3 Comments
User's avatar
Emanuel Maceira's avatar

The planning layer insight is critical and underappreciated. Exposing a robot's reasoning process isn't just about safety -- it's the key to fleet-scale operability. When you're managing hundreds of edge devices across warehouses or construction sites, you need inspectable decision chains for debugging, compliance, and OTA model updates. The real scaling question isn't whether VLAMs can generalize, it's whether the connectivity and governance infrastructure exists to deploy, monitor, and update them across heterogeneous environments with unreliable networks. That's where eSIM-based multi-carrier failover and edge orchestration become as important as the models themselves.

Michael Spencer's avatar

Wayve is probably your best investment yet has a VC.

Sanjeev Arora's avatar

Great coverage on the VLAM topic that aligns well with the progress on overall "Spatial Intelligence" space. Basis like NeRF: Neural Radiance Fields paper - that readers might find useful -

July 2025 - Emerging Technology — Spatial Intelligence: Unlocking 3D Understanding in AI - https://sanjeevarora.substack.com/p/emerging-technology-spatial-intelligence-unlocking-3d-understanding-in-ai