DownloadAlpamayo2-Super is NVIDIA’s flagship open reasoning Vision-Language-Action (VLA) model for autonomous vehicle development, designed to accelerate Level 4 robotaxi and autonomous driving systems. Built on the NVIDIA Cosmos platform, it enables vehicles to perceive, reason, plan, and generate driving actions using human-like decision making rather than relying solely on predefined rules. The model processes multi-camera video, navigation signals, and driving context to produce driving trajectories alongside interpretable Chain-of-Causation reasoning, improving transparency for validation and safety analysis. Alpamayo2-Super is part of the broader NVIDIA Alpamayo ecosystem, which also includes simulation frameworks, reinforcement learning infrastructure, datasets, and physical AI tools for end-to-end autonomous vehicle development. It integrates with AlpaGym for closed-loop reinforcement learning and Cosmos-Dreams for large-scale driving simulation, allowing developers to train, evaluate,
Features
- 32B-parameter Vision-Language-Action reasoning model
- Processes multi-camera video and driving context
- Generates driving trajectories with Chain-of-Causation reasoning
- Designed for Level 4 robotaxi and autonomous vehicle development
- Integrates with AlpaGym for closed-loop reinforcement learning
- Works with Cosmos-Dreams for large-scale driving simulation
- Provides interpretable reasoning for safety validation
- Part of NVIDIA's open Alpamayo autonomous driving ecosystem
Project Samples
