The widespread development of driverless vehicles has led to the formation of autonomous racing competitions, where the high speeds and fierce rivalry in motorsport provide a testbed to accelerate technology development. A particular challenge for an autonomous vehicle is that of identifying a target trajectory - or in the case of a racing car, the ideal racing line. Many existing approaches to identifying the racing line are either not the time-optimal solutions, or have solution times which are computationally expensive, thus rendering them unsuitable for real-time application using on-board processing hardware. This paper describes a machine learning approach to generating an accurate prediction of the racing line in real-time on desktop processing hardware. The proposed algorithm is a dense feed-forward neural network, trained using a dataset comprising racing lines for a large number of circuits calculated via a traditional optimal control lap time simulation. The network is capable of predicting the racing line with a mean absolute error of +/-0.27m, meaning that the accuracy outperforms a human driver, and is comparable to other parts of the autonomous vehicle control system. The system generates predictions within 33ms, making it over 9,000 times faster than traditional methods of finding the optimal racing line. Results suggest that a data-driven approach may therefore be favourable for real-time generation of near-optimal racing lines than traditional computational methods.

We present a work-in-progress approach to improving driver attentiveness in cars provided with automated driving systems. The approach is based on a control loop that monitors the driver's biometrics (eye movement, heart rate, etc.) and the state of the car; analyses the driver's attentiveness level using a deep neural network; plans driver alerts and changes in the speed of the car using a formally verified controller; and executes this plan using actuators ranging from acoustic and visual to haptic devices. The paper presents (i) the self-adaptive system formed by this monitor-analyse-plan-execute (MAPE) control loop, the car and the monitored driver, and (ii) the use of probabilistic model checking to synthesise the controller for the planning step of the MAPE loop.

This paper describes a general-purpose extension of max-value entropy search, a popular approach for Bayesian Optimisation (BO). A novel approximation is proposed for the information gain -- an information-theoretic quantity central to solving a range of BO problems, including noisy, multi-fidelity and batch optimisations across both continuous and highly-structured discrete spaces. Previously, these problems have been tackled separately within information-theoretic BO, each requiring a different sophisticated approximation scheme, except for batch BO, for which no computationally-lightweight information-theoretic approach has previously been proposed. GIBBON (General-purpose Information-Based Bayesian OptimisatioN) provides a single principled framework suitable for all the above, out-performing existing approaches whilst incurring substantially lower computational overheads. In addition, GIBBON does not require the problem's search space to be Euclidean and so is the first high-performance yet computationally light-weight acquisition function that supports batch BO over general highly structured input spaces like molecular search and gene design. Moreover, our principled derivation of GIBBON yields a natural interpretation of a popular batch BO heuristic based on determinantal point processes.

Deep learning classifiers are now known to have flaws in the representations of their class. Adversarial attacks can find a human-imperceptible perturbation for a given image that will mislead a trained model. The most effective methods to defend against such attacks trains on generated adversarial examples to learn their distribution. Previous work aimed to align original and adversarial image representations in the same way as domain adaptation to improve robustness. Yet, they partially align the representations using approaches that do not reflect the geometry of space and distribution. In addition, it is difficult to accurately compare robustness between defended models. Until now, they have been evaluated using a fixed perturbation size. However, defended models may react differently to variations of this perturbation size. In this paper, the analogy of domain adaptation is taken a step further by exploiting optimal transport theory. We propose to use a loss between distributions that faithfully reflect the ground distance. This leads to SAT (Sinkhorn Adversarial Training), a more robust defense against adversarial attacks. Then, we propose to quantify more precisely the robustness of a model to adversarial attacks over a wide range of perturbation sizes using a different metric, the Area Under the Accuracy Curve (AUAC). We perform extensive experiments on both CIFAR-10 and CIFAR-100 datasets and show that our defense is globally more robust than the state-of-the-art.

Testing and evaluation is a crucial step in the development and deployment of Connected and Automated Vehicles (CAVs). To comprehensively evaluate the performance of CAVs, it is of necessity to test the CAVs in safety-critical scenarios, which rarely happen in naturalistic driving environment. Therefore, how to purposely and systematically generate these corner cases becomes an important problem. Most existing studies focus on generating adversarial examples for perception systems of CAVs, whereas limited efforts have been put on the decision-making systems, which is the highlight of this paper. As the CAVs need to interact with numerous background vehicles (BVs) for a long duration, variables that define the corner cases are usually high dimensional, which makes the generation a challenging problem. In this paper, a unified framework is proposed to generate corner cases for the decision-making systems. To address the challenge brought by high dimensionality, the driving environment is formulated based on Markov Decision Process, and the deep reinforcement learning techniques are applied to learn the behavior policy of BVs. With the learned policy, BVs will behave and interact with the CAVs more aggressively, resulting in more corner cases. To further analyze the generated corner cases, the techniques of feature extraction and clustering are utilized. By selecting representative cases of each cluster and outliers, the valuable corner cases can be identified from all generated corner cases. Simulation results of a highway driving environment show that the proposed methods can effectively generate and identify the valuable corner cases.

