that intention signaling can help achieve better teaming by reducing criticism on robot behavior that may appear undesirable but is otherwise required, e.g., due to information asymmetry.
Valuable Robotic Teammates: Algorithms That Reason About the Multiple Dimensions of Human-Robot Teamwork
TLDR
Empirical findings and an algorithm that enables robots to understand the human's intent, communicate their own intent, display effortful behavior, and provide help to optimize the team's task performance are presented.
Hierarchical robot learning for physical collaboration between humans and robots
TLDR
A hierarchical robot learning approach that includes two learning hierarchies for HRC tasks, which enables the robot to adaptively coordinate with a human and produce an active contribution to the HRC tasks.
A game-theoretic approach for adaptive action selection in close proximity human-robot-collaboration
TLDR
A framework based on game theory is presented that allows robots to choose appropriate actions with respect to the action of human coworkers when collaborating in close proximity and holds as a proof-of-concept of the proposed HRC-game model.
Building a Bridge with a Robot: A System for Collaborative On-table Task Execution
TLDR
This paper presents a system for human-robot collaboration for on-table tasks and uses the system to implement five action-selection strategies for the robot: proactive, autonomous, reactive, human-requested and human-commands.
A Survey of Robot Learning Strategies for Human-Robot Collaboration in Industrial Settings
TLDR
A novel taxonomy of levels of interaction between humans and robots along the lines of SAEs guidelines for autonomous vehicles is introduced in response to a need for standard definitions and evolving nature of the field.
Hybrid Human Motion Prediction for Action Selection Within Human-Robot Collaboration
TLDR
Experimental evaluation shows how the proposed prediction approach can be successfully integrated into a game theory based action selection framework.
How to be Helpful? Implementing Supportive Behaviors for Human-Robot Collaboration
TLDR
This work presents a collaborative system capable of assisting the human partner with a variety of supportive behaviors in spite of its limited perceptual and manipulation capabilities and incomplete model of the task.
Real-time recognition of team behaviors by multisensory graph-embedded robot learning
TLDR
This article introduces a novel representation learning approach to recognizing team intent awareness in real-time, based upon both individual human activities and the relationship between human peers in the team, and designs a new algorithm to efficiently solve the formulated regularized optimization problem.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 50 REFERENCES
Human-Robot Interactive Planning using Cross-Training: A Human Team Training Approach
TLDR
A novel framework for applying prior art in Shared Mental Models (SMMs) to promote eective human-robot teaming and shows that cross-training, a common practice used for improving human team shared mental models, yields statistically signicant improvements in convergence of the computational teaming model.
Improved human-robot team performance using Chaski, A human-inspired plan execution system
TLDR
Chaski is a task-level executive that enables a robot to collaboratively execute a shared plan with a person, and it is shown that Chaski reduces the human's idle time by 85%, a statistically significant difference that supports the hypothesis that human-robot team performance is improved when a robot emulates the effective coordination behaviors observed in human teams.
Effects of anticipatory action on human-robot teamwork: Efficiency, fluency, and perception of team
  • Guy Hoffman, C. Breazeal
  • Psychology, Computer Science
    2007 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI)
  • 2007
TLDR
This work proposes an adaptive action selection mechanism for a robotic teammate, making anticipatory decisions based on the confidence of their validity and their relative risk, and predicts an improvement in task efficiency and fluency compared to a purely reactive process.
Training Adaptive Teams
TLDR
Although cross-training has adaptive benefits, it is suggested that process-oriented approaches, such as perturbation training, can lead to more adaptive teams.
Teachable robots: Understanding human teaching behavior to build more effective robot learners
TLDR
The importance of understanding the human-teacher/robot-learner partnership in order to design algorithms that support how people want to teach and simultaneously improve the robot's learning behavior is demonstrated.
Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance
TLDR
The importance of understanding the human-teacher/robot-learner system as a whole in order to design algorithms that support how people want to teach while simultaneously improving the robot's learning performance is demonstrated.
Natural methods for robot task learning: instructive demonstrations, generalization and practice
TLDR
An approach for teaching robots that relies on the key features and the general approach people use when teaching each other: first give a demonstration, then allow the learner to refine the acquired capabilities by practicing under the teacher's supervision, involving a small number of trials.
Robot Learning From Demonstration
TLDR
This work has shown that incorporating a task level direct learning component, which is non-model-based, in addition to the model-based planner, is useful in compensating for structural modeling errors and slow model learning.
Interactively shaping agents via human reinforcement: the TAMER framework
TLDR
Results from two domains demonstrate that lay users can train TAMER agents without defining an environmental reward function (as in an MDP) and indicate that human training within the TAMER framework can reduce sample complexity over autonomous learning algorithms.
Reinforcement learning from simultaneous human and MDP reward
TLDR
A novel algorithm is introduced that shares the same spirit as tamer+rl but learns simultaneously from both reward sources, enabling the human feedback to come at any time during the reinforcement learning process.
...
1
2
3
4
5
...