Krzysztof Czarnecki

• University of Waterloo

Existing vision-language model (VLM)-based methods for out-of-distribution (OOD) detection typically rely on similarity scores between input images and in-distribution (ID) text prototypes. However, the modality gap between image and text often results in high false positive rates, as OOD samples can exhibit high similarity to ID text prototypes. T...

Enhanced visual understanding serves as a cornerstone for multimodal large language models (MLLMs). Recent hybrid MLLMs incorporate a mixture of vision experts to address the limitations of using a single vision encoder and excessively long visual tokens. Despite the progress of these MLLMs, a research gap remains in effectively integrating diverse...

Input aggregation is a simple technique used by state-of-the-art LiDAR 3D object detectors to improve detection. However, increasing aggregation is known to have diminishing returns and even performance degradation, due to objects responding differently to the number of aggregated frames. To address this limitation, we propose an efficient adaptive...

Features are commonly used by developers and users to describe the functional and non-functional characteristics of software. Especially agile development methods, such as SCRUM, FDD or XP, use features to plan and manage software development. Features are often the main units of software reuse, communication, and configuration, abstracting over im...

With the increasing presence of autonomous vehicles (AVs) on public roads, developing robust control strategies to navigate the uncertainty of human-driven vehicles (HVs) is crucial. This paper introduces an advanced method for modeling HV behavior, combining a first-principles model with Gaussian process (GP) learning to enhance velocity predictio...

Scenario-based testing for automated driving systems (ADS) must be able to simulate traffic scenarios that rely on interactions with other vehicles. Although many languages for high-level scenario modelling have been proposed, they lack the features to precisely and reliably control the required micro-simulation, while also supporting behavior reus...

div class="section abstract"> Driving Automation Systems (DAS) are subject to complex road environments and vehicle behaviors and increasingly rely on sophisticated sensors and Artificial Intelligence (AI). These properties give rise to unique safety faults stemming from specification insufficiencies and technological performance limitations, where...

In this work, we study the problem of object re-identification (ReID) in a 3D multi-object tracking (MOT) context, by learning to match pairs of objects from cropped (e.g., using their predicted 3D bounding boxes) point cloud observations. We are not concerned with SOTA performance for 3D MOT, however. Instead, we seek to answer the following quest...

A central design problem in game theoretic analysis is the estimation of the players' utilities. In many real-world interactive situations of human decision making, including human driving, the utilities are multi-objective in nature; therefore, estimating the parameters of aggregation, i.e., mapping of multi-objective utilities to a scalar value,...

Autonomous vehicles require highly sophisticated decision-making to determine their motion. This paper describes how such functionality can be achieved with a practical rule engine learned from expert driving decisions. We propose an algorithm to create and maintain a rule-based behaviour planner, using a two-layer rule-based theory. The first laye...

Predicting the future motion of road agents is a critical task in an autonomous driving pipeline. In this work, we address the problem of generating a set of scene-level, or joint, future trajectory predictions in multi-agent driving scenarios. To this end, we propose FJMP, a Factorized Joint Motion Prediction framework for multi-agent interactive...

Explainable AI (XAI) methods are frequently applied to obtain qualitative insights about deep models' predictions. However, such insights need to be interpreted by a human observer to be useful. In this paper, we aim to use explanations directly to make decisions without human observers. We adopt two gradient-based explanation methods, Integrated G...

In adversarial machine learning, the popular $\ell_\infty$ threat model has been the focus of much previous work. While this mathematical definition of imperceptibility successfully captures an infinite set of additive image transformations that a model should be robust to, this is only a subset of all transformations which leave the semantic label...

Imagine experiencing a crash as the passenger of an autonomous vehicle. Wouldn't you want to know why it happened? Current end-to-end optimizable deep neural networks (DNNs) in 3D detection, multi-object tracking, and motion forecasting provide little to no explanations about how they make their decisions. To help bridge this gap, we design an end-...

3D object detection is an essential part of automated driving, and deep neural networks (DNNs) have achieved state-of-the-art performance for this task. However, deep models are notorious for assigning high confidence scores to out-of-distribution (OOD) inputs, that is, inputs that are not drawn from the training distribution. Detecting OOD inputs...

Although artificial intelligence-based perception (AIP) using deep neural networks (DNN) has achieved near human level performance, its well-known limitations are obstacles to the safety assurance needed in autonomous applications. These include vulnerability to adversarial inputs, inability to handle novel inputs and non-interpretability. While re...

Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning. However its potential in motion forecasting for autonomous driving has rarely been explored. In this stud...

