Shweta Vetal

#Integration and #Testing the complex system in Software Defined Vehicles (#SDV) context is the biggest challenge to be solved by OEMs and Software suppliers!

1

Upgrading a vehicle's features can be as simple as swapping out a hard drive! Consumers are demanding more complex vehicle features, and OEMs need adaptable platforms to keep up. Aptiv Open Server Platform (OSP) is a high-performance compute solution that evolves with the vehicle. When the OSP ages and can't run the latest applications or updates, the owner can easily exchange it at a dealership for a newer, more capable version — without altering the rest of the vehicle's architecture.

13

With the recent layoffs in various Autonomous driving companies (latest was Motional, wish all friends there all the best in securing new opportunities), here’s how I read the market: It was the trend 3~4 years ago for OEMs & Tier suppliers to work and invest money on ADAS as they saw it the future for selling their cars/products, and they thought that creating a fully autonomous vehicle (L3+ or even Level 4) was just a small step of iterative improvement to the current Level 2 ADAS systems they had and maybe with burning more money and dragging in huge resources they would fastly achieve it. Here’s what they discovered: - The laws/standards for developing and launching such cars (at least in Europe is not ready) - Current technologies (Cameras, sensors) are good but putting them together and processing these huge data to act like a ‚human driver‘ is very expensive and complex to do. - Engineering automotive resources were also a little behind in Tech areas to quickly adapt to the fast paces of other Tech. silicon valley companies. - Robotaxis as a business model is very hard to achieve profitability taking into account that they need a huge fleet of cars (every car is equipped with 50+ K system + car price) running almost 24 hours with the addition of the need of Technical support/Remote guidance and regular maintenance (done by a human, like charging or even checking the tire pressure), with all these costs on top to compete with human taxi drivers or Uber like apps will not be easy. Accordingly the companies were split to 3 streams: 1. Huge Cash companies (such as Waymo supported by Google) who still burn money in this direction hoping it will dominate the market when other players are out of money. 2. companies who decided to slow the pace and investment to achieve reasonable targets (maybe not as fast as it was planned) 3. companies who gave up and shutdown (like my beloved Argo) Again this is a personal opinion and how I read the situation and hope the market of Automotive is going to heal soon and recover. #ADAS #AutonomousDriving

355

15 Comments

News about ADS - Jun 17, 2024: 😢 1) Waymo driverless vehicle contacts with a tele pole in an alley near 7th Avenue and Roosevelt Street 8 mph when pulling over in AZ on May 21, 2024 -> SW recall on Jun 12, 2024 https://lnkd.in/g9xQScah https://lnkd.in/gC_MYrE2 https://lnkd.in/g8zAxcQZ Root cause: "SW map" seems not a real root cause-> possible perception issue 2) Real robot driving a car - robot driver Misachi 😁 https://lnkd.in/ggpB_u3G 3) "NVIDIA Research Wins CVPR Autonomous Grand Challenge for End-to-End Driving" 👍 https://lnkd.in/ginE6CWF 4) Tier IV & Suzuki partner up for ADS 👍 https://lnkd.in/gTzvTrEJ 5) A sad story - but what happens to the driver who used the phone - too unresponsible 😔 - Tesla with FSD engaged from AP News https://lnkd.in/gCS9eXuZ

1

The automotive industry's embrace of electronic systems is accelerating rapidly, leading to vehicles with enhanced connectivity, security, driveability, and comfort compared to previous models. This expansion brings a surge in electronic control modules (ECUs) and complex software, necessitating a robust development process to ensure quality and efficiency while eliminating bugs. Enter the V-cycle, the standard software development process in automotive. It divides development into two phases: requirement analysis, design, and change management on the left, and verification and validation on the right. Key Steps: 1. Function Requirements: Define what the software should do. 2. Function Development: Design and test functionality using model-based development. 3. Software Development: Code the software, considering functionality and optimization. 4. Software Integration: Combine and test all modules at the system level. 5. Function Integration: Test the developed function in the vehicle. 6. Function Calibration: Fine-tune parameters for optimal performance. Advantages of the V-cycle include simplicity, clear roles, and efficiency with clear requirements. However, it lacks flexibility in emergencies and doesn't provide early prototypes, and problem resolution during testing phases can be unclear. #AutomotiveTech #SoftwareDevelopment #VCycle

