From Road to Code: Using Neurosymbolic for Sythesis and Analysis of Autonomous | Sridhar Duggirala

💬 Discord: https://discord.gg/h8NVzwnysW 💻 GitHub: https://github.com/centaurinstitute 🤝 LinkedIn: https://www.linkedin.com/company/centaur-ai-institute/ 📢 New Initiative: Neuro-Symbolic Agentic Protocol ⭐ Star us on GitHub https://github.com/centaurinstitute/neuro-symbolic-agentic-protocol — ​​📘 This week, Sridhar Duggirala will presents translating real-world driving scenes into executable simulation scenarios is essential for the safe, scalable, and cost-effective development of autonomous vehicles. While large-scale autonomous driving datasets provide rich multimodal recordings of traffic environments, they are typically distributed as raw sensor streams and frame-level annotations, making them difficult to edit, analyze, or directly deploy in simulation frameworks that require structured scenario descriptions. In this work, we present Road2Code, a neuro-symbolic framework and dataset pipeline that bridges the gap between real-world traffic data and simulation environments by compiling real-world driving scenes into executable scenario programs. We present two approaches, first that uses an intermediate text representation and uses language models to synthesize code and second uses structred decompositional approaches using temporal and geometric aspects of vehicle behaviors. We demonstrate the utility of our work by presenting various applications such as scenario augmentation, search, and question-answering tasks. Preliminary results show that textual representations are much more efficient and accurate at answering behavioral questions over a wide range of driving scenarios. 📃 Paper link: https://proceedings.mlr.press/v288/leung25a.html — 🗨️ ​Join us for an interactive session exploring Neuro-Symbolic AI, the emerging paradigm that blends the strengths of neural networks with symbolic reasoning. We will discuss how hybrid approaches can enhance generalization, interpretability, and reasoning, and how these methods are shaping the future of intelligent systems. Whether you’re a researcher, engineer, or simply curious about the cutting edge of AI, you’ll find an engaging space to learn, connect, and exchange ideas. Event Format: 🔍 Reading Group 🎙️ Panel Discussion 🧩 Tutorials/Workshop Series 💬 Research Roundtable 🛠️ Open-Source Project Review 📄 Paper Pitch 🤝 Collaboration Hour 🍵 Networking Mixer #AI #NeuroSymbolic #FutureOfAI