While there has been an increasing focus on the use of game theoretic models for autonomous driving, empirical evidence shows that there are still open questions around dealing with the challenges of common knowledge assumptions as well as modeling bounded rationality. To address some of these practical challenges, we develop a framework of general...

The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods in 3D object detection remains challenging due to timing and computational constraints. To tackle this issue,...

Modelling pedestrian behavior is crucial in the development and testing of autonomous vehicles. In this work, we present a hierarchical pedestrian behavior model that generates high-level decisions through the use of behavior trees, in order to produce maneuvers executed by a low-level motion planner using an adapted Social Force model. A full impl...

Although artificial intelligence-based perception (AIP) using deep neural networks (DNN) has achieved near human level performance, its well-known limitations are obstacles to the safety assurance needed in autonomous applications. These include vulnerability to adversarial inputs, inability to handle novel inputs and non-interpretability. While re...

Scenario-based testing for automated driving systems (ADS) must be able to simulate traffic scenarios that rely on interactions with other vehicles. Although many languages for high-level scenario modelling have been proposed, they lack the features to precisely and reliably control the required micro-simulation, while also supporting behavior reus...

div class="section abstract"> Safety assurance is a central concern for the development and societal acceptance of automated driving (AD) systems. Perception is a key aspect of AD that relies heavily on Machine Learning (ML). Despite the known challenges with the safety assurance of ML-based components, proposals have recently emerged for unit-leve...

Machine Vision Components (MVC) are becoming safety-critical. Assuring their quality, including safety, is essential for their successful deployment. Assurance relies on the availability of precisely specified and, ideally, machine-verifiable requirements. MVCs with state-of-the-art performance rely on machine learning (ML) and training data but la...

We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully address our precise problem definition, which nevertheless arises naturally in the context of safety-critical rob...

This paper characterizes safe following distances for on-road driving when vehicles can avoid collisions by either braking or by swerving into an adjacent lane. In particular, we focus on safety as defined in the Responsibility-Sensitive Safety (RSS) framework. We extend RSS by introducing swerve maneuvers as a valid response in addition to the alr...

In order to enable autonomous vehicles (AV) to navigate busy traffic situations, in recent years there has been a focus on game-theoretic models for strategic behavior planning in AVs. However, a lack of common taxonomy impedes a broader understanding of the strategies the models generate as well as the development of safety specification to identi...

While there has been an increasing focus on the use of game theoretic models for autonomous driving, empirical evidence shows that there are still open questions around dealing with the challenges of common knowledge assumptions as well as modeling bounded rationality. To address some of these practical challenges, we develop a framework of general...

A particular challenge for both autonomous and human driving is dealing with risk associated with dynamic occlusion, i.e., occlusion caused by other vehicles in traffic. Based on the theory of hypergames, we develop a novel multi-agent dynamic occlusion risk (DOR) measure for assessing situational risk in dynamic occlusion scenarios. Furthermore, w...

Safety assurance is a central concern for the development and societal acceptance of automated driving (AD) systems. Perception is a key aspect of AD that relies heavily on Machine Learning (ML). Despite the known challenges with the safety assurance of ML-based components, proposals have recently emerged for unit-level safety cases addressing thes...

Formal reasoning on the safety of controller systems interacting with plants is complex because developers need to specify behavior while taking into account perceptual uncertainty. To address this, we propose an automated workflow that takes an Event-B model of an uncertainty-unaware controller and a specification of uncertainty as input. First, o...

Reinforcement learning (RL) is an attractive way to implement high-level decision-making policies for autonomous driving, but learning directly from a real vehicle or a high-fidelity simulator is variously infeasible. We therefore consider the problem of transfer reinforcement learning and study how a policy learned in a simple environment using Wi...

Formal reasoning on the safety of controller systems interacting with plants is complex because developers need to specify behavior while taking into account perceptual uncertainty. To address this, we propose an automated workflow that takes an Event-B model of an uncertainty-unaware controller and a specification of uncertainty as input. First, o...

With autonomous vehicles (AV) set to integrate further into regular human traffic, there is an increasing consensus of treating AV motion planning as a multi-agent problem. However, the traditional game theoretic assumption of complete rationality is too strong for the purpose of human driving, and there is a need for understanding human driving as...

Autonomous Vehicles (AV) will transform transportation, but also the interaction between vehicles and pedestrians. In the absence of a driver, it is not clear how an AV can communicate its intention to pedestrians. One option is to use visual signals. To advance their design, we conduct four human-participant experiments and evaluate six representa...