The deployment of future intelligent transportation systems is contingent upon seamless and reliable operation of connected and autonomous vehicles (CAVs). One key challenge in developing CAVs is the design of an autonomous controller that can accurately execute near real-time control decisions, such as a quick acceleration when merging to a highway and frequent speed changes in a stop-and-go traffic. However, the use of conventional feedback controllers or traditional learning-based controllers, solely trained by each CAV's local data, cannot guarantee a robust controller performance over a wide range of road conditions and traffic dynamics. In this paper, a new federated learning (FL) framework enabled by large-scale wireless connectivity is proposed for designing the autonomous controller of CAVs. In this framework, the learning models used by the controllers are collaboratively trained among a group of CAVs. To capture the varying CAV participation in the FL training process and the diverse local data quality among CAVs, a novel dynamic federated proximal (DFP) algorithm is proposed that accounts for the mobility of CAVs, the wireless fading channels, as well as the unbalanced and nonindependent and identically distributed data across CAVs. A rigorous convergence analysis is performed for the proposed algorithm to identify how fast the CAVs converge to using the optimal autonomous controller. In particular, the impacts of varying CAV participation in the FL process and diverse CAV data quality on the convergence of the proposed DFP algorithm are explicitly analyzed. A preliminary version of this work has been submitted to the proceeding of IEEE Conference on Decision and Control (CDC), 2021 [1]. This research was supported by the U.S. National Science Foundation under Grants CNS-1739642, CNS-1941348, and CNS-2008646, and by the Academy of Finland Project CARMA, by the Academy of Finland Project MISSION, by the Academy of Finland Project SMARTER, as well as by the INFOTECH Project NOOR. T. Zeng and W. Saad are with Wireless@VT, Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, 24061 USA.

Machine learning systems are often trained using data collected from historical decisions. If past decisions were biased, then automated systems that learn from historical data will also be biased. We propose a black-box approach to identify and remove biased training data. Machine learning models trained on such debiased data (a subset of the original training data) have low individual discrimination, often 0%. These models also have greater accuracy and lower statistical disparity than models trained on the full historical data. We evaluated our methodology in experiments using 6 real-world datasets. Our approach outperformed seven previous approaches in terms of individual discrimination and accuracy.

In this paper, we study the problem of deceptive reinforcement learning to preserve the privacy of a reward function. Reinforcement learning is the problem of finding a behaviour policy based on rewards received from exploratory behaviour. A key ingredient in reinforcement learning is a reward function, which determines how much reward (negative or positive) is given and when. However, in some situations, we may want to keep a reward function private; that is, to make it difficult for an observer to determine the reward function used. We define the problem of privacy-preserving reinforcement learning, and present two models for solving it. These models are based on dissimulation -- a form of deception that `hides the truth'. We evaluate our models both computationally and via human behavioural experiments. Results show that the resulting policies are indeed deceptive, and that participants can determine the true reward function less reliably than that of an honest agent.

In chaotic modern society, there is an increasing demand for the realization of true 'fairness'. In Greek mythology, Themis, the 'goddess of justice', has a sword in her right hand to protect society from vices, and a 'balance of judgment' in her left hand that measures good and evil. In this study, we propose a fair distribution method 'utilising physics' for the profit in games of characteristic function form. Specifically, we show that the linear programming problem for calculating 'nucleolus' can be efficiently solved by considering it as a physical system in which gravity works. In addition to being able to significantly reduce computational complexity thereby, we believe that this system could have flexibility necessary to respond to real-time changes in the parameter.

Artificial intelligence has simultaneously been one of the most promising and at the same time worrying topics of the past few years. It unavoidably draws attention with its latest achievements and many are worried that AI could overtake a large percentage of the jobs in the world in the near future. But besides that, artificial intelligence can also end up being a powerful military tool. The National Office of Military Space Intelligence has already developed a powerful artificial brain named Sentient, which was revealed in 2019 by the National Intelligence Office (NRO) under the freedom of information law. Unlike any other AIs in existence, it differs in the degree of independence.