Abul Bashar Raz’s Post

Discover how Gaussian Splatting revolutionizes AV simulation! This cutting-edge technique enhances the realism of autonomous vehicle simulations by efficiently rendering complex environments with high fidelity. Learn how Gaussian Splatting can improve safety and performance in autonomous driving technology. #gaussiansplatting #avsimulation #autonomousvehicles #selfdrivingcars #simulation #automotive #machinelearning #deeplearning #computervision #technology #rendering #highfidelity #complexenvironments #cuttingedge #futureoftransportation #autonomousdriving #ai #artificialintelligence #vehicletechnology #simulationtechnology

Explore the new paper, "NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking." This research introduces NAVSIM, a novel approach for evaluating autonomous vehicle performance using simulation-based metrics. The paper provides a comprehensive analysis of NAVSIM's methodology, which includes simplified bird's-eye view abstractions and a multi-dimensional metric called the PDM Score. These techniques enable efficient, open-loop metric computation while maintaining strong alignment with closed-loop evaluations. For developers and researchers in autonomous driving and AI, this paper is a valuable resource. It offers insights into improving the accuracy and reliability of autonomous vehicle simulations. Read the full paper here: [https://lnkd.in/gABwp37E]

Check out our latest scientific article entitled "RNN-based linear parameter varying adaptive model predictive control for autonomous driving" 😀  Proposing a predictive control approach for autonomous driving, the article makes use of the LPV theory combined with improved metahuristic optimization and recursive learning. Published in International Journal of Systems Science.

🚗 Excited to share a new research paper on autonomous decision-making! Check out the latest blog post introducing the Driver to Evaluation dataset (D2E) - a comprehensive dataset covering driver states, vehicle conditions, and human evaluation scores. This dataset goes beyond traditional vehicle and environmental data, providing crucial insights into human factors. Dive into the details at https://bit.ly/3xeFkhg to learn more about how D2E is shaping the future of data-driven decision-making in autonomous driving. #AutonomousDriving #DataScience #ResearchPublication

Last week I had the opportunity to attend the Simulation, Testing & Validation for AD conference in Stuttgart, where I was able to contribute to the discussion on the importance of understanding our human behavior for the successful implementation of autonomous driving. Not only for the future human-machine interface, but especially to build the necessary resilience into the vehicle to deal with the complexity of our urban scenarios! Why don't we use our own resilience as a benchmark for driverless operations? If you want to know a bit more about it, check it out my latest article, where I briefly describe the topic. The shift to Autonomous Driving from a human perspective https://lnkd.in/eDGup25z Automotive IQ Rebecca Cavanagh Alice Andrews #AutonomousDriving #humanfactors ##SafetyManagementSystem

Not only looking at zero emissions electrical transformation, but also, safety increasing solutions. This innovative approach could enhance safety and performance in autonomous vehicles, making them more adaptable to challenging road conditions. Researchers at Stanford University have developed an autonomous DeLorean car that can drift and drive sideways. The project aims to improve self-driving technology by teaching cars to handle extreme situations. The DeLorean, famous for its role in the “Back to the Future” movies, was modified with sensors and algorithms to perform controlled drifts. The team used reinforcement learning to train the car, allowing it to execute precise maneuvers. https://lnkd.in/d92fMZXj

I'm excited to share our latest paper "Optimal Motion Design for Autonomous Vehicles With Learning Aided Robust Control" published in the most recent issue of IEEE Transactions on Vehicular Technology (C1 ranked). The paper is open access and available for download here: https://lnkd.in/gtMBwyeA A big congratulations to my talented Ph.D. student, Attila Lelkó, for his hard work on this study! This paper presents a control design framework for the integration of robust controller and reinforcement learning-based (RL) control agent. The proposed integration method is applied to motion control of autonomous road vehicles, providing safe motion. The RL-based control agent is used to determine the steering angle and reference velocity of the vehicle to achieve high-performance motion. The effectiveness of the proposed control through simulation examples with comparisons to predictive control methods is illustrated. Moreover, the applicability of the method through a real-life test scenario on a small-scaled test vehicle is demonstrated.

🚗 𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗿𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗮𝗻𝗱 𝘁𝗲𝘀𝘁 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗳𝗼𝗿 𝗮𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗱𝗿𝗶𝘃𝗶𝗻𝗴: 𝗣𝗼𝘄𝗲𝗿𝗳𝘂𝗹 𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝘀 𝗳𝗿𝗼𝗺 𝗚𝗲𝗻𝗲𝗦𝘆𝘀 𝗘𝗹𝗲𝗸𝘁𝗿𝗼𝗻𝗶𝗸 𝗚𝗺𝗯𝗛 🚗 Inertial reference systems are critical for testing autonomous vehicles, providing a vital reference model to verify driving performance during the development of autonomous vehicle technologies. Reflected satellite signals from structures, bridges and tunnels all result in significant jumps in position estimates. Pure #GNSS systems therefore lack reliability on public roads. 𝗚𝗲𝗻𝗲𝗦𝘆𝘀 𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻𝘀 𝗳𝗼𝗿 𝗮𝘂𝘁𝗼𝗻𝗼𝗺𝗼𝘂𝘀 𝗱𝗿𝗶𝘃𝗶𝗻𝗴 ✅ Our inertial reference system #ADMA for autonomous vehicle testing provides high-precision data even in the case of strong GNSS interference. ✅ Different ADMA variants, our ADMA-PP post-processing software, ADMA Add-Ons and Options allow you to flexibly put together the ideal inertial navigation system for your requirements. Combined with the 4adrivingRobot from 4activeSystems and the steering robot SDrive - Stähle Autopilot from STÄHLE GmbH, this solution is completely conform with all high-standard (#NCAP, #UNECE, ...) protocols. 👉 Further information can be found here: https://loom.ly/WcFocBs #DTA #ADAS #automotivetesting #vehicledynamics #MeasuringShouldBeEasy AMFD - Auto Mobil Forschung Dresden GmbH

Autonomous driving is set to revolutionize future mobility by improving traffic efficiency, convenience, and safety. However, guaranteeing safety across diverse road environments and unpredictable scenarios is critical to its progress. Real-world testing presents significant challenges, making scenario-based virtual simulations an essential solution for verifying system reliability. In mixed traffic conditions, recreating and analyzing accident scenarios is crucial for assessing autonomous systems. We are pleased to share a white paper that underscores the importance of scenario-based safety verification and highlights how MORAI’s simulation technology enhances the reliability of autonomous systems. #AutonomousDriving #FutureMobility #SimulationTechnology #Safety #MORAI.

𝐀𝐍 𝐞𝐱𝐭𝐞𝐧𝐭𝐢𝐯𝐞 𝐆𝐮𝐢𝐝𝐞 𝐨𝐧 𝐀𝐮𝐭𝐨𝐦𝐨𝐭𝐢𝐯𝐞 𝐒𝐞𝐦𝐢𝐜𝐨𝐧𝐝𝐮𝐜𝐭𝐨𝐫 (𝐋𝐚𝐭𝐞𝐬𝐭 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧) #automotivesemiconductor The development of autonomous vehicles presents a unique opportunity for semiconductor manufacturers to participate in an innovative technological shift. The future of transportation is expected to be influenced significantly by businesses that can provide reliable, high-performance, and energy-efficient semiconductor solutions suited to the unique requirements of autonomous driving