Deep neural networks (DNNs) are often constructed under the closed-world assumption, which may fail to generalize to the out-of-distribution (OOD) data. This leads to DNNs producing overconfident wrong predictions and can result in disastrous consequences in safety-critical applications. Existing OOD detection methods mainly rely on curating a set of OOD data for model training or hyper-parameter tuning to distinguish OOD data from training data (also known as in-distribution data or InD data). However, OOD samples are not always available during the training phase in real-world applications, hindering the OOD detection accuracy. To overcome this limitation, we propose a Gaussian-process-based OOD detection method to establish a decision boundary based on InD data only. The basic idea is to perform uncertainty quantification of the unconstrained softmax scores of a DNN via a multi-class Gaussian process (GP), and then define a score function to separate InD and potential OOD data based on their fundamental differences in the posterior predictive distribution from the GP. Two case studies on conventional image classification datasets and real-world image datasets are conducted to demonstrate that the proposed method outperforms the state-of-the-art OOD detection methods when OOD samples are not observed in the training phase.

Domain adaptation for object detection (DAOD) aims to transfer a trained model from a source to a target domain. Various DAOD methods exist, some of which minimize context bias between foreground-background associations in various domains. However, no prior work has studied context bias in DAOD by analyzing changes in background features during adaptation and how context bias is represented in different domains. Our research experiment highlights the potential usability of context bias in DAOD. We address the problem by varying activation values over different layers of trained models and by masking the background, both of which impact the number and quality of detections. We then use one synthetic dataset from CARLA and two different versions of real open-source data, Cityscapes and Cityscapes foggy, as separate domains to represent and quantify context bias. We utilize different metrics such as Maximum Mean Discrepancy (MMD) and Maximum Variance Discrepancy (MVD) to find the layer-specific conditional probability estimates of foreground given manipulated background regions for separate domains. We demonstrate through detailed analysis that understanding of the context bias can affect DAOD approach and foc

With the advent of universal function approximators in the domain of reinforcement learning, the number of practical applications leveraging deep reinforcement learning (DRL) has exploded. Decision-making in autonomous vehicles (AVs) has emerged as a chief application among them, taking the sensor data or the higher-order kinematic variables as the input and providing a discrete choice or continuous control output. There has been a continuous effort to understand the black-box nature of the DRL models, but so far, there hasn't been any discussion (to the best of authors' knowledge) about how the models learn the physical process. This presents an overwhelming limitation that restricts the real-world deployment of DRL in AVs. Therefore, in this research work, we try to decode the knowledge learnt by the attention-based DRL framework about the physical process. We use a continuous proximal policy optimization-based DRL algorithm as the baseline model and add a multi-head attention framework in an open-source AV simulation environment. We provide some analytical techniques for discussing the interpretability of the trained models in terms of explainability and causality for spatial and temporal correlations. We show that the weights in the first head encode the positions of the neighboring vehicles while the second head focuses on the leader vehicle exclusively. Also, the ego vehicle's action is causally dependent on the vehicles in the target lane spatially and temporally. Through these findings, we reliably show that these techniques can help practitioners decipher the results of the DRL algorithms.

While there has been extensive work on generating physics-based adversarial samples recently, an overlooked class of such samples come from physical failures in the camera. Camera failures can occur as a result of an external physical process, i.e. breakdown of a component due to stress, or an internal component failure. In this work, we develop a simulated physical process for generating broken lens as a class of physics-based adversarial samples. We create a stress-based physical simulation by generating particles constrained in a mesh and apply stress at a random point and at a random angle. We perform stress propagation through the mesh and the end result of the mesh is a corresponding image which simulates the broken lens pattern. We also develop a neural emulator which learns the non-linear mapping between the mesh as a graph and the stress propagation using constrained propagation setup. We can then statistically compare the difference between the generated adversarial samples with real, simulated and emulated adversarial examples using the detection failure rate of the different classes and in between the samples using the Frechet Inception distance. Our goal through this work is to provide a robust physics based process for generating adversarial samples.

