ad-foundation-models

Official

Empower AD research with advanced foundation models and safety insights.

AuthorRoboSafe-Lab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides comprehensive knowledge on foundation models for autonomous driving, including VLAs, E2E driving, LLM/VLM planning, and safety implications.

Core Features & Use Cases

  • Understanding VLAs: Deep dive into Vision-Language-Action models, including RT-2, OpenVLA, and DriveVLM.
  • E2E Autonomous Driving: Explore evolution, key methods like UniAD and SparseDrive, and evaluation benchmarks.
  • Safety Implications: Grasp critical challenges like hallucination, latency, and distributional shift in foundation models.
  • Safety Architecture: Learn about patterns like Foundation Model + Safety Filter and Hierarchical with Safety Monitor.
  • Research Frontiers: Identify open problems in scaling laws, pre-training, and compositional generalization.

Quick Start

Use the ad-foundation-models skill to get an overview of the critical safety challenges in deploying foundation models in AD systems.

Dependency Matrix

Required Modules

None required

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ad-foundation-models
Download link: https://github.com/RoboSafe-Lab/ad-safety-research-skills/archive/main.zip#ad-foundation-models

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.