US , August 4, 2026 - NVIDIA has launched Alpamayo 2 Super, a new artificial intelligence (AI) foundation model for autonomous vehicles (AVs), which is set to help developers build safer and more transparent self-driving systems. The new model, which is available for commercial use under an open license, is designed to handle complex and unpredictable driving situations that autonomous vehicles are struggling with. The company said that the new model is part of the Alpamayo family of open reasoning models, which it has branded as the most widely adopted open reasoning models for autonomous driving on Hugging Face. The model is built on NVIDIA Cosmos 3 Super Reasoner and has been post-trained using reinforcement learning to improve reasoning across multiple autonomous driving tasks, according to the company. NVIDIA added that Alpamayo 2 Super processes full 360-degree camera views from the front, sides, and rear of a vehicle, allowing it to better understand lane changes, highway merges, unprotected turns, and complex intersections. For every driving scenario, the model generates five outputs, including a planned vehicle trajectory, a chain-of-causation explanation describing its reasoning, a driving intent such as yielding or changing lanes, automated reasoning labels for training datasets, and visual question answering linked to specific regions in camera images, according to NVIDIA. “Handling these long‑tail events takes more than just object detection and motion prediction. AVs must understand the situation, reason about cause and effect, choose the right action and turn that decision into a safe, comfortable path — all in real time and in a way developers can inspect, validate and trust,” the company stated. “Alpamayo 2 Super is part of NVIDIA’s growing collection of open models, datasets and tools for autonomous driving, expanding access, strengthening competition, giving developers greater control and supporting safer, more transparent AV deployment,” it added.