With autonomous vehicles (AV) set to integrate further into regular human traffic, there is an increasing consensus of treating AV motion planning as a multi-agent problem. However, the traditional game theoretic assumption of complete rationality is too strong for the purpose of human driving, and there is a need for understanding human driving as...

Deep neural networks (DNNs) have become the de facto learning mechanism in different domains. Their tendency to perform unreliably on out-of-distribution (OOD) inputs hinders their adoption in critical domains. Several approaches have been proposed for detecting OOD inputs. However, existing approaches still lack robustness. In this paper, we shed...

div class="section abstract"> With the widespread development of automated driving systems (ADS), it is imperative that standardized testing methodologies be developed to assure safety and functionality. Scenario testing evaluates the behavior of an ADS-equipped subject vehicle (SV) in predefined driving scenarios. This paper compares four modes of...

This paper characterizes safe following distances for on-road driving when vehicles can avoid collisions by either braking or by swerving into an adjacent lane. In particular, we focus on safety as defined in the Responsibility-Sensitive Safety (RSS) framework. We extend RSS by introducing swerve manoeuvres as a valid response in addition to the al...

The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing the image to be out of distribution. This paper adapts state-of-the-art methods for detecting out of distribution images fo...

Deep neural networks achieve superior performance in challenging tasks such as image classification. However, deep classifiers tend to incorrectly classify out-of-distribution (OOD) inputs, which are inputs that do not belong to the classifier training distribution. Several approaches have been proposed to detect OOD inputs, but the detection task...

By design, discriminatively trained neural network classifiers produce reliable predictions only for in-distribution samples. For their real-world deployments, detecting out-of-distribution (OOD) samples is essential. Assuming OOD to be outside the closed boundary of in-distribution, typical neural classifiers do not contain the knowledge of this b...

WiseMove is a platform to investigate safe deep reinforcement learning (DRL) in the context of motion planning for autonomous driving. It adopts a modular architecture that mirrors our autonomous vehicle software stack and can interleave learned and programmed components. Our initial investigation focuses on a state-of-the-art DRL approach from the...

We explore the complex design space of behaviour planning for autonomous driving. Design choices that successfully address one aspect of behaviour planning can critically constrain others. To aid the design process, in this work we decompose the design space with respect to important choices arising from the current state of the art approaches, and...

Image semantic segmentation systems based on deep learning are prone to making erroneous predictions for images affected by uncertainty influence factors such as occlusions or inclement weather. Bayesian deep learning applies the Bayesian framework to deep models and allows estimating so-called epistemic and aleatoric uncertainties as part of the p...

Advanced autonomy features of vehicles are typically difficult or impossible to specify precisely and this has led to the rise of machine learning (ML) from examples as an alternative implementation approach to traditional programming. Developing software without specifications sacrifices the ability to effectively verify the software yet this is a...

We present a controlled experiment for the empirical evaluation of example-driven modeling (EDM), an approach that systematically uses examples for model comprehension and domain knowledge transfer. We conducted the experiment with 26 graduate (Masters and Ph.D. level) and undergraduate (Bachelor level) students from electrical and computer enginee...

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution). Therefore, detecting out-of-distribution (OOD) samples is very important to avoid classification errors. In the context of OOD detection for image classification, one of the recent approaches proposes training...

A key challenge to software product line engineering is to explore a huge space of various products and to find optimal or near-optimal solutions that satisfy all predefined constraints and balance multiple often competing objectives. To address this challenge, we propose a hybrid multi-objective optimization algorithm called SMTIBEA that combines...

Performance evaluation of urban autonomous vehicles requires a realistic model of the behavior of other road users in the environment. Learning such models from data involves collecting naturalistic data of real-world human behavior. In many cases, acquisition of this data can be prohibitively expensive or intrusive. Additionally, the available dat...

In industry, evaluating candidate architectures for automotive embedded systems is routinely done during the design process. Today’s engineers, however, are limited in the number of candidates that they are able to evaluate in order to find the optimal architectures. This limitation results from the difficulty in defining the candidates as it is a...

Feature code is often scattered across a software system. Scattering is not necessarily bad if used with care, as witnessed by systems with highly scattered features that evolved successfully. Feature scattering, often realized with a pre-processor, circumvents limitations of programming languages and software architectures. Unfortunately, little i...

There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems. A number of recent papers have proposed methods for detecting anomalous image data that appear different from known inlier data samples, including reconstruction-based autoencoders....

In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to estimate the probability of each predicted object in a given region and the confidence interval for its boundin...

