--This study investigates how autonomous vehicle (A V) technology is perceived by pedestrians and bicyclists in Pittsburgh. Using survey data from over 1200 respondents, the research explores the interplay between demographics, A V interactions, infrastructural readiness, safety perceptions, and trust. Findings highlight demographic divides, infrastructure gaps, and the crucial role of communication and education in A V adoption. Autonomous vehicle (A V) integration into urban settings has sparked serious concerns about how these vehicles may affect vulnerable road users, especially pedestrians and cyclists. It is critical to comprehend the comfort, safety, and views of these road users as autonomous vehicles (A Vs) are tested and used more frequently in places like Pittsburgh. Sharing the road with autonomous vehicles poses special risks for pedestrians and cyclists because of their exposure and lack of physical protection. Among these issues are worries regarding A Vs' capacity to recognize and react to their motions, especially in situations with a lot of traffic or unpredictability. Furthermore, concerns and discomfort may be exacerbated by the inadequacy of the current urban infrastructure to facilitate the safe coexistence of A Vs and non-motorized users.

Leveraging multimodal data from intersections, road sections, and urban villages, combined with high-precision radar and computer vision algorithms, the dataset emphasizes high-density interaction events. By systematically reviewing VRU dataset advancements and technical challenges, this study provides theoretical and practical guidance for future dataset development. As technology and ecosystems evolve, VRU datasets will play an increasingly vital role in autonomous driving safety research, laying a robust foundation for global transportation safety and intelligent traffic systems.Dataset Name Location Setting Composition Collection Method Purpose Mix-t India Urban roads Mixed traffic flow Roadside camera Mixed flow modeling BIWI Hotel Switzerland Entrance/Exit Pedestrians Roadside camera Behavior modeling BIWI ETH Switzerland Campus roads Pedestrians Roadside camera Behavior modeling Crowds UCY/Zara USA Campus and urban roads Pedestrians Roadside camera Behavior modeling Ko-PER Germany Urban intersections Mixed traffic flow Roadside camera Behavior modeling VRU Germany Urban intersections Mixed traffic flow Roadside camera Behavior modeling DUT / CITR Germany Campus roads Vehicles and pedestrians Drone Behavior modeling Stanford Drone USA Campus Mixed traffic flow Drone Behavior modeling LUMPI Germany Signalized intersections Mixed traffic flow Radar, roadside camera Traffic safety analysis UniD Germany Campus roads Mixed traffic flow Drone Behavior prediction INTERACTION USA/China Intersections Vehicles Drone, roadside Behavior modeling V2X-Seq China Intersections Mixed traffic flow Radar, roadside camera Autonomous driving testing InD? Germany Intersections Mixed traffic flow Drone Interaction behavior ApolloScape? China Urban roads Mixed traffic flow Radar, roadside camera Autonomous driving TRAF India Intersections Mixed traffic flow Drone Behavior modeling Waymo USA Urban roads Mixed traffic flow Onboard radar Autonomous driving testing IDD-X India Intersections Mixed traffic flow Onboard camera Behavior modeling Kitti? Germany Urban roads Mixed traffic flow Onboard camera, radar Autonomous driving testing SinD? China Intersections Mixed traffic flow Onboard camera, radar Autonomous driving testing Table 1: Summary of Dataset Information 3. Dataset Construction In this section, we outline the detailed process of dataset construction, covering location selection, data collection, data processing, map generation, and other key aspects.

Public urban spaces like streetscapes and plazas serve residents and accommodate social life in all its vibrant variations. Recent advances in Robotics and Embodied AI make public urban spaces no longer exclusive to humans. Food delivery bots and electric wheelchairs have started sharing sidewalks with pedestrians, while diverse robot dogs and humanoids have recently emerged in the street. Ensuring the generalizability and safety of these forthcoming mobile machines is crucial when navigating through the bustling streets in urban spaces. In this work, we present MetaUrban, a compositional simulation platform for Embodied AI research in urban spaces. MetaUrban can construct an infinite number of interactive urban scenes from compositional elements, covering a vast array of ground plans, object placements, pedestrians, vulnerable road users, and other mobile agents' appearances and dynamics. We design point navigation and social navigation tasks as the pilot study using MetaUrban for embodied AI research and establish various baselines of Reinforcement Learning and Imitation Learning. Experiments demonstrate that the compositional nature of the simulated environments can substantially improve the generalizability and safety of the trained mobile agents. MetaUrban will be made publicly available to provide more research opportunities and foster safe and trustworthy embodied AI in urban spaces.

