Publications

Flow-level coordination of connected and autonomous vehicles in multilane freeway ramp merging areas | Elsevier Enhanced Reader

On-ramp merging areas are deemed to be typical bottlenecks for freeway networks due to the intensive disturbances induced by the frequent merging, weaving, and lane-changing behaviors. The Connected and Autonomous Vehicles (CAVs), benefited from their

Facilitating Collaboration Between Humans and Unmanned Heavy Vehicles using Verbal Interaction and Augmented Reality

The development of unmanned self-driving vehicles appears to have great potential to increase safety and transport productivity. In industry, these vehicles are expected to be adopted first in confined contexts (hubs), such as mines. However, there is a

Designing Collaboration between Human Beings and Self-driving Heavy Vehicles with Emerging Interaction Technologies

The present work-in-progress paper describes the development of novel user interface concepts that allow human operators to collaborate with self-driving heavy vehicles in a mining context. Concept development was performed within a user-centered design

ComFASE: A Tool for Evaluating the Effects of V2V Communication Faults and Attacks on Automated Vehicles

This paper presents ComFASE, a communication fault and attack simulation engine. ComFASE is used to identify and evaluate potentially dangerous behaviours of interconnected automated vehicles in the presence of faults and attacks in wireless vehicular

Multidimensional Framework for Characterizing Verification and Validation of Automated Systems

Verification and Validation (V&V) of automated systems is becoming more costly and time-consuming because of the increasing size and complexity of these systems. Moreover, V&V of these systems can be hindered if the methods and processes are not properly

DELFASE: A Deep Learning Method for Fault Space Exploration

Cyber-Physical Systems (CPSs) are increasingly used in various safety-critical domains; assuring the safety of these systems is of paramount importance. Fault Injection is known as an effective testing method for analyzing the safety of CPSs. However, the

Criteria for the Analysis of Gaps and Limitations of V&V Methods for Safety- and Security-Critical Systems

As society increasingly relies on safety- and security- critical systems, the need for confirming their dependability becomes essential. Adequate V&V (verification and validation) methods must be employed, e.g., for system testing. When selecting and using

On the Evaluation of Three Pre-Injection Analysis Techniques for Model-Implemented Fault- and Attack Injection

Fault- and attack injection are techniques used to measure dependability attributes of computer systems. An important property of such injectors is their efficiency that deals with the time and effort needed to explore the target system’s fault- or attack

Modeling and Evaluating the Effects of Jamming Attacks on Connected Automated Road Vehicles

In this work, we evaluate the safety of a platoon of four vehicles under jamming attacks. The platooning application is provided by Plexe-veins, which is a cooperative driving framework, and the vehicles in the platoon are equipped with cooperative

Regulating Road Vehicle Teleoperation: Back to the Near Future

Due to the many remaining obstacles before reliability and safety can sufficiently be guaranteed for high-level automated vehicles (AVs), teleoperation or remote operation of partially automated vehicles by a human driver has become increasingly

Study of different steering feedback models influence during remote driving’

Steering feedback is one essential aspect to provide real world information, and can influence driving performance during remote driving. In this work, the classical feedback models based on physical characteristics (Physical Model) and modular

Comparing Vehicle Safety Systems in Adverse Condition Splash and Spray between Road and Test Site

The effect of CMS with AR on drivingperformance

This Master Thesis was conducted in the Industrial Design Engineering program at theChalmers University of Technology in collaboration with RISE and Volvo Cars. The aimwas to investigate the difference in driving performance between a traditional mirror

Interaction design for Augmented Reality Head-Up Displays: Developing graphics design and evaluating perceptual and safety aspects for navigation use cases

The interactions with everyday products and technology are often done without being noticed or reflected upon. Interactions driving a vehicle are happening automatically for most people when having experience driving. With the innovative shift within the

An Industrial Experience Report about Challenges from Continuous Monitoring, Improvement, and Deployment for Autonomous Driving Features

Description of same-direction car-to-bicycle crash scenarios using real-world data from Sweden, Germany, and a global crash database

