Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Jiawei, Gong, Xun, Fang, Fen, Yang, Muli, Qu, Bohao, Hu, Yunfeng, Chen, Hong, Yang, Xulei, Guo, Qing
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910115905404928
author Liu, Jiawei
Gong, Xun
Fang, Fen
Yang, Muli
Qu, Bohao
Hu, Yunfeng
Chen, Hong
Yang, Xulei
Guo, Qing
author_facet Liu, Jiawei
Gong, Xun
Fang, Fen
Yang, Muli
Qu, Bohao
Hu, Yunfeng
Chen, Hong
Yang, Xulei
Guo, Qing
contents Most Human-Machine Interaction (HMI) research overlooks the maneuvering needs of passengers in autonomous driving (AD). Natural language offers an intuitive interface, yet translating passenger open-ended instructions into control signals, without sacrificing interpretability and traceability, remains a challenge. This study proposes an instruction-realization framework that leverages a large language model (LLM) to interpret instructions, generates executable scripts that schedule multiple model predictive control (MPC)-based motion planners based on real-time feedback, and converts planned trajectories into control signals. This scheduling-centric design decouples semantic reasoning from vehicle control at different timescales, establishing a transparent, traceable decision-making chain from high-level instructions to low-level actions. Due to the absence of high-fidelity evaluation tools, this study introduces a benchmark for open-ended instruction realization in a closed-loop setting. Comprehensive experiments reveal that the framework significantly improves task-completion rates over instruction-realization baselines, reduces LLM query costs, achieves safety and compliance on par with specialized AD approaches, and exhibits considerable tolerance to LLM inference latency. For more qualitative illustrations and a clearer understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08031
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles
Liu, Jiawei
Gong, Xun
Fang, Fen
Yang, Muli
Qu, Bohao
Hu, Yunfeng
Chen, Hong
Yang, Xulei
Guo, Qing
Robotics
Computer Vision and Pattern Recognition
Most Human-Machine Interaction (HMI) research overlooks the maneuvering needs of passengers in autonomous driving (AD). Natural language offers an intuitive interface, yet translating passenger open-ended instructions into control signals, without sacrificing interpretability and traceability, remains a challenge. This study proposes an instruction-realization framework that leverages a large language model (LLM) to interpret instructions, generates executable scripts that schedule multiple model predictive control (MPC)-based motion planners based on real-time feedback, and converts planned trajectories into control signals. This scheduling-centric design decouples semantic reasoning from vehicle control at different timescales, establishing a transparent, traceable decision-making chain from high-level instructions to low-level actions. Due to the absence of high-fidelity evaluation tools, this study introduces a benchmark for open-ended instruction realization in a closed-loop setting. Comprehensive experiments reveal that the framework significantly improves task-completion rates over instruction-realization baselines, reduces LLM query costs, achieves safety and compliance on par with specialized AD approaches, and exhibits considerable tolerance to LLM inference latency. For more qualitative illustrations and a clearer understanding.
title Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.08031