The current approach to connected and autonomous driving function development and evaluation uses model-in-the-loop simulation, hardware-in-the-loop simulation, and limited proving ground work followed by public road deployment of beta version of software and technology. The rest of the road users are involuntarily forced into taking part in the development and evaluation of these connected and autonomous driving functions in this approach. This is an unsafe, costly and inefficient method. Motivated by these shortcomings, this paper introduces the Vehicle-in-Virtual-Environment (VVE) method of safe, efficient and low cost connected and autonomous driving function development, evaluation and demonstration. The VVE method is compared to the existing state-of-the-art. Its basic implementation for a path following task is used to explain the method where the actual autonomous vehicle operates in a large empty area with its sensor feeds being replaced by realistic sensor feeds corresponding to its location and pose in the virtual environment. It is possible to easily change the development virtual environment and inject rare and difficult events which can be tested very safely. Vehicle-to-Pedestrian (V2P) communication based pedestrian safety is chosen as the application use case for VVE and corresponding experimental results are presented and discussed. It is noted that actual pedestrians and other vulnerable road users can be used very safely in this approach.

Cycling is an increasingly popular method of transportation for sustainability and health benefits. However, cyclists face growing risks, especially when encountering semi-trailer trucks. This study aims to reduce the number of truck-cyclist collisions, which are often caused by semi-trailer trucks making right-hook turns and poor driver attention to blind spots. To achieve this, we designed a visual-based blind spot warning system that can detect cyclists for semi-trailer truck drivers using deep learning. First, several greater than 90% mAP cyclist detection models, such as the EfficientDet Lite 1 and SSD MobileNetV2, were created using state-of-the-art lightweight deep learning architectures fine-tuned on a newly proposed cyclist image dataset composed of a diverse set of over 20,000 images. Next, the object detection model was deployed onto a Google Coral Dev Board mini-computer with a camera module and analyzed for speed, reaching inference times as low as 15 milliseconds. Lastly, the end-to-end blind spot cyclist detection device was tested in real-time to model traffic scenarios and analyzed further for performance and feasibility. We concluded that this portable blind spot alert device can accurately and quickly detect cyclists and have the potential to significantly improve cyclist safety. Future studies could determine the feasibility of the proposed device in the trucking industry and improvements to cyclist safety over time.

Market-leading provider of vehicle safety systems Brigade Electronics has launched a new predictive collision detection system. Sidescan Predict is the next generation of collision avoidance systems. Supported by the Knowledge Transfer Partnership initiative with Cambridge University, the aim was to develop a cost-effective and reliable collision detection system that can intelligently discriminate potential collisions and warn the driver with sufficient time for intervention – a predictive system. Having been in development and undergone rigorous testing for more than seven years, including 10,000 hours of research, Sidescan Predict had its first trials in 2020 receiving excellent driver feedback. Drivers noticed a significant reduction in the risk of collision with both vulnerable road users and static objects.

After spending years looking into 30 separate Tesla crashes, this week federal safety officials finally took a step toward cracking down on the electric carmaker. On Monday, the National Highway Traffic and Safety Administration announced an investigation into Autopilot, Tesla's driver assistance system, which allows the vehicle to manage certain highway tasks like changing lanes and moderating speed, and which numerous drivers have treated like a fully autonomous driving system (sometimes for the entertainment of their social media followers). NHTSA's new investigation has a narrow focus: It will seek to determine why Teslas with Autopilot engaged have crashed at least 11 times into stationary first-responder vehicles. Depending on what the agency concludes, NHTSA could declare a "defect" in Autopilot, insisting that Tesla correct it or else face a hefty fine. NHTSA's power over the automotive sector shouldn't be underestimated; the agency's investigation in Takata's faulty airbags helped push the multi-billion dollar company into bankruptcy in 2017.

Whether we like it or not, driverless cars seem to be on their way. It might still be many years until the technology is ubiquitous on our roads, but when automated vehicles (AVs) do arrive, they're going to shake things up in a huge way. One of the biggest benefits AVs are expected to bring is improvements to road safety. Human error is the biggest cause of road trauma -- remove human drivers from the equation and the number of those injured or killed on our roads should decrease significantly. As vulnerable road users, cyclists can rightly feel a sense of excitement at the prospect of driverless vehicles.

Annotating automotive radar data is a difficult task. This article presents an automated way of acquiring data labels which uses a highly accurate and portable global navigation satellite system (GNSS). The proposed system is discussed besides a revision of other label acquisitions techniques and a problem description of manual data annotation. The article concludes with a systematic comparison of conventional hand labeling and automatic data acquisition. The results show clear advantages of the proposed method without a relevant loss in labeling accuracy. Minor changes can be observed in the measured radar data, but the so introduced bias of the GNSS reference is clearly outweighed by the indisputable time savings. Beside data annotation, the proposed system can also provide a ground truth for validating object tracking or other automated driving system applications.

One of the biggest concerns about driverless vehicles is that their actions will be difficult to predict, especially for pedestrians, cyclists and other vulnerable road users. But Jaguar Land Rover has suggested this might not be an issue in the future with the development of a system that notifies everyone outside the car which way the vehicle is about to go. The concept projects the direction of travel onto the road ahead, which the car maker says will help people develop a level of trust in autonomous technology. 'After you...': Jaguar Land Rover believes autonomous cars will be able to notify pedestrians which way they are going to go to prevent collisions Jaguar Land Rover has given plenty of thought to the safety of future vehicles in recent months. Last October it worked with Guide Dogs for the Blind to develop the best sound for electric vehicles to make so they can be heard by those with visual impairments.