No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
What Would I Do If…? Promoting Understanding in HRI through Real-Time Explanations in the Wild
... Knowing the causal structure of a system provides a significant advantage in many robotics applications. Indeed, research in causal inference, which includes causal discovery and reasoning, has gained increasing attention in recent robotics literature [3,4,5,6,7,8,9,10,11,12,13,14,15]. However, to the best of our knowledge, no prior work has explored causal inference for robot decision-making in the context of dynamic environments and human-aware navigation. ...
... PCMCI and F-PCMCI have been used to establish causal models for underwater robots navigating toward target positions [5] and to predict human spatial interactions in social robotics [6,7]. Moreover, causality-based approaches have been explored in various robotics domains, including robot imitation learning, manipulation and explainable HRI [8,9,10,14,15]. ...
The growing integration of robots in shared environments -- such as warehouses, shopping centres, and hospitals -- demands a deep understanding of the underlying dynamics and human behaviours, including how, when, and where individuals engage in various activities and interactions. This knowledge goes beyond simple correlation studies and requires a more comprehensive causal analysis. By leveraging causal inference to model cause-and-effect relationships, we can better anticipate critical environmental factors and enable autonomous robots to plan and execute tasks more effectively. To this end, we propose a novel causality-based decision-making framework that reasons over a learned causal model to predict battery usage and human obstructions, understanding how these factors could influence robot task execution. Such reasoning framework assists the robot in deciding when and how to complete a given task. To achieve this, we developed also PeopleFlow, a new Gazebo-based simulator designed to model context-sensitive human-robot spatial interactions in shared workspaces. PeopleFlow features realistic human and robot trajectories influenced by contextual factors such as time, environment layout, and robot state, and can simulate a large number of agents. While the simulator is general-purpose, in this paper we focus on a warehouse-like environment as a case study, where we conduct an extensive evaluation benchmarking our causal approach against a non-causal baseline. Our findings demonstrate the efficacy of the proposed solutions, highlighting how causal reasoning enables autonomous robots to operate more efficiently and safely in dynamic environments shared with humans.
The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.
Recent applications of autonomous agents and robots have brought attention to crucial trust-related challenges associated with the current generation of artificial intelligence (AI) systems. AI systems based on the connectionist deep learning neural network approach lack capabilities of explaining their decisions and actions to others, despite their great successes. Without symbolic interpretation capabilities, they are ’black boxes’, which renders their choices or actions opaque, making it difficult to trust them in safety-critical applications. The recent stance on the explainability of AI systems has witnessed several approaches to eXplainable Artificial Intelligence (XAI); however, most of the studies have focused on data-driven XAI systems applied in computational sciences. Studies addressing the increasingly pervasive goal-driven agents and robots are sparse at this point in time. This paper reviews approaches on explainable goal-driven intelligent agents and robots, focusing on techniques for explaining and communicating agents’ perceptual functions (e.g., senses, vision) and cognitive reasoning (e.g., beliefs, desires, intention, plans, and goals) with humans in the loop. The review highlights key strategies that emphasize transparency, understandability, and continual learning for explainability. Finally, the paper presents requirements for explainability and suggests a road map for the possible realization of effective goal-driven explainable agents and robots.
In recent years, the ability of intelligent systems to be understood by developers and users has received growing attention. This holds in particular for social robots, which are supposed to act autonomously in the vicinity of human users and are known to raise peculiar, often unrealistic attributions and expectations. However, explainable models that, on the one hand, allow a robot to generate lively and autonomous behavior and, on the other, enable it to provide human-compatible explanations for this behavior are missing. In order to develop such a self-explaining autonomous social robot, we have equipped a robot with own needs that autonomously trigger intentions and proactive behavior, and form the basis for understandable self-explanations. Previous research has shown that undesirable robot behavior is rated more positively after receiving an explanation. We thus aim to equip a social robot with the capability to automatically generate verbal explanations of its own behavior, by tracing its internal decision-making routes. The goal is to generate social robot behavior in a way that is generally interpretable, and therefore explainable on a socio-behavioral level increasing users' understanding of the robot's behavior. In this article, we present a social robot interaction architecture, designed to autonomously generate social behavior and self-explanations. We set out requirements for explainable behavior generation architectures and propose a socio-interactive framework for behavior explanations in social human-robot interactions that enables explaining and elaborating according to users' needs for explanation that emerge within an interaction. Consequently, we introduce an interactive explanation dialog flow concept that incorporates empirically validated explanation types. These concepts are realized within the interaction architecture of a social robot, and integrated with its dialog processing modules. We present the components of this interaction architecture and explain their integration to autonomously generate social behaviors as well as verbal self-explanations. Lastly, we report results from a qualitative evaluation of a working prototype in a laboratory setting, showing that (1) the robot is able to autonomously generate naturalistic social behavior, and (2) the robot is able to verbally self-explain its behavior to the user in line with users' requests.
