Search

We need to trust robots that use often opaque AI methods. They need to explain themselves to us, and we need to trust their explanation. In this regard, explainability plays a critical role in trustworthy autonomous decision-making to foster transparency and acceptance among end users, especially in complex autonomous driving. Recent advancements in Multi-Modal Large Language models (MLLMs) have shown promising potential in enhancing the explainability as a driving agent by producing control predictions along with natural language explanations. However, severe data scarcity due to expensive annotation costs and significant domain gaps between different datasets makes the development of a robust and generalisable system an extremely challenging task. Moreover, the prohibitively expensive training requirements of MLLM and the unsolved problem of catastrophic forgetting further limit their generalisability post-deployment. To address these challenges, we present RAG-Driver, a novel retrieval-augmented multi-modal large language model that leverages in-context learning for high-performance, explainable, and generalisable autonomous driving. By grounding in retrieved expert demonstration, we empirically validate that RAG-Driver achieves state-of-the-art performance in producing driving action explanations, justifications, and control signal prediction. More importantly, it exhibits exceptional zero-shot generalisation capabilities to unseen environments without further training endeavours., Comment: 14 pages, 6 figures

This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction. Given the scarcity and strong imbalance of data samples, we propose a self-supervision pipeline to infer representative and well-separated embeddings. Key aspects are interpretability and explainability; as such, we embed in our architecture attention mechanisms that can create spatial and temporal heatmaps on the scene graphs. We evaluate our system on the ROAD dataset against a fully-supervised approach, showing the superiority of our training regime., Comment: Accepted to the 2023 IEEE International Conference on Robotics and Automation (ICRA)

The provision of natural language explanations for the predictions of deep-learning-based vehicle controllers is critical as it enhances transparency and easy audit. In this work, a state-of-the-art (SOTA) prediction and explanation model is thoroughly evaluated and validated (as a benchmark) on the new Sense--Assess--eXplain (SAX). Additionally, we developed a new explainer model that improved over the baseline architecture in two ways: (i) an integration of part of speech prediction and (ii) an introduction of special token penalties. On the BLEU metric, our explanation generation technique outperformed SOTA by a factor of 7.7 when applied on the BDD-X dataset. The description generation technique is also improved by a factor of 1.3. Hence, our work contributes to the realisation of future explainable autonomous vehicles., Comment: Accepted to IV 2023

Corner case scenarios are an essential tool for testing and validating the safety of autonomous vehicles (AVs). As these scenarios are often insufficiently present in naturalistic driving datasets, augmenting the data with synthetic corner cases greatly enhances the safe operation of AVs in unique situations. However, the generation of synthetic, yet realistic, corner cases poses a significant challenge. In this work, we introduce a novel approach based on Heterogeneous Graph Neural Networks (HGNNs) to transform regular driving scenarios into corner cases. To achieve this, we first generate concise representations of regular driving scenes as scene graphs, minimally manipulating their structure and properties. Our model then learns to perturb those graphs to generate corner cases using attention and triple embeddings. The input and perturbed graphs are then imported back into the simulation to generate corner case scenarios. Our model successfully learned to produce corner cases from input scene graphs, achieving 89.9% prediction accuracy on our testing dataset. We further validate the generated scenarios on baseline autonomous driving methods, demonstrating our model's ability to effectively create critical situations for the baselines., Comment: The first two authors contributed equally to this work

The nature of explanations provided by an explainable AI algorithm has been a topic of interest in the explainable AI and human-computer interaction community. In this paper, we investigate the effects of natural language explanations' specificity on passengers in autonomous driving. We extended an existing data-driven tree-based explainer algorithm by adding a rule-based option for explanation generation. We generated auditory natural language explanations with different levels of specificity (abstract and specific) and tested these explanations in a within-subject user study (N=39) using an immersive physical driving simulation setup. Our results showed that both abstract and specific explanations had similar positive effects on passengers' perceived safety and the feeling of anxiety. However, the specific explanations influenced the desire of passengers to takeover driving control from the autonomous vehicle (AV), while the abstract explanations did not. We conclude that natural language auditory explanations are useful for passengers in autonomous driving, and their specificity levels could influence how much in-vehicle participants would wish to be in control of the driving activity.

