Search Results for author: Krzysztof Czarnecki

Found 49 papers, 16 papers with code

Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance

no code implementations29 Feb 2024 Huakun Shen, Boyue Caroline Hu, Krzysztof Czarnecki, Lina Marsso, Marsha Chechik

While Neural Networks (NNs) have surpassed human accuracy in image classification on ImageNet, they often lack robustness against image corruption, i. e., corruption robustness.

Data Augmentation Image Classification

SSL-Interactions: Pretext Tasks for Interactive Trajectory Prediction

no code implementations15 Jan 2024 Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki

This paper addresses motion forecasting in multi-agent environments, pivotal for ensuring safety of autonomous vehicles.

Autonomous Vehicles Motion Forecasting +1

SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling

no code implementations8 Jan 2024 Chengjie Huang, Vahdat Abdelzad, Sean Sedwards, Krzysztof Czarnecki

We consider the problem of cross-sensor domain adaptation in the context of LiDAR-based 3D object detection and propose Stationary Object Aggregation Pseudo-labelling (SOAP) to generate high quality pseudo-labels for stationary objects.

3D Object Detection Domain Adaptation +2

STEAM & MoSAFE: SOTIF Error-and-Failure Model & Analysis for AI-Enabled Driving Automation

no code implementations15 Dec 2023 Krzysztof Czarnecki, Hiroshi Kuwajima

The Safety of the Intended Functionality (SOTIF) standard emerges as a promising framework for addressing these concerns, focusing on scenario-based analysis to identify hazardous behaviors and their causes.

Object Re-Identification from Point Clouds

no code implementations17 May 2023 Benjamin Thérien, Chengjie Huang, Adrian Chow, Krzysztof Czarnecki

To our knowledge, we are the first to study object re-identification from real point cloud observations.

3D Multi-Object Tracking Autonomous Driving +3

Revealed Multi-Objective Utility Aggregation in Human Driving

no code implementations13 Mar 2023 Atrisha Sarkar, Kate Larson, Krzysztof Czarnecki

A central design problem in game theoretic analysis is the estimation of the players' utilities.

Decision Making

XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection

1 code implementation20 Oct 2022 Sunsheng Gu, Vahdat Abdelzad, Krzysztof Czarnecki

We evaluate the effectiveness of XC scores via the task of distinguishing true positive (TP) and false positive (FP) detected objects in the KITTI and Waymo datasets.

3D Object Detection Explainable Artificial Intelligence (XAI) +1

A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Composition

no code implementations5 Oct 2022 Luke Rowe, Benjamin Thérien, Krzysztof Czarnecki, Hongyang Zhang

In adversarial machine learning, the popular $\ell_\infty$ threat model has been the focus of much previous work.

Interpretable Deep Tracking

no code implementations3 Oct 2022 Benjamin Thérien, Krzysztof Czarnecki

By enumerating different tracking decisions and associated reasoning procedures, we can train individual networks to reason about the possible decisions via IIT.

Motion Forecasting Multi-Object Tracking

SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving

1 code implementation28 Jun 2022 Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki

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.

Motion Forecasting Representation Learning +1

LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection

no code implementations1 Jun 2022 Matthew Pitropov, Chengjie Huang, Vahdat Abdelzad, Krzysztof Czarnecki, Steven Waslander

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.

3D Object Detection Object +1

A Safety Assurable Human-Inspired Perception Architecture

no code implementations10 May 2022 Rick Salay, Krzysztof Czarnecki

While research in addressing these limitations is active, in this paper, we argue that a fundamentally different approach is needed to address them.

Image Classification

If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components

no code implementations8 Feb 2022 Boyue Caroline Hu, Lina Marsso, Krzysztof Czarnecki, Rick Salay, Huakun Shen, Marsha Chechik

In this paper, we address the need for defining machine-verifiable reliability requirements for MVCs against transformations that simulate the full range of realistic and safety-critical changes in the environment.

