Gerard van Dijck 🇪🇺 🇳🇱’s Post

I'm happy to share that a RAND report has been published on the risks from emerging and disruptive transportation technologies. Steven Popper, Hye Min Park, Zara Fatima Abdurahaman, Jalal Awan, Joe Iacobucci, Sydney Maves, Adam Cohen, and I completed the work for The National Academies of Sciences, Engineering, and Medicine, 's National Cooperative Highway Research Program (NCHRP). In the report, we review the risks posed by four transportation technologies: #electricvehicles, #autonomousvehicles, #modmaas, and #advancedairmobility. We also provide an adaptive risk register framework for cataloguing and tracking risks over time. #mobilityondemand #mobilityasaservice #airtaxi #robotaxi #driverlessvehicles #EVs #transportation #Nationalacademies #NCHRP #BEVs https://lnkd.in/gHnWHjeA

Our report on Risks Related to Emerging and Disruptive Transportation Technologies is out! Conventional risk assessments consider the severity and likelihood of an incident occurring. However, when it comes to emerging and disruptive technologies, determining the likelihood of potential risks can be challenging due to the lack of historical data. In our project for the National Cooperative Highway Research Program (NCHRP), we developed an agile/adaptive risk management framework to assist transportation agencies, state Departments of Transportation (DOTs), and Metropolitan Planning Organizations (MPOs) in managing risks associated with the adoption of emerging and disruptive transportation technologies. We also used this framework to develop a risk register for four transportation technologies: Electric Vehicles, Connected Autonomous Vehicles, Mobility on Demand (MoD)/Mobility as a Service (MaaS), and Advanced Air Mobility. #EVs #emergingtechnologies #advancedairmobility #modmaas #transportationtechnologies #NCHRP #TRB #RAND

Thrilled to share our latest publication, "Tube-Based Model Predictive Control of an Autonomous Underwater Vehicle Using Line-of-Sight Re-Planning," in Ocean Engineering!  This work is the result of a collaborative effort with my PhD advisors, Dr. Hong Yue and Prof. Mike Grimble, whose expertise and guidance have been invaluable throughout this process. This research introduces a novel Tube-Based Model Predictive Control framework for 3D motion control of coupled and nonlinear Autonomous Underwater Vehicles (AUVs). The framework enhances system robustness against disturbances and model uncertainties while maintaining reasonable computation requirements. By integrating Line-of-Sight (LOS) re-planning it addresses input saturation challenges caused by realistic input magnitude and rate constraints.  To explore the details of our findings, access the full article here: https://lnkd.in/ewgdiAJ7.  #Research #OceanEngineering #MarineSystems #PTDF #Strathclyde #RobustControl

As a possibility for future road traffic, autonomous intersection management (AIM) has attracted significant attention. However, the issue of pedestrian crossing has always been a challenge. This research offers a new possibility: placing pedestrians in shuttles, allowing them to cross the street in batches, similar to taking a (horizontal version) elevator. Traffic will never be stopped, having great potential to reduce emissions and fuel consumption. #decarbonization Left: Separate pedestrian phase. Right: Proposed pedestrian shuttle service Paper: TR-C https://lnkd.in/dTXFvQ6Z Coauthored with Zhihong Yao Haoran Jiang Yongxiang Zhang 蒋阳升yangsheng PS: Compared to current signalized intersection (pedestrain waiting for their phase) and current AIM in literature (left), the proposed one (right) actually shortens pedestrain waiting time. Basically, pedestrains and cars are treated equally. PS: It looks crazy, but my understanding is that a scientist’s mission is to create possibilities for the future, while an engineer’s is to improve daily life.

This year, our MORE Munich Mobility Research Campus team from the Universität der Bundeswehr München was well-represented at the #IEEE Intelligent Vehicles Symposium (#IV 2024), showcasing research across multiple domains of intelligent vehicle technology. Here's a brief overview of the projects we presented: 1. Independent Near-Field Monitoring: A Novel Approach to Improve Active Safety in Autonomous Vehicles Junnan Pan, PRODROMOS SOTIRIADIS , Ferdinand Englberger 2. User Segmentation Based on Usage Frequency: A Case Study of a Multimodal Shared Micromobility in a Non-Urban Campus Environment Maryna Pobudzei, Silja Hoffmann 3. The Good, the Sparse, and the Ugly: Investigating the Impact of Corrupted HD-Map Features on Ego-Vehicle Localization Lukas Beer, Thorsten Lüttel, Mirko Maehlisch 4. Low Latency Instance Segmentation by Continuous Clustering for LiDAR Sensors Andreas Reich, Mirko Maehlisch 5. Evolutionary Image Quality Monitoring for ADAS under Adverse Weather Juan David González González, Mirko Maehlisch #IEEEIV2024 #IntelligentVehicles #AutonomousVehicles #Innovation #Research #UniversityOfTheBundeswehr

https://lnkd.in/db62r4wG 🚦📈 Ready to explore the Effect of Automated and Human-Driven Vehicles on the Performance of Intelligent Intersections? Dive into our latest research! 🛣️💡 #Transportation #AutomatedVehicles #TrafficFlow #Intersection #ASCE ASCE Publishing

Future traffic management by AI. Asking seemingly impossible questions like ‘Why do we need separate pedestrian crossing?’ Can unlock new exciting realities. Here AI manages vehicle and pedestrians equally to maximize intersection throughput.

