Forming Real-World Human-Robot Cooperation for Tasks With General Goal
This work is significant for human-robot interaction researchers and practitioners, as it tackles the realistic problem of humans having general rather than specific goals, which can lead to frustration and reduced team performance.
This paper addresses human-robot cooperation where humans initially have only a general goal, which needs to be interactively clarified into a specific goal during cooperation. The proposed Evolutionary Value Learning approach, using State-based Multivariate Bayesian Inference and goal specificity features, enables the robot to actively enhance this specification process and find cooperative policies. The method achieved faster goal specification and better team performance in a dynamic ball balancing task with human subjects compared to existing methods.
In human-robot cooperation, the robot cooperates with humans to accomplish the task together. Existing approaches assume the human has a specific goal during the cooperation, and the robot infers and acts toward it. However, in real-world environments, a human usually only has a general goal (e.g., general direction or area in motion planning) at the beginning of the cooperation, which needs to be clarified to a specific goal (i.e., an exact position) during cooperation. The specification process is interactive and dynamic, which depends on the environment and the partner's behavior. The robot that does not consider the goal specification process may cause frustration to the human partner, elongate the time to come to an agreement, and compromise team performance. This work presents the Evolutionary Value Learning approach to model the dynamics of the goal specification process with State-based Multivariate Bayesian Inference and goal specificity-related features. This model enables the robot to enhance the process of the human's goal specification actively and find a cooperative policy in a Deep Reinforcement Learning manner. Our method outperforms existing methods with faster goal specification processes and better team performance in a dynamic ball balancing task with real human subjects.