The overall number of traffic crashes is decreasing, but the number of crashes incurring cyclist injuries is not decreasing at the same pace. Of all car-to-bicycle crashes, same-direction crashes are among the ones with the highest risk of a serious-to

On the importance of driver models for the development and assessment of active safety: A new collision warning system to make overtaking cyclists safer

The total number of road crashes in Europe is decreasing, but the number of crashes involving cyclists is not decreasing at the same rate. When cars and bicycles share the same lane, cars typically need to overtake them, creating dangerous conflicts

Methods and models for safety benefit assessment of advanced driver assistance systems in car-to-cyclist conflicts

To help drivers avoid or mitigate the severity of crashes, advanced driver assistance systems (ADAS) can be designed to provide warnings or interventions. Prospective safety assessment of ADAS is important to quantify and optimise their safety benefit

FaceDancer: Pose- and Occlusion-Aware High Fidelity Face Swapping

In this work, we present a new single-stage method for subject agnostic face swapping and identity transfer, named FaceDancer. We have two major contributions: Adaptive Feature Fusion Attention (AFFA) and Interpreted Feature Similarity Regularization (IFSR

An autonomous performance testing framework using self-adaptive fuzzy reinforcement learning

Test automation brings the potential to reduce costs and human effort, but several aspects of software testing remain challenging to automate. One such example is automated performance testing to find performance breaking points. Current approaches to

Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testing

This paper presents an extended version of Deeper, a search-based simulation-integrated test solution that generates failure-revealing test scenarios for testing a deep neural network-based lane-keeping system. In the newly proposed version, we utilize a

Exploring ML testing in practice -- Lessons learned from an interactive rapid review with Axis Communications

There is a growing interest in industry and academia in machine learning (ML) testing. We believe that industry and academia need to learn together to produce rigorous and relevant knowledge. In this study, we initiate a collaboration between stakeholders

Ergo, SMIRK is Safe: A Safety Case for a Machine Learning Component in a Pedestrian Automatic Emergency Brake System

Integration of Machine Learning (ML) components in critical applications introduces novel challenges for software certification and verification. New safety standards and technical guidelines are under development to support the safety of ML-based systems

Public Report SMILE III

Future autonomous vehicles will rely on Deep machine learning algorithms (DML), whose correct behavior cannot be guaranteed by traditional software engineering approaches. This uncertainty is a big obstacle to ensure the quality of systems using DML

On Improving Validity of Deep Neural Networks in Safety Critical Applications

Context: Deep learning has proven to be a valuable component in object detection and classification, as the technique has shown an increased performance throughput compared to traditional software algorithms. Deep learning refers to the process, in which

The Head AIS 4+ Injury Thresholds for the Elderly Vulnerable Road User Based on Detailed Accident Reconstructions

Compared with the young, the elderly (age greater than or equal to 60 years old) vulnerable road users (VRUs) face a greater risk of injury or death in a traffic accident. A contributing vulnerability is the aging processes that affect their brain

Eye Tracking in Driver Attention Research - How Gaze Data Interpretations Influence What We Learn

Eye tracking (ET) has been used extensively in driver attention research. Amongst other findings, ET data have increased our knowledge about what drivers look at in different traffic environments and how they distribute their glances when interacting with

Behavioral adaptation of drivers when driving among automated vehicles

Purpose – This paper aims to explore whether drivers would adapt their behavior when they drive among automated vehicles (AVs) compared to driving among manually driven vehicles (MVs).Understanding behavioral adaptation of drivers when they encounter AVs

Efficient and Effective Generation of Test Cases for Pedestrian Detection – Search-based Software Testing of Baidu Apollo in SVL

With the growing capabilities of autonomous vehicles, there is a higher demand for sophisticated and pragmatic quality assurance approaches for machine learning-enabled systems in the automotive AI context. The use of simulation-based prototyping platforms

Dynamic Spatial Tuning Patterns of Shoulder Muscles with Volunteers in a Driving Posture

Computational human body models (HBMs) of drivers for pre-crash simulations need active shoulder muscle control, and volunteer data are lacking. The goal of this paper was to build shoulder muscle dynamic spatial tuning patterns, with a secondary focus to

DDI2022 ABSTRACT BOOK

The Vision Zero Handbook

Is the major source for everyone working with Vision Zero.