Over the years complexity theorists have proposed many structural parameters to explain the surprising efficiency of conflict-driven clause-learning (CDCL) SAT solvers on a wide variety of large industrial Boolean instances. While some of these parameters have been studied empirically, until now there has not been a unified comparative study of the...

Restarts are a pivotal aspect of conflict-driven clause-learning (CDCL) SAT solvers, yet it remains unclear when they are favorable in practice, and whether they offer additional power in theory. In this paper, we consider the power of restarts through the lens of backdoors. Extending the notion of learning-sensitive (LS) backdoors, we define a new...

Perception is a safety-critical function of autonomous vehicles and machine learning (ML) plays a key role in its implementation. This position paper identifies (1) perceptual uncertainty as a performance measure used to define safety requirements and (2) its influence factors when using supervised ML. This work is a first step towards a framework...

The use of machine learning (ML) is on the rise in many sectors of software development, and automotive software development is no different. In particular, Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) are two areas where ML plays a significant role. In automotive development, safety is a critical objective, and the...

Embedded software is growing fast in size and complexity, leading to intimate mixture of complex architectures and complex control. Consequently, software specification requires modeling both structures and behaviour of systems. Unfortunately, existing languages do not integrate these aspects well, usually prioritizing one of them. It is common to...

This document defines a catalog of basic motion control tasks for ADS. These tasks reside at operational level and comprise (i) longitudinal control, including acceleration, deceleration, and speed maintenance, and (ii) lateral control, including straight driving, cornering, and swerving. Each task is analyzed in terms of factors impacting its exec...

This document is Part 1 of an ontology definition for specifying operational world models for an Automated Driving System (ADS). Part 1 defines a road structure ontology, which covers road types, road surface, road geometry, cross-section design, traffic control devices, pedestrian and cycling facilities, junctions, railroad level crossings, bridge...

This document is Part 2 of an ontology definition for specifying operational world models for an Automated Driving System (ADS). Part 2 covers road users, including vehicles and pedestrians and their behavior models; animals; other obstacles, including objects placed by forces of nature, lost cargo, and construction equipment; and environmental con...

This document defines a taxonomy of basic terms used in the description of an Operational Design Domain (ODD) for an Automated Driving System (ADS). Among others, the taxonomy defines operational world models and terms for specifying driving scenarios and their attributes.

This document provides a taxonomy of on-road safety of an Automated Driving System (ADS) and describes safety analysis methods applicable at requirements and early design stage of ADS development. In particular, it covers Driving Behavior Safety Assurance, Safety of The Intended Functionality (SOTIF) Assurance, and the Hazard Analysis and Risk Asse...

This document defines a maneuver catalog for driving on structured roads. It also provides a maneuver analysis method and a multi-dimensional organization of the maneuvers. The catalog is divided into primary maneuvers, which include lane maintenance; lane changing; and swerves and turns out of and into a lane; and secondary maneuvers, including pa...

This document analyzes safety requirements on driving behavior for ADS-operated vehicles, both at operational and tactical levels. The first part of the document describes motor-vehicle crash typology and pre-crash scenarios based on existing traffic safety data and literature. The second part proposes a classification of safety requirements on dri...

This document analyzes how the driving behavior of an ADS-operated vehicle impacts road user comfort. The main focus is occupant comfort related to acceleration and jerk; however, the analysis also considers other physical parameters, such as speed and gaps, and links them to comfort using the concept of a comfort zone. While much research on drivi...

In this paper, we analyze a suite of 7 well-known branching heuristics proposed by the SAT community and show that the better heuristics tend to generate more learnt clauses per decision, a metric we define as the global learning rate (GLR). We propose GLR as a metric for the branching heuristic to optimize. We test our hypothesis by developing a n...

Many software systems today are configurable, offering customization of functionality by feature selection. Understanding how performance varies in terms of feature selection is key for selecting appropriate configurations that meet a set of given requirements. Due to a huge configuration space and the possibly high cost of performance measurement,...

SAT solvers are increasingly being used for cryptanalysis of hash functions and symmetric encryption schemes. Inspired by this trend, we present MapleCrypt which is a SAT solver-based cryptanalysis tool for inverting hash functions. We reduce the hash function inversion problem for fixed targets into the satisfiability problem for Boolean logic, an...

Machine learning (ML) plays an ever-increasing role in advanced automotive functionality for driver assistance and autonomous operation; however, its adequacy from the perspective of safety certification remains controversial. In this paper, we analyze the impacts that the use of ML as an implementation approach has on ISO 26262 safety lifecycle an...