In commentary driving, drivers verbalise their observations, assessments and intentions. By speaking out their thoughts, both learning and expert drivers are able to create a better understanding and awareness of their surroundings. In the intelligent vehicle context, automated driving commentary can provide intelligible explanations about driving actions, thereby assisting a driver or an end-user during driving operations in challenging and safety-critical scenarios. In this paper, we conducted a field study in which we deployed a research vehicle in an urban environment to obtain data. While collecting sensor data of the vehicle's surroundings, we obtained driving commentary from a driving instructor using the think-aloud protocol. We analysed the driving commentary and uncovered an explanation style; the driver first announces his observations, announces his plans, and then makes general remarks. He also makes counterfactual comments. We successfully demonstrated how factual and counterfactual natural language explanations that follow this style could be automatically generated using a transparent tree-based approach. Generated explanations for longitudinal actions (e.g., stop and move) were deemed more intelligible and plausible by human judges compared to lateral actions, such as lane changes. We discussed how our approach can be built on in the future to realise more robust and effective explainability for driver assistance as well as partial and conditional automation of driving functions.

In commentary driving, drivers verbalise their observations, assessments and intentions. By speaking out their thoughts, both learning and expert drivers are able to create a better understanding and awareness of their surroundings. In the intelligent vehicle context, automated driving commentary can provide intelligible explanations about driving actions, thereby assisting a driver or an end-user during driving operations in challenging and safety-critical scenarios. In this paper, we conducted a field study in which we deployed a research vehicle in an urban environment to obtain data. While collecting sensor data of the vehicle's surroundings, we obtained driving commentary from a driving instructor using the think-aloud protocol. We analysed the driving commentary and uncovered an explanation style; the driver first announces his observations, announces his plans, and then makes general remarks. He also makes counterfactual comments. We successfully demonstrated how factual and counterfactual natural language explanations that follow this style could be automatically generated using a transparent tree-based approach. Generated explanations for longitudinal actions (e.g., stop and move) were deemed more intelligible and plausible by human judges compared to lateral actions, such as lane changes. We discussed how our approach can be built on in the future to realise more robust and effective explainability for driver assistance as well as partial and conditional automation of driving functions., Comment: Presented in the 2022 IEEE Intelligent Vehicles Symposium

With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and understanding the outcomes of machine learning models. Despite this growing interest, existing works on interpretability and explanations have been mostly intended for expert users. Explanations for general users have been neglected in many usable and practical applications (e.g., image tagging, caption generation). It is important for non-technical users to understand features and how they affect an instance-specific prediction to satisfy the need for justification. In this paper, we propose a model-agnostic method for generating context-based explanations aiming for general users. We implement partial masking on segmented components to identify the contextual importance of each segment in scene classification tasks. We then generate explanations based on feature importance. We present visual and text-based explanations: (i) saliency map presents the pertinent components with a descriptive textual justification, (ii) visual map with a color bar graph showing the relative importance of each feature for a prediction. Evaluating the explanations using a user study (N = 50), we observed that our proposed explanation method visually outperformed existing gradient and occlusion based methods. Hence, our proposed explanation method could be deployed to explain models’ decisions to non-expert users in real-world applications.

With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and understanding the outcomes of machine learning models. Despite this growing interest, existing works on interpretability and explanations have been mostly intended for expert users. Explanations for general users have been neglected in many usable and practical applications (e.g., image tagging, caption generation). It is important for non-technical users to understand features and how they affect an instance-specific prediction to satisfy the need for justification. In this paper, we propose a model-agnostic method for generating context-based explanations aiming for general users. We implement partial masking on segmented components to identify the contextual importance of each segment in scene classification tasks. We then generate explanations based on feature importance. We present visual and text-based explanations: (i) saliency map presents the pertinent components with a descriptive textual justification, (ii) visual map with a color bar graph showing the relative importance of each feature for a prediction. Evaluating the explanations using a user study (N = 50), we observed that our proposed explanation method visually outperformed existing gradient and occlusion based methods. Hence, our proposed explanation method could be deployed to explain models’ decisions to non-expert users in real-world applications.