Brings together all the major topics of the subject in one publication.

Presents a new road safety paradigm that can be applied to many other areas.

Introduces a way of thinking about goal

Final Report: Traffic Safety Footprint

Final Report_AI Driven Mobility

FinalReport_AI Reducing Risks Of Near Incidents_PreStudy

During the spring 2021 several workshops were initiated by the AI Driven Mobility network within the focus group traffic safety. The idea was to find interesting topics where AI have a potential to improve traffic safety. Around eight suggestions on

Final Report Driver Interaction

Final Report: Trustworthy AI from a Traffic Safety Perspective

Final Report: Drone Lighting Systems: will it take off

Final Report: Exploring the impact of embodied cognition on automated driving design

Final Report: Pre-study Synthetic Scenarios

Traffic is the sum of road design, road user behavior, and their interactions. Understanding the dynamics is central to making the transport system efficient, safe, and sustainable. Viscando offers Al-enabled data-driven solutions for traffic analysis

Final Report - OpenBike-CD

We are witnessing rapid changes in the transport landscape that have resulted in a gap between the quality of data available and what is needed from stakeholders. Therefore, this pre-study aims to increase the knowledge about bicycle flow by, together with

Final Project Report - Report on the safety and traffic flow impact of mixed traffic condition

Heterogeneous project is a collaboration between VTI, Chalmers, Volvo AB and Volvo Cars to study the coupling relationship between different automated driving behaviours and manual driving behaviour. The aim of Heterogenous project is to develop methods

Interactions Between Heavy Trucks and Vulnerable Road Users—A Systematic Review to Inform the Interactive Capabilities of Highly Automated Trucks

This study investigates interactive behaviors and communication cues of heavy goods vehicles (HGVs) and vulnerable road users (VRUs) such as pedestrians and cyclists as a means of informing the interactive capabilities of highly automated HGVs. Following a

SAFETY OF COOPERATIVE AUTOMATED DRIVING: ANALYSIS AND OPTIMIZATION

New cooperative intelligent transportation system (C-ITS) applications become enabled thanks to advances in communication technologies between vehicles(V2V) and with the infrastructure (V2I). Communicating vehicles share information with each other and

PREPER dataset for safety evaluation of AI object perception in AD and ADAS

Deep learning algorithms are becoming the state-of-the-art technology used in the perception functions of AD and ADAS. With the safety assurance of level 5 AD systems the perception of the environment and especially dynamic objects becomes a central

EVALUATION OF A FRAGRANCE SYSTEM - Final Report

Driver fatigue is a major cause of car accidents, and the prevention of fatigue is a major goal in the automotive industry. To reach the goal of zero traffic-accident fatalities, developing innovative solutions to prevent fatigue is a key objective

Making overtaking cyclists safer: Driver intention models in threat assessment and decision-making of advanced driver assistance system

Introduction: The number of cyclist fatalities makes up 3% of all fatalities globally and 7.8% in the European Union. Cars overtaking cyclists on rural roads are complex situations. Miscommunication and misunderstandings between road users may lead to

Dynamic Spatial Tuning Patterns of Shoulder Muscles with Volunteers in a Driving Posture

Computational human body models (HBMs) of drivers for pre-crash simulations need active shoulder muscle control, and volunteer data are lacking. The goal of this paper was to build shoulder muscle dynamic spatial tuning patterns, with a secondary focus to

The Effect of Pre-Crash Braking on Thoracic Injuries in Frontal Impacts

Deaths caused by road traffic crashes worldwide increased from 1.15 to 1.35 million from 2000 to 2016 [1].
Passenger car occupants account for the majority of these deaths [2]. In frontal impacts, the thorax is the most frequently injured body region for

OSCCAR Newsletter October 2021