Generating Explanations for Autonomous Robots: a Systematic Review

Building trust between humans and robots has long interested the robotics community. Various studies have aimed to clarify the factors that influence the development of user trust. In Human-Robot Interaction (HRI) environments, a critical aspect of trust development is the robot's ability to make its behavior understandable. The concept of an eXplainable Autonomous Robot (XAR) addresses this requirement. However, giving a robot self-explanatory abilities is a complex task. Robot behavior includes multiple skills and diverse subsystems. This complexity led to research into a wide range of methods for generating explanations about robot behavior. This paper presents a systematic literature review that analyzes existing strategies for generating explanations in robots and studies the current XAR trends. Results indicate promising advancements in explainability systems. However, these systems are still unable to fully cover the complex behavior of autonomous robots. Furthermore, we also identify a lack of consensus on the theoretical concept of explainability, and the need for a robust methodology to assess explainability methods and tools has been identified.

Enhancing Robot Explanation Capabilities through Vision-Language Models: a Preliminary Study by Interpreting Visual Inputs for Improved Human-Robot Interaction

This paper presents an improved system based on our prior work, designed to create explanations for autonomous robot actions during Human-Robot Interaction (HRI). Previously, we developed a system that used Large Language Models (LLMs) to interpret logs and produce natural language explanations. In this study, we expand our approach by incorporating Vision-Language Models (VLMs), enabling the system to analyze textual logs with the added context of visual input. This method allows for generating explanations that combine data from the robot's logs and the images it captures. We tested this enhanced system on a basic navigation task where the robot needs to avoid a human obstacle. The findings from this preliminary study indicate that adding visual interpretation improves our system's explanations by precisely identifying obstacles and increasing the accuracy of the explanations provided.

Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models

The deployment of autonomous agents in environments involving human interaction has increasingly raised security concerns. Consequently, understanding the circumstances behind an event becomes critical, requiring the development of capabilities to justify their behaviors to non-expert users. Such explanations are essential in enhancing trustworthiness and safety, acting as a preventive measure against failures, errors, and misunderstandings. Additionally, they contribute to improving communication, bridging the gap between the agent and the user, thereby improving the effectiveness of their interactions. This work presents an accountability and explainability architecture implemented for ROS-based mobile robots. The proposed solution consists of two main components. Firstly, a black box-like element to provide accountability, featuring anti-tampering properties achieved through blockchain technology. Secondly, a component in charge of generating natural language explanations by harnessing the capabilities of Large Language Models (LLMs) over the data contained within the previously mentioned black box. The study evaluates the performance of our solution in three different scenarios, each involving autonomous agent navigation functionalities. This evaluation includes a thorough examination of accountability and explainability metrics, demonstrating the effectiveness of our approach in using accountable data from robot actions to obtain coherent, accurate and understandable explanations, even when facing challenges inherent in the use of autonomous agents in real-world scenarios.

Integration of Large Language Models within Cognitive Architectures for Autonomous Robots

The usage of Large Language Models (LLMs) has increased recently, not only due to the significant improvements in their accuracy but also because of the use of the quantization that allows running these models without intense hardware requirements. As a result, the LLMs have proliferated. It implies the creation of a great variety of LLMs with different capabilities. This way, this paper proposes the integration of LLMs in cognitive architectures for autonomous robots. Specifically, we present the design, development and deployment of the llama\_ros tool that allows the easy use and integration of LLMs in ROS 2-based environments, afterward integrated with the state-of-the-art cognitive architecture MERLIN2 for updating a PDDL-based planner system. This proposal is evaluated quantitatively and qualitatively, measuring the impact of incorporating the LLMs in the cognitive architecture.

Using Large Language Models for Interpreting Autonomous Robots Behaviors

The deployment of autonomous robots in various domains has raised significant concerns about their trustworthiness and accountability. This study explores the potential of Large Language Models (LLMs) in analyzing ROS 2 logs generated by autonomous robots and proposes a framework for log analysis that categorizes log files into different aspects. The study evaluates the performance of three different language models in answering questions related to StartUp, Warning, and PDDL logs. The results suggest that GPT 4, a transformer-based model, outperforms other models, however, their verbosity is not enough to answer why or how questions for all kinds of actors involved in the interaction.