With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and understanding the outcomes of machine learning models. Despite this growing interest, existing works on interpretability and explanations have been mostly intended for expert users. Explanations for general users have been neglected in many usable and practical applications (e.g., image tagging, caption generation). It is important for non-technical users to understand features and how they affect an instance-specific prediction to satisfy the need for justification. In this paper, we propose a model-agnostic method for generating context-based explanations aiming for general users. We implement partial masking on segmented components to identify the contextual importance of each segment in scene classification tasks. We then generate explanations based on feature importance. We present visual and text-based explanations: (i) saliency map presents the pertinent components with a descriptive textual justification, (ii) visual map with a color bar graph showing the relative importance of each feature for a prediction. Evaluating the explanations using a user study (N = 50), we observed that our proposed explanation method visually outperformed existing gradient and occlusion based methods. Hence, our proposed explanation method could be deployed to explain models’ decisions to non-expert users in real-world applications.

The safe deployment of autonomous physical systems in real-world scenarios requires them to be explainable and trustworthy, especially in critical domains. In contrast with g€black-box' systems, explainable and trustworthy autonomous physical systems will lend themselves to easy assessments by system designers and regulators. This promises to pave ways for easy improvements that can lead to enhanced performance, and as well, increased public trust. In this one-day virtual workshop, we aim to gather a globally distributed group of researchers and practitioners to discuss the opportunities and social challenges in the design, implementation, and deployment of explainable and trustworthy autonomous physical systems, especially in a post-pandemic era. Interactions will be fostered through panel discussions and a series of spotlight talks. To ensure lasting impact of the workshop, we will conduct a pre-workshop survey which will examine the public perception of the trustworthiness of autonomous physical systems. Further, we will publish a summary report providing details about the survey as well as the identified challenges resulting from the workshop's panel discussions.

Third-party tracking allows companies to collect users' be-havioural data and track their activity across digital devices. This can put deep insights into users' private lives into the hands of strangers, and often happens without users' awareness or explicit consent. EU and UK data protection law, however, requires consent, both 1) to access and store information on users' devices and 2) to legitimate the processing of personal data as part of third-party tracking, as we analyse in this paper. This paper further investigates whether and to what extent consent is implemented in mobile apps. First, we analyse a representative sample of apps from the Google Play Store. We find that most apps engage in third-party tracking, but few obtained consent before doing so, indicating potentially widespread violations of EU and UK privacy law. Second, we examine the most common third-party tracking libraries in detail. While most acknowledge that they rely on app developers to obtain consent on their behalf, they typically fail to put in place robust measures to ensure this: disclosure of consent requirements is limited; default consent implementations are lacking; and compliance guidance is difficult to find, hard to read, and poorly maintained.

The safe deployment of autonomous physical systems in real-world scenarios requires them to be explainable and trustworthy, especially in critical domains. In contrast with g€black-box' systems, explainable and trustworthy autonomous physical systems will lend themselves to easy assessments by system designers and regulators. This promises to pave ways for easy improvements that can lead to enhanced performance, and as well, increased public trust. In this one-day virtual workshop, we aim to gather a globally distributed group of researchers and practitioners to discuss the opportunities and social challenges in the design, implementation, and deployment of explainable and trustworthy autonomous physical systems, especially in a post-pandemic era. Interactions will be fostered through panel discussions and a series of spotlight talks. To ensure lasting impact of the workshop, we will conduct a pre-workshop survey which will examine the public perception of the trustworthiness of autonomous physical systems. Further, we will publish a summary report providing details about the survey as well as the identified challenges resulting from the workshop's panel discussions.

Autonomous vehicles (AVs) have the potential to change the way we commute, travel, and transport our goods. The deployment of AVs in society, however, requires that people understand, accept, and trust them. Intelligible explanations can help different AV stakeholders to assess AVs' behaviours, and in turn, increase their confidence and foster trust. In a user study (N = 101), we examined different explanation types (based on investigatory queries) provided by an AV and their effect on people using the trust determinant factors. Our quantitative and qualitative analysis shows that explanations with causal attributions improved task performance and understanding when assessing driving events but did not directly improve perceived trust. This underlines the potential need for additional measures and research to enhance trust in AVs.

With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and understanding the outcomes of machine learning models. Despite this growing interest, existing works on interpretability and explanations have been mostly intended for expert users. Explanations for general users have been neglected in many usable and practical applications (e.g., image tagging, caption generation). It is important for non-technical users to understand features and how they affect an instance-specific prediction to satisfy the need for justification. In this paper, we propose a model-agnostic method for generating context-based explanations aiming for general users. We implement partial masking on segmented components to identify the contextual importance of each segment in scene classification tasks. We then generate explanations based on feature importance. We present visual and text-based explanations: (i) saliency map presents the pertinent components with a descriptive textual justification, (ii) visual map with a color bar graph showing the relative importance of each feature for a prediction. Evaluating the explanations using a user study (N = 50), we observed that our proposed explanation method visually outperformed existing gradient and occlusion based methods. Hence, our proposed explanation method could be deployed to explain models’ decisions to non-expert users in real-world applications.