As part of his summer tour, Robert Habeck, Federal Minister for Economic Affairs and Climate Action, stopped off at Paderborn Town Hall this morning to learn more about the NeMo.bil project 🚗, which is receiving 17.1 million euros in funding from the Federal Ministry for Economic Affairs and Climate Protection. The project aims to create an 𝗶𝗻𝗻𝗼𝘃𝗮𝘁𝗶𝘃𝗲, 𝘀𝘄𝗮𝗿𝗺-𝗯𝗮𝘀𝗲𝗱 𝗺𝗼𝗯𝗶𝗹𝗶𝘁𝘆 𝘀𝘆𝘀𝘁𝗲𝗺 that will serve as a beacon for the whole of Germany, enabling a new form of sustainable and demand-oriented passenger and freight transport in rural areas 🌱. dSPACE is a consortium partner in the project: Our task: To develop a practical and standard-compliant validation and verification (V&V) concept for the entire product development process🛠️. In addition, dSPACE is developing a concept for an interdisciplinary work package test strategy that ensures fleet validation during development by selecting suitable test instances and methods. In front of Paderborn Town Hall, our dSPACE colleagues Wanghanzhe Chen, Nora Harlammert, and Ursula Kemper showed what our contribution looks like beyond the concept work: A MicroAutoBox is integrated in the vehicles. Perception and driving functions are simulated and visualized with our #AURELION software 🖥️. Habeck showed great interest in the project and explained that what he has seen could be a big step towards a permanent solution, namely low-cost autonomous driving of small vehicles. #InnovationInMobility #SustainableTransport #AutonomousDriving #TechInnovation #dSPACE

New Paper 🎉🎉🎉 "A Generalizable D-VIO and Its Fusion With GNSS/IMU for Improved Autonomous Vehicle Localization" Abstract An autonomous vehicle must be able to locate itself precisely and reliably in a large-scale outdoor area. In an attempt to enhance the localization of an autonomous vehicle based on Global Navigation Satellite System (GNSS)/Camera/Inertial Measurement Unit (IMU), when GNSS signals are interfered with or obstructed by reflected signals, a multi-step correction filter is used to smooth the inaccurate GNSS data obtained. The proposed solutions integrate a high amount of data from several sensors to compensate for the sensors' individual weaknesses. Additionally, this work proposes a Generalizable Deep Visual Intertial Odometry (GD-VIO) to better locate the vehicle in the event of GNSS outages. The algorithms suggested in this research have been tested through real-world experimentations, demonstrating that they are able to deliver accurate and trustworthy vehicle pose estimation. Konya Technical University MPG KTUN Robotics Automation Control Research and Development Laboratory (RACLAB) IEEE Xplore IEEE Transactions on Intelligent Vehicles #raclab #ktunraclab #konyatekniküniversitesi #ktunedu  #deeplearning   #research #robotics #robots #development #computerscience #autonomousvehicles #deepvisualinertialodometry #gnss #imu #localization #sensorfusion Reference: Abdullah Yusefi, Akif DURDU, Fırat Bozkaya, Sukrucan TIGLIOGLU, Alper Yilmaz and Cemil SUNGUR, “A Generalizable D-VIO and Its Fusion with GNSS/IMU for Improved Autonomous Vehicle Localization”, IEEE Transactions on Intelligent Vehicles, Volume: 9, Issue: 1, January 2024 doi: 10.1109/TIV.2023.3316361. (SCI-E) Link:  https://lnkd.in/dRNak4Us

🚀 We're happy to support the Hi-Drive project. The European Union-funded Hi-Drive project is an ambitious initiative, aimed at advancing connected and automated driving (CAD) systems, to tackles some of the biggest challenges in autonomous vehicle development, focusing on expanding operational design domains, improving safety, and reducing reliance on human intervention. This includes: - Complex traffic including merging and exiting - Coping with adverse weather - Complex interaction with other road users including VRUs in normal traffic - Dynamic traffic rules and signs - GNSS occluded areas like tunnels It's great to help several work packages of this initiative with our drone-based naturatlistic trajectory data. Among other, our #exiD and #inD datasets are used for impact assessment, scenario and edge case detection as they cover large amounts of urban and highway scenarios. The use of these datasets by talented researchers like Marcel Sonntag, Lennart Vater, Henri Sintonen, Saeed Rahmani underscores the real-world applicability of high-quality traffic data for developing automated driving functions. One concrete example of using our data can be discovered in the paper by Marcel Sonntag, Lennart Vater, Roman Vuskov, Lutz Eckstein with the title: "Detecting Edge Cases from Trajectory Datasets Using Deep Learning Based Outlier Detection". The link to the paper can be found in the comments below 👇 🔎 Interested in learning more about how our datasets can support your projects? Reach out, and let’s explore the potential for collaboration! #HiDrive #AutomatedDriving #TrafficData #ADAS #SafetyValidation #Innovation #DroneData #ScenarioData #EdgeCase #ScenarioDetection #ImpactAssessment