Solutions for Self-Driving Cars

Performance driving on a racetrack is a highly exciting sport. However, it is not generally accessible, as it requires advanced driving skills honed over many years. Rimac’s Driver Coach enables any driver to learn from the onboard AI system, and enjoy performance driving on racetracks using full autonomous driving at very high speeds (> 350km/h). In this session, we discuss how AI can be used to accelerate driver education and safely provide racing experiences at incredibly high speeds. We provide a deep dive into the overall development pipeline, from collecting data, to training models, to simulation testing using NVIDIA DRIVE Sim, and finally, implementing software on the NVIDIA DRIVE platform. Discover how AI technology can beat human professional race drivers.

Natural language processing (NLP) is a phenomenal AI technology with benefits for virtually any business. In this session, Jaguar Land Rover discusses its NLP research and engineering methodology, decision-making processes, and key learnings. The company’s Research and Innovation team is using NLP capabilities to improve knowledge and systems, and accelerate the development of high-quality, validated, and cutting-edge products going into production for internal and external clients. Leadership in AI, connected services, data, and software development is a key element of Jaguar Land Rover’s Reimagine strategy, and we'll start with an overview of the impact NLP can have on automotive businesses and outline current Jaguar Land Rover NLP use cases. This illustrates the power of NLP to help Jaguar Land Rover create the features, technology, and unique client experiences required to deliver its vision of modern luxury, while setting new benchmarks in quality, technology, and sustainability. Then we'll explore the development methodology established, including data preparation/cleaning, model selection, pipeline development, and monitoring/performance metrics. Key results from using BERT, CarBERT (custom domain-specific model) and GPT/Prompt Learning are discussed. Finally, we'll dive into the deployment challenges experienced while applying NLP technology to complex automotive problems and experiences using Triton Inference Server.

Stereo camera and route recognition technologies are critical for robust perception. In this session, Subaru walks through how it uses AI to enhance stereo camera recognition for more accurate object detection to prevent accidents on the road. This session also discusses Subaru’s results from performing large dataset training using GPUs on-premises and in the cloud.