Stanford shares PhD defense on world models for autonomous land, sea and air exploration
StanfordAILab · x · 2026-11-09
Isaac Ward's PhD defense recording is now online, covering world models for autonomous exploration across land, sea, and sky. The accompanying infographic surveys the research line: GPU-accelerated aerodynamic world models for spacecraft rendezvous (AMS 2026), the CLOVER contrast-learning framework for onboard vision robots, best-paper-awarded resilient quadrotor learning, underwater vehicle control and wildlife tracking, the Prospect cave simulation environment, hierarchical belief world models for long-horizon assembly, and diffusion-based multimodal action distributions for aerial path planning — over a dozen papers mostly published at ICRA/IROS and related venues.
More from Embodied
- Developer builds a physical prompting controller out of OpenAI DevDay merch — paw_lean · 2026-11-09
- Robot installations hit 603k in 2025 as China holds 59%, US second — ingliguori · 2026-11-09
- Zipline raises $1.5B at $21.5B valuation to build nationwide drone delivery network — emmanuelvivier · 2026-11-09
- CoRL 2026 spotlight paper explains why VLAs fail at contact-rich tasks and how to fix them — StanfordAILab · 2026-11-09
- Nomagic chief scientist: master one industrial task first, then scale to general robots — lukas_m_ziegler · 2026-11-09
- Robot founder: supplier forgot leg joint screws, damaged his humanoid; AI visual QC is extremely useful — yongqianme · 2026-11-09