hustvl/Senna

• highreadme#1

  Reposition the core value proposition in the README

  原因：

  当前

  <div align ="center">
  
  <h3> Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving </h3>
  
  Bo Jiang<sup>1</sup>, Shaoyu Chen<sup>1</sup>, Bencheng Liao<sup>1</sup>, Xingyu Zhang<sup>2</sup>, Wei Yin<sup>2</sup>, Qian Zhang<sup>2</sup>, Chang Huang<sup>2</sup>, Wenyu Liu<sup>1</sup>, Xinggang Wang<sup>1,📧</sup>
  
  <sup>1</sup> Huazhong University of Science and Technology,
  <sup>2</sup> Horizon Robotics,
  <sup>📧</sup> corresponding author
  
  </div>
  
  [](https://arxiv.org/abs/2410.22313)
  [](https://huggingface.co/rb93dett/Senna)
  </div>
  
  https://github.com/user-attachments/assets/3fd172be-d78d-47ae-867d-a473a1e6ddd6
  
  ## News

  复制粘贴的修复

  复制

  <div align ="center">
  
  <h3> Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving </h3>
  
  Bo Jiang<sup>1</sup>, Shaoyu Chen<sup>1</sup>, Bencheng Liao<sup>1</sup>, Xingyu Zhang<sup>2</sup>, Wei Yin<sup>2</sup>, Qian Zhang<sup>2</sup>, Chang Huang<sup>2</sup>, Wenyu Liu<sup>1</sup>, Xinggang Wang<sup>1,📧</sup>
  
  <sup>1</sup> Huazhong University of Science and Technology,
  <sup>2</sup> Horizon Robotics,
  <sup>📧</sup> corresponding author
  
  </div>
  
  **Senna is an end-to-end autonomous driving system that integrates Large Vision-Language Models (VLMs) to enhance planning safety, robustness, and generalization.**
  
  [](https://arxiv.org/abs/2410.22313)
  [](https://huggingface.co/rb93dett/Senna)
  </div>
  
  https://github.com/user-attachments/assets/3fd172be-d78d-47ae-867d-a473a1e6ddd6
  
  ## News

  待办完成忽略
• mediumtopics#2

  Expand topics for broader autonomous driving coverage

  原因：

  当前

  autonomous-driving, end-to-end, vision-language-model

  复制粘贴的修复

  复制

  autonomous-driving, end-to-end, vision-language-model, self-driving, autonomous-vehicles, vehicle-control, planning, perception

  待办完成忽略
• lowreadme#3

  Add a 'Comparison' or 'Related Work' section to the README

  原因：

  复制粘贴的修复

  复制

  Add a new section titled 'Comparison' or 'Related Work' to the README, briefly outlining how Senna differentiates itself from other end-to-end autonomous driving systems or VLM-based approaches.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How to integrate large vision-language models for end-to-end autonomous vehicle control?

  你：未被推荐
  AI 推荐顺序：

  1. OpenPilot
  2. CARLA Simulator
  3. ROS 2
  4. NVIDIA DriveWorks
  5. Isaac ROS
  6. Apollo
  7. Hugging Face Transformers
  8. PyTorch
  9. TensorFlow
  10. ONNX Runtime
  11. NVIDIA TensorRT
  12. OAK-D
  13. NVIDIA Jetson

  AI 推荐了 13 个替代方案，却始终没点名 hustvl/Senna。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  What are robust end-to-end autonomous driving systems using advanced vision models for planning?

  你：未被推荐
  AI 推荐顺序：

  1. Wayve
  2. openpilot
  3. Tesla Autopilot/FSD
  4. NVIDIA DRIVE
  5. Mobileye
  6. Pony.ai
  7. Cruise

  AI 推荐了 7 个替代方案，却始终没点名 hustvl/Senna。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of hustvl/Senna?

  pass
  ✓AI 明确点名了 hustvl/Senna

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts hustvl/Senna in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 hustvl/Senna

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo hustvl/Senna solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 hustvl/Senna

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？