Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC
Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC
This research presents Fast-TD-MPC, a lightweight framework inspired by dual-process theory that adaptively routes between fast policy execution and test-time planning. It achieves up to ~4x faster inference across 103 continuous control tasks while maintaining robustness comparable to the original planner under external disturbances.
The paper introduces Fast-TD-MPC, a framework combining learned world models with adaptive deliberation to achieve up to ~4x faster inference across 103 continuous control tasks while maintaining robustness under disturbances.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2609.32591v3 Announce Type: replace Abstract: Data-driven model predictive control (MPC) combines learned world models with online trajectory optimization, achieving strong performance in continuous control. However, the per-step cost of sampling and evaluating hundreds of candidate trajectories restricts deployment to control frequencies well below what real-time robotics demands. Motivated by the dual-process
Open source S2
theory of human cognition, which distinguishes between fast, intuitive processing (System 1) and slower, deliberative reasoning (System 2), we ask whether every decision requires the same degree of computational deliberation. We propose Fast-TD-MPC, a lightweight framework that adaptively routes between fast policy execution and test-time planning, reserving costly deliberation for states where it is most needed. Fa
Open source S3
st-TD-MPC delivers competitive task performance across 103 continuous control tasks while achieving up to ~4x faster inference. Under external disturbances, Fast-TD-MPC selectively falls back to planning, maintaining robustness comparable to the original planner.
Open source S4
Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC
Open source S1
Source：arXiv Robotics — research abstracts · arxiv.org