Factored Reasoning with Inner Speech and Persistent Memory for Evidence-Grounded Human-Robot Interaction

Dialogue-based human-robot interaction requires robot cognitive assistants to maintain persistent user context, recover from underspecified requests, and ground responses in external evidence, while keeping intermediate decisions verifiable. In this paper we introduce JANUS, a cognitive architecture for assistive robots that models interaction as a partially observable Markov decision process and realizes control as a factored controller with typed interfaces. To this aim, Janus (i) decomposes the overall behavior into specialized modules, related to scope detection, intent recognition, memory, inner speech, query generation, and outer speech, and (ii) exposes explicit policies for information sufficiency, execution readiness, and tool grounding. A dedicated memory agent maintains a bounded recent-history buffer, a compact core memory, and an archival store with semantic retrieval, coupled through controlled consolidation and revision policies. Models inspired by the notion of inner speech in cognitive theories provide a control-oriented internal textual flow that validates parameter completeness and triggers clarification before grounding, while a faithfulness constraint ties robot-to-human claims to an evidence bundle combining working context and retrieved tool outputs. We evaluate JANUS through module-level unit tests in a dietary assistance domain grounded on a knowledge graph, reporting high agreement with curated references and practical latency profiles. These results support factored reasoning as a promising path to scalable, auditable, and evidence-grounded robot assistance over extended interaction horizons.

A Social Robot with Inner Speech for Dietary Guidance

We explore the use of inner speech as a mechanism to enhance transparency and trust in social robots for dietary advice. In humans, inner speech structures thought processes and decision-making; in robotics, it improves explainability by making reasoning explicit. This is crucial in healthcare scenarios, where trust in robotic assistants depends on both accurate recommendations and human-like dialogue, which make interactions more natural and engaging. Building on this, we developed a social robot that provides dietary advice, and we provided the architecture with inner speech capabilities to validate user input, refine reasoning, and generate clear justifications. The system integrates large language models for natural language understanding and a knowledge graph for structured dietary information. By making decisions more transparent, our approach strengthens trust and improves human-robot interaction in healthcare. We validated this by measuring the computational efficiency of our architecture and conducting a small user study, which assessed the reliability of inner speech in explaining the robot's behavior.

Robot's Inner Speech Effects on Trust and Anthropomorphic Cues in Human-Robot Cooperation

Inner Speech is an essential but also elusive human psychological process which refers to an everyday covert internal conversation with oneself. We argue that programming a robot with an overt self-talk system, which simulates human inner speech, might enhance human trust by improving robot transparency and anthropomorphism. For this reasons, this work aims to investigate if robot's inner speech, here intended as overt self-talk, affects human trust and anthropomorphism when human and robot cooperate. A group of participants was engaged in collaboration with the robot. During cooperation, the robot talks to itself. To evaluate if the robot's inner speech influences human trust, two questionnaires were administered to each participant before (pre-test) and after (post-test) the cooperative session with the robot. Preliminary results evidenced differences between the answers of participants in the pre-test and post-test assessment, suggesting that robot's inner speech influences human trust. Indeed, participant's levels of trust and perception of robot anthropomorphic features increase after the experimental interaction with the robot.