The reviewed record of science sign in
Pith

arxiv: 2412.17118 · v1 · pith:CC7UDQC4 · submitted 2024-12-22 · cs.RO · cs.SY· eess.SY

Transformer-Based Model Predictive Path Integral Control

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:CC7UDQC4record.jsonopen to challenge →

classification cs.RO cs.SYeess.SY
keywords controltransformermppicomputationalefficiencymppisamplesequencetransformer
0
0 comments X
read the original abstract

This paper presents a novel approach to improve the Model Predictive Path Integral (MPPI) control by using a transformer to initialize the mean control sequence. Traditional MPPI methods often struggle with sample efficiency and computational costs due to suboptimal initial rollouts. We propose TransformerMPPI, which uses a transformer trained on historical control data to generate informed initial mean control sequences. TransformerMPPI combines the strengths of the attention mechanism in transformers and sampling-based control, leading to improved computational performance and sample efficiency. The ability of the transformer to capture long-horizon patterns in optimal control sequences allows TransformerMPPI to start from a more informed control sequence, reducing the number of samples required, and accelerating convergence to optimal control sequence. We evaluate our method on various control tasks, including avoidance of collisions in a 2D environment and autonomous racing in the presence of static and dynamic obstacles. Numerical simulations demonstrate that TransformerMPPI consistently outperforms traditional MPPI algorithms in terms of overall average cost, sample efficiency, and computational speed in the presence of static and dynamic obstacles.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Robust Path Tracking for Vehicles via Continuous-Time Residual Learning: An ICODE-MPPI Approach

    cs.RO 2026-05 unverdicted novelty 6.0

    ICODE-MPPI uses Input Concomitant Neural ODEs to learn residual dynamics and reduce vehicle cross-tracking error by up to 69% under disturbances compared with standard MPPI.