Image Classification

Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning

no code implementations20 Jan 2022 Jaeyoung Lee, Sean Sedwards, Krzysztof Czarnecki

In this work, after describing and motivating our problem with a simple example, we present a suitable constrained reinforcement learning algorithm that prevents learning instability, using recursive constraints.

reinforcement-learning Reinforcement Learning (RL)

A taxonomy of strategic human interactions in traffic conflicts

no code implementations27 Sep 2021 Atrisha Sarkar, Kate Larson, Krzysztof Czarnecki

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.

Autonomous Vehicles Navigate

I Know You Can't See Me: Dynamic Occlusion-Aware Safety Validation of Strategic Planners for Autonomous Vehicles Using Hypergames

no code implementations20 Sep 2021 Maximilian Kahn, Atrisha Sarkar, Krzysztof Czarnecki

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.

Autonomous Vehicles

Generalized dynamic cognitive hierarchy models for strategic driving behavior

no code implementations20 Sep 2021 Atrisha Sarkar, Kate Larson, Krzysztof Czarnecki

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.

Autonomous Driving

The missing link: Developing a safety case for perception components in automated driving

no code implementations30 Aug 2021 Rick Salay, Krzysztof Czarnecki, Hiroshi Kuwajima, Hirotoshi Yasuoka, Toshihiro Nakae, Vahdat Abdelzad, Chengjie Huang, Maximilian Kahn, Van Duong Nguyen

In this paper, we propose the Integration Safety Case for Perception (ISCaP), a generic template for such a linking safety argument specifically tailored for perception components.

SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection

1 code implementation7 Jan 2021 Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki

In this paper, we propose two variants of self-attention for contextual modeling in 3D object detection by augmenting convolutional features with self-attention features.

3D Object Detection Object +1

Autonomous Vehicle Visual Signals for Pedestrians: Experiments and Design Recommendations

no code implementations10 Oct 2020 Henry Chen, Robin Cohen, Kerstin Dautenhahn, Edith Law, Krzysztof Czarnecki

Based on the results, we distill twelve practical design recommendations for AV visual signals, with focus on signal pattern design and placement.

Autonomous Vehicles Persuasiveness

Solution Concepts in Hierarchical Games under Bounded Rationality with Applications to Autonomous Driving

1 code implementation21 Sep 2020 Atrisha Sarkar, Krzysztof Czarnecki

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.

Autonomous Driving Motion Planning

The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches

no code implementations25 Jun 2020 Vahdat Abdelzad, Krzysztof Czarnecki, Rick Salay

In addition to comparing several OODD approaches using our proposed robustness score, we demonstrate that some optimization methods provide better solutions for OODD approaches.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Canadian Adverse Driving Conditions Dataset

1 code implementation27 Jan 2020 Matthew Pitropov, Danson Garcia, Jason Rebello, Michael Smart, Carlos Wang, Krzysztof Czarnecki, Steven Waslander

The Canadian Adverse Driving Conditions (CADC) dataset was collected with the Autonomoose autonomous vehicle platform, based on a modified Lincoln MKZ.

3D Object Detection object-detection

Improving Confident-Classifiers For Out-of-distribution Detection

1 code implementation25 Sep 2019 Sachin Vernekar, Ashish Gaurav, Vahdat Abdelzad, Taylor Denouden, Rick Salay, Krzysztof Czarnecki

In the context of OOD detection for image classification, one of the recent approaches proposes training a classifier called “confident-classifier” by minimizing the standard cross-entropy loss on in-distribution samples and minimizing the KLdivergence between the predictive distribution of OOD samples in the low-density“boundary” of in-distribution and the uniform distribution (maximizing the entropy of the outputs).

Out-of-Distribution Detection Out of Distribution (OOD) Detection

TruPercept: Trust Modelling for Autonomous Vehicle Cooperative Perception from Synthetic Data

1 code implementation17 Sep 2019 Braden Hurl, Robin Cohen, Krzysztof Czarnecki, Steven Waslander

Inter-vehicle communication for autonomous vehicles (AVs) stands to provide significant benefits in terms of perception robustness.

Autonomous Vehicles

MLOD: A multi-view 3D object detection based on robust feature fusion method

no code implementations9 Sep 2019 Jian Deng, Krzysztof Czarnecki

The detector takes an RGB image and a LIDAR point cloud as input and follows the two-stage object detection framework.

