MIT Opens Full Visual Navigation for Autonomous Vehicles Course, Perception to Control
blaizedsouza · x · 2026-09-20
MIT's 16.485 Visual Navigation for Autonomous Vehicles (VNAV) course has all materials publicly available, covering the full perception-to-control stack for robotics, drones and self-driving systems.
Topics include:
- 2D and 3D vision for navigation
- Visual and visual-inertial odometry for state estimation
- Place recognition and SLAM for localization and mapping
- Trajectory optimization for motion planning
- Learning-based perception in geometric settings
Slides and notes are free at vnav.mit.edu.
More from Companies & People
- Higher ed must teach AI and cybersecurity fluency, argues Chuck Brooks — ChuckDBrooks · 2026-09-20
- Researcher advice: pick the nicest PIs, not the most famous ones — skoularidou · 2026-09-20
- Superhuman CEO on promotion criteria flipping mid-career as employers quietly reward AI usage — cen6wkf · 2026-09-20
- Meta's Muse Gets Its First-Ever TV Ad, Airing During the Big Game — ccerrato147 · 2026-09-20
- 10 free AI certificates in 2026, from Google Skills to Hugging Face — socialwithaayan · 2026-09-20
- MIT Media Lab to Host ScienceClaw Hackathon on Building an Internet of Agents for Science — ProfBuehlerMIT · 2026-09-20