The collaborative mind: intention reading and trust in human-robot interaction

Abstract

Robots are likely to become important social actors in our future and so require more human-like ways of assisting us. We state that collaboration between humans and robots is fostered by two cognitive skills: intention reading and trust. An agent possessing these abilities would be able to infer the non-verbal intentions of others and to evaluate how likely they are to achieve their goals, jointly understanding what kind and which degree of collaboration they require. For this reason, we propose a developmental artificial cognitive architecture that integrates unsupervised machine learning and probabilistic models to imbue a humanoid robot with intention reading and trusting capabilities. Our experimental results show that the synergistic implementation of these cognitive skills enable the robot to cooperate in a meaningful way, with the intention reading model allowing a correct goal prediction and with the trust component enhancing the likelihood of a positive outcome for the task.

Keywords: Artificial Intelligence; Human-Centered Computing; Human-Computer Interaction.

Graphical abstract

Figure 1

Overview of the mechanisms leading to joint action Expanded from Bauer et al. (2008) through the addition of trust estimation.

Figure 2

The proposed artificial cognitive architecture which integrates intention reading and trust mechanisms for the purpose of collaborative intelligence Please refer to the Transparent methods section of the Supplemental information for the detail of each component.

Figure 3

Experimental setup for the block building game (A) Schematic of the playing table, depicting the position of the 4 colored blocks: blue (B), orange (O), red (R), and green (G). (B) The 8 admissible block sequences obtained by picking blocks alternatively from each side. These sequences are the goals for this scenario.

Figure 4

Comparison of the collaboration success rates with and without the trust model for each of the simulated informants

Figure 5

Variation of the opinion value at each turn of interaction for the 3 deterministic simulated informants ($H_1$, $H_2$, and $H_3$), initialized with a trusting BN When $O\left(H\right)$ becomes less than 0, the robot starts distrusting the informant and taking more control on the task.

Figure 6

Opinion dynamics for the stochastic human $H_4$ (50% success rate) during its first 10 iterations

Figure 7

Opinion dynamics for the stochastic human $H_5$ (80% success rate) during 10 iterations

Figure 8

Opinion dynamics for the stochastic human $H_6$ (20% success rate) during 10 iterations

Figure 9

Opinion dynamics for the stochastic human $H_7$ (80% success rate, against a naively distrusting BN) during 10 iterations