← All concepts

model predictive control

Model predictive control is a planning strategy where a controller simulates the future outcomes of different action sequences using a model of the system. It picks the best first action, executes it, then repeats the entire simulation from the new state. This receding horizon approach allows flexible reactions to change guided by predicted future states.

The papers share a focus on how to build the model used for control. One combines the approach with reinforcement learning to handle whole-body balance. Another uses a world model trained on autonomously collected play data to enable dexterous manipulation. A third directly fixes a failure of standard world models to represent action consequences. Together, they show that the quality of the learned model is the decisive factor for success in complex applications.

Papers
5
Released code
0
First seen
Sept 2026
Latest
Nov 2026

5 papers in the last two months, against 0 in the two before.

Start here

Two papers to read first, in the order they came out
  1. 1HULK teaches humanoids to carry heavy loads while staying balanced

    HULK uses model predictive control to guide reinforcement learning for humanoid whole-body forceful loco-manipulation under sustained payloads.

    Oct 2026
  2. 2Minutes of supervised play bootstrap hours of autonomous robot practice

    A robot learns dexterous manipulation by mimicking minutes of human play, then autonomously practices to train a world model and guide control.

    Oct 2026

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.