We examine the problem of estimating footprint uncertainty of objects imaged using the infrastructure based camera sensing. A closed form relationship is established between the ground coordinates and the sources of the camera errors. Using the error propagation equation, the covariance of a given ground coordinate can be measured as a function of the camera errors. The uncertainty of the footprint of the bounding box can then be given as the function of all the extreme points of the object footprint. In order to calculate the uncertainty of a ground point, the typical error sizes of the error sources are required. We present a method of estimating the typical error sizes from an experiment using a static, high-precision LiDAR as the ground truth. Finally, we present a simulated case study of uncertainty quantification from infrastructure based camera in CARLA to provide a sense of how the uncertainty changes across a left turn maneuver.

Autonomous vehicles (AVs) need to determine their position and orientation accurately with respect to global coordinate system or local features under different scene geometries, traffic conditions and environmental conditions. \cite{reid2019localization} provides a comprehensive framework for the localization requirements for AVs. However, the framework is too restrictive whereby - (a) only a very small deviation from the lane is tolerated (one every $10^{8}$ hours), (b) all roadway types are considered same without any attention to restriction provided by the environment onto the localization and (c) the temporal nature of the location and orientation is not considered in the requirements. In this research, we present a more practical view of the localization requirement aimed at keeping the AV safe during an operation. We present the following novel contributions - (a) we propose a deviation penalty as a cumulative distribution function of the Weibull distribution which starts from the adjacent lane boundary, (b) we customize the parameters of the deviation penalty according to the current roadway type, particular lane boundary that the ego vehicle is against and roadway curvature and (c) we update the deviation penalty based on the available gap in the adjacent lane. We postulate that this formulation can provide a more robust and achievable view of the localization requirements than previous research while focusing on safety.

Pedestrian safety has become an important research topic among various studies due to the increased number of pedestrian-involved crashes. To evaluate pedestrian safety proactively, surrogate safety measures (SSMs) have been widely used in traffic conflict-based studies as they do not require historical crashes as inputs. However, most existing SSMs were developed based on the assumption that road users would maintain constant velocity and direction. Risk estimations based on this assumption are less unstable, more likely to be exaggerated, and unable to capture the evasive maneuvers of drivers. Considering the limitations among existing SSMs, this study proposes a probabilistic framework for estimating the risk of pedestrian-vehicle conflicts at intersections. The proposed framework loosen restrictions of constant speed by predicting trajectories using a Gaussian Process Regression and accounts for the different possible driver maneuvers with a Random Forest model. Real-world LiDAR data collected at an intersection was used to evaluate the performance of the proposed framework. The newly developed framework is able to identify all pedestrian-vehicle conflicts. Compared to the Time-to-Collision, the proposed framework provides a more stable risk estimation and captures the evasive maneuvers of vehicles. Moreover, the proposed framework does not require expensive computation resources, which makes it an ideal choice for real-time proactive pedestrian safety solutions at intersections.

Inverse reinforcement learning (IRL) is used to infer the reward function from the actions of an expert running a Markov Decision Process (MDP). A novel approach using variational inference for learning the reward function is proposed in this research. Using this technique, the intractable posterior distribution of the continuous latent variable (the reward function in this case) is analytically approximated to appear to be as close to the prior belief while trying to reconstruct the future state conditioned on the current state and action. The reward function is derived using a well-known deep generative model known as Conditional Variational Auto-encoder (CVAE) with Wasserstein loss function, thus referred to as Conditional Wasserstein Auto-encoder-IRL (CWAE-IRL), which can be analyzed as a combination of the backward and forward inference. This can then form an efficient alternative to the previous approaches to IRL while having no knowledge of the system dynamics of the agent. Experimental results on standard benchmarks such as objectworld and pendulum show that the proposed algorithm can effectively learn the latent reward function in complex, high-dimensional environments.

A common approach for defining a reward function for Multi-objective Reinforcement Learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a new solution is required for any change in these settings. This paper investigates the relationship between the reward function and the optimal value function for MORL; specifically addressing the question of how to approximate the optimal value function well beyond the set of weights for which the optimization problem was actually solved, thereby avoiding the need to recompute for any particular choice. We prove that the value function transforms smoothly given a transformation of weights of the reward function (and thus a smooth interpolation in the policy space). A Gaussian process is used to obtain a smooth interpolation over the reward function weights of the optimal value function for three well-known examples: GridWorld, Objectworld and Pendulum. The results show that the interpolation can provide very robust values for sample states and action space in discrete and continuous domain problems. Significant advantages arise from utilizing this interpolation technique in the domain of autonomous vehicles: easy, instant adaptation of user preferences while driving and true randomization of obstacle vehicle behavior preferences during training.