Interpretable machine learning aims at unveiling the reasons behind predictions returned by uninterpretable classifiers. One of the most valuable types of explanation consists of counterfactuals. A counterfactual explanation reveals what should have been different in an instance to observe a diverse outcome. For instance, a bank customer asks for a loan that is rejected. The counterfactual explanation consists of what should have been different for the customer in order to have the loan accepted. Recently, there has been an explosion of proposals for counterfactual explainers. The aim of this work is to survey the most recent explainers returning counterfactual explanations. We categorize explainers based on the approach adopted to return the counterfactuals, and we label them according to characteristics of the method and properties of the counterfactuals returned. In addition, we visually compare the explanations, and we report quantitative benchmarking assessing minimality, actionability, stability, diversity, discriminative power, and running time. The results make evident that the current state of the art does not provide a counterfactual explainer able to guarantee all these properties simultaneously.
Socially assistive robots have the potential to augment and enhance therapist’s effectiveness in repetitive tasks such as cognitive therapies. However, their contribution has generally been limited as domain experts have not been fully involved in the entire pipeline of the design process as well as in the automatisation of the robots’ behaviour. In this article, we present aCtive leARning agEnt aSsiStive bEhaviouR (CARESSER), a novel framework that actively learns robotic assistive behaviour by leveraging the therapist’s expertise (knowledge-driven approach) and their demonstrations (data-driven approach). By exploiting that hybrid approach, the presented method enables in situ fast learning, in a fully autonomous fashion, of personalised patient-specific policies. With the purpose of evaluating our framework, we conducted two user studies in a daily care centre in which older adults affected by mild dementia and mild cognitive impairment ( N = 22) were requested to solve cognitive exercises with the support of a therapist and later on of a robot endowed with CARESSER. Results showed that: (i) the robot managed to keep the patients’ performance stable during the sessions even more so than the therapist; (ii) the assistance offered by the robot during the sessions eventually matched the therapist’s preferences. We conclude that CARESSER, with its stakeholder-centric design, can pave the way to new AI approaches that learn by leveraging human–human interactions along with human expertise, which has the benefits of speeding up the learning process, eliminating the need for the design of complex reward functions, and finally avoiding undesired states.
Advanced communication protocols are critical for the coexistence of autonomous robots and humans. Thus, the development of explanatory capabilities in robots is an urgent first step toward realizing autonomous robots. This survey provides an overview of the various types of ‘explainability’ discussed in the machine learning literature. The definition of ‘explainability’ in the context of autonomous robots is then discussed by exploring the question: ‘What is an explanation?’ We further conduct a survey based on this definition and present relevant topics for future research in this paper.
Current developments in Artificial Intelligence (AI) led to a resurgence of Explainable AI (XAI). New methods are being researched to obtain information from AI systems in order to generate explanations for their output. However, there is an overall lack of valid and reliable evaluations of the effects on user's experience and behaviour of explanations. New XAI methods are often based on an intuitive notion what an effective explanation should be. Contrasting rule- and example-based explanations are two exemplary explanation styles. In this study we evaluated the effects of these two explanation styles on system understanding, persuasive power and task performance in the context of decision support in diabetes self-management. Furthermore, we provide three sets of recommendations based on our experience designing this evaluation to help improve future evaluations. Our results show that rule-based explanations have a small positive effect on system understanding, whereas both rule- and example-based explanations seem to persuade users in following the advice even when incorrect. Neither explanation improves task performance compared to no explanation. This can be explained by the fact that both explanation styles only provide details relevant for a single decision, not the underlying rational or causality. These results show the importance of user evaluations in assessing the current assumptions and intuitions on effective explanations.
This paper introduces a new research area called Explainable Robotics, which studies explainability in the context of human-robot interactions. The focus is on developing novel computational models, methods and algorithms for generating explanations that allow robots to operate at different levels of autonomy and communicate with humans in a trustworthy and human-friendly way. Individuals may need explanations during human-robot interactions for different reasons, which depend heavily on the context and human users involved. Therefore, the research challenge is identifying what needs to be explained at each level of autonomy and how these issues should be explained to different individuals. The paper presents the case for Explainable Robotics using a scenario involving the provision of medical health care to elderly patients with dementia with the help of technology. The paper highlights the main research challenges of Explainable Robotics. The first challenge is the need for new algorithms for generating explanations that use past experiences, analogies and real-time data to adapt to particular audiences and purposes. The second research challenge is developing novel computational models of situational and learned trust and new algorithms for the real-time sensing of trust. Finally, more research is needed to understand whether trust can be used as a control variable in Explainable Robotics.
There has been much discussion of the right to explanation in the EU General Data Protection Regulation, and its existence, merits, and disadvantages. Implementing a right to explanation that opens the black box of algorithmic decision-making faces major legal and technical barriers. Explaining the functionality of complex algorithmic decision-making systems and their rationale in specific cases is a technically challenging problem. Some explanations may offer little meaningful information to data subjects, raising questions around their value. Explanations of automated decisions need not hinge on the general public understanding how algorithmic systems function. Even though such interpretability is of great importance and should be pursued, explanations can, in principle, be offered without opening the black box. Looking at explanations as a means to help a data subject act rather than merely understand, one could gauge the scope and content of explanations according to the specific goal or action they are intended to support. From the perspective of individuals affected by automated decision-making, we propose three aims for explanations: (1) to inform and help the individual understand why a particular decision was reached, (2) to provide grounds to contest the decision if the outcome is undesired, and (3) to understand what would need to change in order to receive a desired result in the future, based on the current decision-making model. We assess how each of these goals finds support in the GDPR. We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims. These counterfactual explanations describe the smallest change to the world that can be made to obtain a desirable outcome, or to arrive at the closest possible world, without needing to explain the internal logic of the system.