With the increased use of machine learning in decision-making scenarios, there has been a growing interest in explaining and understanding the outcomes of machine learning models. Despite this growing interest, existing works on interpretability and explanations have been mostly intended for expert users. Explanations for general users have been neglected in many usable and practical applications (e.g., image tagging, caption generation). It is important for non-technical users to understand features and how they affect an instance-specific prediction to satisfy the need for justification. In this paper, we propose a model-agnostic method for generating context-based explanations aiming for general users. We implement partial masking on segmented components to identify the contextual importance of each segment in scene classification tasks. We then generate explanations based on feature importance. We present visual and text-based explanations: (i) saliency map presents the pertinent components with a descriptive textual justification, (ii) visual map with a color bar graph showing the relative importance of each feature for a prediction. Evaluating the explanations using a user study (N = 50), we observed that our proposed explanation method visually outperformed existing gradient and occlusion based methods. Hence, our proposed explanation method could be deployed to explain models’ decisions to non-expert users in real-world applications.

Third-party tracking allows companies to collect users' behavioural data and track their activity across digital devices. This can put deep insights into users' private lives into the hands of strangers, and often happens without users' awareness or explicit consent. EU and UK data protection law, however, requires consent, both 1) to access and store information on users' devices and 2) to legitimate the processing of personal data as part of third-party tracking, as we analyse in this paper. This paper further investigates whether and to what extent consent is implemented in mobile apps. First, we analyse a representative sample of apps from the Google Play Store. We find that most apps engage in third-party tracking, but few obtained consent before doing so, indicating potentially widespread violations of EU and UK privacy law. Second, we examine the most common third-party tracking libraries in detail. While most acknowledge that they rely on app developers to obtain consent on their behalf, they typically fail to put in place robust measures to ensure this: disclosure of consent requirements is limited; default consent implementations are lacking; and compliance guidance is difficult to find, hard to read, and poorly maintained., Comment: This paper will be presented at the 7th Symposium on Usable Privacy and Security (SOUPS 2021), 8th-10th August 2021

The automotive industry has witnessed an increasing level of development in the past decades; from manufacturing manually operated vehicles to manufacturing vehicles with a high level of automation. With the recent developments in Artificial Intelligence (AI), automotive companies now employ blackbox AI models to enable vehicles to perceive their environments and make driving decisions with little or no input from a human. With the hope to deploy autonomous vehicles (AV) on a commercial scale, the acceptance of AV by society becomes paramount and may largely depend on their degree of transparency, trustworthiness, and compliance with regulations. The assessment of the compliance of AVs to these acceptance requirements can be facilitated through the provision of explanations for AVs' behaviour. Explainability is therefore seen as an important requirement for AVs. AVs should be able to explain what they have 'seen', done, and might do in environments in which they operate. In this paper, we provide a comprehensive survey of the existing body of work around explainable autonomous driving. First, we open with a motivation for explanations by highlighting and emphasising the importance of transparency, accountability, and trust in AVs; and examining existing regulations and standards related to AVs. Second, we identify and categorise the different stakeholders involved in the development, use, and regulation of AVs and elicit their explanation requirements for AV. Third, we provide a rigorous review of previous work on explanations for the different AV operations (i.e., perception, localisation, planning, control, and system management). Finally, we identify pertinent challenges and provide recommendations, such as a conceptual framework for AV explainability. This survey aims to provide the fundamental knowledge required of researchers who are interested in explainability in AVs., Comment: Accepted for publication in IEEE Transactions on Intelligent Transportation Systems

We present Smooth Grad-CAM++, a technique which combines two recent techniques: SMOOTHGRAD and Grad-CAM++. Smooth Grad-CAM++ has the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance. We experimented with few images, and we discovered that Smooth Grad-CAM++ produced more visually sharp maps with larger number of salient pixels highlighted in the given input images when compared with other methods. Smooth Grad-CAM++ will give insight into what our deep CNN models (including models trained on medical scan or imagery) learn. Hence informing decisions on creating a representative training set., Comment: Presented at NeurIPS 2019 Workshop on Machine Learning for the Developing World. arXiv admin note: substantial text overlap with arXiv:1908.01224

Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have been a concern to computer vision researchers and decision makers. These deep models are often referred to as black box due to low comprehension of their internal workings. As an effort to developing explainable deep learning models, several methods have been proposed such as finding gradients of class output with respect to input image (sensitivity maps), class activation map (CAM), and Gradient based Class Activation Maps (Grad-CAM). These methods under perform when localizing multiple occurrences of the same class and do not work for all CNNs. In addition, Grad-CAM does not capture the entire object in completeness when used on single object images, this affect performance on recognition tasks. With the intention to create an enhanced visual explanation in terms of visual sharpness, object localization and explaining multiple occurrences of objects in a single image, we present Smooth Grad-CAM++ \footnote{Simple demo: http://35.238.22.135:5000/}, a technique that combines methods from two other recent techniques---SMOOTHGRAD and Grad-CAM++. Our Smooth Grad-CAM++ technique provides the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance at the inference level (model prediction process). After experimenting with few images, Smooth Grad-CAM++ produced more visually sharp maps with better localization of objects in the given input images when compared with other methods., Comment: Accepted in the Intelligent Systems Conference 2019

Urbanization is a common phenomenon in developing countries and it poses serious challenges when not managed effectively. Lack of proper planning and management may cause the encroachment of urban fabrics into reserved or special regions which in turn can lead to an unsustainable increase in population. Ineffective management and planning generally leads to depreciated standard of living, where physical hazards like traffic accidents and disease vector breeding become prevalent. In order to support urban planners and policy makers in effective planning and accurate decision making, we investigate urban land-use in sub-Saharan Africa. Land-use dynamics serves as a crucial parameter in current strategies and policies for natural resource management and monitoring. Focusing on Nairobi, we use an efficient deep learning approach with patch-based prediction to classify regions based on land-use from 2004 to 2018 on a quarterly basis. We estimate changes in land-use within this period, and using the Autoregressive Integrated Moving Average (ARIMA) model, our results forecast land-use for a given future date. Furthermore, we provide labelled land-use maps which will be helpful to urban planners.

Several changes occur in the brain in response to voluntary and involuntary activities performed by a person. The ability to retrieve data from the brain within a time space provides a basis for in-depth analyses that offer insight on what changes occur in the brain during its decision-making processes. In this work, we present the technical description and software implementation of an electroencephalographic (EEG) based communication system. We read EEG data in real-time with which we compute the likelihood that a voluntary eye blink has been made by a person and use the decision to trigger buttons on a user interface in order to produce text. Relevant texts are suggested using a modification of the T9 algorithm. Our results indicate that EEG-based technology can be effectively applied in facilitating speech for people with severe speech and muscular disabilities, providing a foundation for future work in the area., Comment: Conference paper

Agriculture is vital for human survival and remains a major driver of several economies around the world; more so in underdeveloped and developing economies. With increasing demand for food and cash crops, due to a growing global population and the challenges posed by climate change, there is a pressing need to increase farm outputs while incurring minimal costs. Previous machine vision technologies developed for selective weeding have faced the challenge of reliable and accurate weed detection. We present approaches for plant seedlings classification with a dataset that contains 4,275 images of approximately 960 unique plants belonging to 12 species at several growth stages. We compare the performances of two traditional algorithms and a Convolutional Neural Network (CNN), a deep learning technique widely applied to image recognition, for this task. Our findings show that CNN-driven seedling classification applications when used in farming automation has the potential to optimize crop yield and improve productivity and efficiency when designed appropriately., Comment: 5 pages

Web security has become an important subject; many companies and organizations are becoming more security conscious as they build web applications to render online services and increase web presence. Unfortunately, many of these web applications are still susceptible to threats as they lack strong immunity to malicious attacks. This poses potential danger to the users of the sites and could also affect operations of the organizations or companies concerned. Educational institutions are not left out, their portals and websites hold vital information whose integrity is of utmost importance. Taking Carnegie Mellon University Africa's internship portal as case study, we carried out penetration tests to investigate web vulnerabilities and proffered possible remedies to the discovered vulnerabilities. Our result will inform educational institutions on better website security practices, especially in the African domain., Comment: 4 pages, 2 figures