151

6 Comments

🔆Thrilled to share a milestone 🔆 I had the incredible opportunity to present at SAEINDIA International Mobility Conference 2024, where I presented on the electric powertrain NVH challenges and solutions. If I can use one line to summarize the work, then it would be “Solving electric powertrain NVH challenges using single simulation tool, GT-SUITE, that allows performing the complete e-NVH CAE analysis workflow starting from electromagnetic motor design to Acoustic analysis of structural housing (e-Motor+ Inverter+ MBD+ Structural/Surface Vibrations + Acoustic @ microphone locations) under one roof.  Also, it was very exciting to present the use of in-built GT-SUITE’s Machine Learning Assistant for applying pre-CAE methodology for early design of motor. A heartfelt thank you to the organizers, attendees, and everyone who engaged in the discussions—your questions and insights truly added value. Moreover, thanks to SAE team for publishing this topic as a technical paper. Looking forward to continuing the conversations and applying these learnings to electric powertrain. https://lnkd.in/d3sjgNy3 Nakul Joshi #GTSUITE #eNVH #epowertrain #electricpowertrain #NVH #CAE

84

3 Comments

Electric vehicles are not zero emissions vehicles! For example, a BEV pickup truck has higher life cycle GHG than an HEV sedan. A new paper that I co-authored shows that for a given vehicle size, a BEV is only about 15%-30% lower GHG than a HEV. Regulations that count BEVs as "zero" are NOT performance-based and do NOT provide the right incentives to maximize GHG benefits. https://lnkd.in/gDV8X7vG

218

8 Comments

Turns out the GMC HUMMER EV is as smart as it is tough! From Extract Mode to Watts to Freedom, here are 5 features that prove it’s more than just muscle: https://lnkd.in/ghcrHzjc #IWorkForGM

1

Introducing Auto-Llama: A Specialized LLM for Automotive Safety Auto-Llama is an advanced language model built on Llama 3.1-8B-Instruct, meticulously fine-tuned using data from key automotive safety standards such as ISO 21434, ISO 21448, and ISO 26262. Designed for automotive professionals, it provides precise, domain-specific insights to support systems engineering, safety assurance, and regulatory compliance. You can explore Auto-Llama today on Hugging Face by visiting Auto-Llama_Preview(https://lnkd.in/gBDzDzRA). It’s currently in Preview mode, and your feedback is invaluable to refining its capabilities. #AI #AutomotiveSafety #ISO21434 #ISO21448 #ISO26262

4

Delve into the world of Advanced Driver Assistance Systems (ADAS) and discover how they're reshaping the automotive landscape. From adaptive cruise control to lane departure warning systems, ADAS technologies are revolutionizing vehicle safety and driving experiences. Learn how these systems work and their impact on the automotive industry. #ADAS #Automotive #SafetyTech #Innovation #VehicleTechnology

13

Could not believe it when I read the news about GM yesterday, which I have summarized below. General Motors (GM) is stepping back from its robotaxi plans, citing high costs and tough competition in the autonomous vehicle space. This shift comes after a rocky year for Cruise, GM’s self-driving unit. Cruise hit a major roadblock in 2023 when one of its vehicles injured a pedestrian, triggering a pause in operations, regulatory reviews, and a legal settlement. Despite resuming testing in California and striking a deal with Uber to deploy its robotaxis, GM has decided the financial and operational challenges are too steep right now. Instead, the company will combine Cruise’s team with GM’s other technical groups to focus on driver assistance tech, like its Super Cruise and Ultra Cruise systems, which are already being used in consumer vehicles. While this may seem like a step back, it’s also an opportunity for GM to double down on the technologies that are closer to market and can make driving safer for millions of people today. By focusing on practical solutions, GM could set itself up for long-term success in autonomous tech. All this being said, it is being reported that the decision has left many Cruise employees feeling blindsided and uncertain about their future. Clear communication and support from leadership will be crucial to maintaining morale and ensuring a smooth transition. What do you think—are incremental advancements like driver assistance systems the smarter play for now, or should companies keep pushing full steam ahead on robotaxis? #GM #Cruise #GeneralMotors #robotaxi #autonomousvehicles #ADAS

16

10 Comments

Car tire has an issue, luckily with this break out diagram I can find and fix the issue

3

1 Comment