There has been a recent resurgence in the area of explainable artificial intelligence as researchers and practitioners seek to provide more transparency to their algorithms. Much of this research is focused on explicitly explaining decisions or actions to a human observer, and it should not be controversial to say that, if these techniques are to succeed, the explanations they generate should have a structure that humans accept. However, it is fair to say that most work in explainable artificial intelligence uses only the researchers' intuition of what constitutes a `good' explanation. There exists vast and valuable bodies of research in philosophy, psychology, and cognitive science of how people define, generate, select, evaluate, and present explanations. This paper argues that the field of explainable artificial intelligence should build on this existing research, and reviews relevant papers from philosophy, cognitive psychology/science, and social psychology, which study these topics. It draws out some important findings, and discusses ways that these can be infused with work on explainable artificial intelligence.
For social robots to be able to operate in unstructured public spaces, they need to be able to gauge complex factors such as human-robot engagement and inter-person social groups, and be able to decide how and with whom to interact. Additionally, such robots should be able to explain their decisions after the fact, to improve accountability and confidence in their behavior. To address this, we present a two-layered proactive system that extracts high-level social features from low-level perceptions and uses these features to make high-level decisions regarding the initiation and maintenance of human robot interactions. With this system outlined, the primary focus of this work is then a novel method to generate counterfactual explanations in response to a variety of contrastive queries. We provide an early proof of concept to illustrate how these explanations can be generated by leveraging the two-layer system.
This paper presents an exploration of the role of explanations provided by robots in enhancing transparency during human-robot interaction (HRI). We conducted a study with 85 participants to investigate the impact of different types and timings of explanations on transparency. In particular, we tested different conditions: (1) no explanations, (2) short explanations, (3) detailed explanations, (4) short explanations for unexpected robot actions, and (5) detailed explanations for unexpected robot actions. We used the Human-Robot Interaction Video Sequencing Task (HRIVST) metric to evaluate legibility and predictability. The preliminary results suggest that providing a short explanation is sufficient to improve transparency in HRI. The HRIVST score for short explanations is higher and very close to the score for detailed explanations of unexpected robot actions. This work contributes to the field by highlighting the importance of tailored explanations to enhance the mutual understanding between humans and robots.
This paper presents an exploration of the role of explanations provided by robots in enhancing transparency during human-robot interaction (HRI). We conducted a study with 85 participants to investigate the impact of different types and timings of explanations on transparency. In particular, we tested different conditions: (1) no explanations, (2) short explanations, (3) detailed explanations, (4) short explanations for unexpected robot actions, and (5) detailed explanations for unexpected robot actions. We used the Human-Robot Interaction Video Sequencing Task (HRIVST) metric to evaluate legibility and predictability. The preliminary results suggest that providing a short explanation is sufficient to improve transparency in HRI. The HRIVST score for short explanations is higher and very close to the score for detailed explanations of unexpected robot actions. This work contributes to the field by highlighting the importance of tailored explanations to enhance the mutual understanding between humans and robots.
Deep reinforcement learning has shown useful in the field of robotics but the black-box nature of deep neural networks impedes the applicability of deep reinforcement learning agents for real-world tasks. This is addressed in the field of explainable artificial intelligence, by developing explanation methods that aim to explain such agents to humans. Model trees as surrogate models have proven useful for producing explanations for black-box models used in real-world robotic applications, in particular, due to their capability of providing explanations in real time. In this paper, we provide an overview and analysis of available methods for building model trees for explaining deep reinforcement learning agents solving robotics tasks. We find that multiple outputs are important for the model to be able to grasp the dependencies of coupled output features, i.e. actions. Additionally, our results indicate that introducing domain knowledge via a hierarchy among the input features during the building process results in higher accuracies and a faster building process.
We propose a general method for generating counterfactual explanations (CFXs) for a range of Bayesian Network Classifiers (BCs), e.g. single- or multi-label, binary or multidimensional. We focus on explanations built from relations of (critical and potential) influence between variables, indicating the reasons for classifications, rather than any probabilistic information. We show by means of a theoretical analysis of CFXs’ properties that they serve the purpose of indicating (potentially) pivotal factors in the classification process, whose absence would give rise to different classifications. We then prove empirically for various BCs that CFXs provide useful information in real world settings, e.g. when race plays a part in parole violation prediction, and show that they have inherent advantages over existing explanation methods in the literature.
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.
In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally varound the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.
Towards a rigorous science of inter-pretable machine learning
- F Doshi-Velez
- B Kim