3D Object Detection Object +2

A Micro-Objective Perspective of Reinforcement Learning

no code implementations24 May 2019 Changjian Li, Krzysztof Czarnecki

The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward.

reinforcement-learning Reinforcement Learning (RL)

Analysis of Confident-Classifiers for Out-of-distribution Detection

1 code implementation27 Apr 2019 Sachin Vernekar, Ashish Gaurav, Taylor Denouden, Buu Phan, Vahdat Abdelzad, Rick Salay, Krzysztof Czarnecki

Discriminatively trained neural classifiers can be trusted, only when the input data comes from the training distribution (in-distribution).

General Classification Out-of-Distribution Detection +1

Learning a Lattice Planner Control Set for Autonomous Vehicles

1 code implementation5 Mar 2019 Ryan De Iaco, Stephen L. Smith, Krzysztof Czarnecki

This paper introduces a method to compute a sparse lattice planner control set that is suited to a particular task by learning from a representative dataset of vehicle paths.

Autonomous Vehicles

Towards a Framework to Manage Perceptual Uncertainty for Safe Automated Driving

no code implementations3 Mar 2019 Krzysztof Czarnecki, Rick Salay

Perception is a safety-critical function of autonomous vehicles and machine learning (ML) plays a key role in its implementation.

Autonomous Vehicles BIG-bench Machine Learning +1

WiseMove: A Framework for Safe Deep Reinforcement Learning for Autonomous Driving

no code implementations11 Feb 2019 Jaeyoung Lee, Aravind Balakrishnan, Ashish Gaurav, Krzysztof Czarnecki, Sean Sedwards

Machine learning can provide efficient solutions to the complex problems encountered in autonomous driving, but ensuring their safety remains a challenge.

Autonomous Driving Motion Planning +2

Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distance

no code implementations6 Dec 2018 Taylor Denouden, Rick Salay, Krzysztof Czarnecki, Vahdat Abdelzad, Buu Phan, Sachin Vernekar

There is an increasingly apparent need for validating the classifications made by deep learning systems in safety-critical applications like autonomous vehicle systems.

Out-of-Distribution Detection

Calibrating Uncertainties in Object Localization Task

no code implementations27 Nov 2018 Buu Phan, Rick Salay, Krzysztof Czarnecki, Vahdat Abdelzad, Taylor Denouden, Sachin Vernekar

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.

Autonomous Driving Decision Making +5

Urban Driving with Multi-Objective Deep Reinforcement Learning

1 code implementation21 Nov 2018 Changjian Li, Krzysztof Czarnecki

Autonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers.

Autonomous Driving Q-Learning +2

Using Machine Learning Safely in Automotive Software: An Assessment and Adaption of Software Process Requirements in ISO 26262

no code implementations5 Aug 2018 Rick Salay, Krzysztof Czarnecki

In automotive development, safety is a critical objective, and the emergence of standards such as ISO 26262 has helped focus industry practices to address safety in a systematic and consistent way.

Unlimited Road-scene Synthetic Annotation (URSA) Dataset

no code implementations16 Jul 2018 Matt Angus, Mohamed ElBalkini, Samin Khan, Ali Harakeh, Oles Andrienko, Cody Reading, Steven Waslander, Krzysztof Czarnecki

Utilizing open-source tools and resources found in single-player modding communities, we provide a method for persistent, ground truth, asset annotation of a game world.

Semantic Segmentation

Relating Complexity-theoretic Parameters with SAT Solver Performance

no code implementations26 Jun 2017 Edward Zulkoski, Ruben Martins, Christoph Wintersteiger, Robert Robere, Jia Liang, Krzysztof Czarnecki, Vijay Ganesh

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.

SAT-based Analysis of Large Real-world Feature Models is Easy

1 code implementation17 Jun 2015 Jia Hui Liang, Vijay Ganesh, Venkatesh Raman, Krzysztof Czarnecki

We discovered that a key reason why large real-world FMs are easy-to-analyze is that the vast majority of the variables in these models are unrestricted, i. e., the models are satisfiable for both true and false assignments to such variables under the current partial assignment.

Cannot find the paper you are looking for? You can Submit a new open access paper.