_index.org

Sliding Mode UAV Control

Last edited: August 8, 2025

Problem: we have a drone in an elevator; the elevator moves and hence the drone has a non-internal reference frame.

For a dynamical system which has uncertainty term which is not observable to the controller, one could control for position and velocity well with a Sliding Mode Controller

Sliding mode observer controls for the disturbance in the non-inertial reference frame.

slope (statistics)

Last edited: August 8, 2025

Smith 20??

Last edited: August 8, 2025

HSVI

One-Liner

“impact of approximation decreases as steps from the root node”

Novelty

  • combined alpha-vector and forward heuristics to guide search of belief states before backup
  • 100x times faster in PBVI
  • scales to huge environments

Goal: minimize “regret” (difference until optimal policy)

Novelty HSVI 2

  • Projected the upper bound onto a convex hull (HSVI2: via approximate convex hull projection)
  • uses blind lower bound

Notable Methods

Key Figs

New Concepts

Notes

smooth function

Last edited: August 8, 2025

a function is called smoo

Social Learning

Last edited: August 8, 2025

Social Learning is the property of learning with other agents in your environment.

  • learning from feedback
  • human ai coordination
  • social learning
  • adversarial training