Saved in:
Bibliographic Details
Main Authors: Pchelintsev, Svyatoslav, Patratskiy, Maxim, Onishchenko, Anatoly, Korchemnyi, Alexandr, Medvedev, Aleksandr, Vinogradova, Uliana, Galuzinsky, Ilya, Postnikov, Aleksey, Kovalev, Alexey K., Panov, Aleksandr I.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05135
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911191612260352
author Pchelintsev, Svyatoslav
Patratskiy, Maxim
Onishchenko, Anatoly
Korchemnyi, Alexandr
Medvedev, Aleksandr
Vinogradova, Uliana
Galuzinsky, Ilya
Postnikov, Aleksey
Kovalev, Alexey K.
Panov, Aleksandr I.
author_facet Pchelintsev, Svyatoslav
Patratskiy, Maxim
Onishchenko, Anatoly
Korchemnyi, Alexandr
Medvedev, Aleksandr
Vinogradova, Uliana
Galuzinsky, Ilya
Postnikov, Aleksey
Kovalev, Alexey K.
Panov, Aleksandr I.
contents Large Language Models are increasingly used in robotics for task planning, but their reliance on textual inputs limits their adaptability to real-world changes and failures. To address these challenges, we propose LERa - Look, Explain, Replan - a Visual Language Model-based replanning approach that utilizes visual feedback. Unlike existing methods, LERa requires only a raw RGB image, a natural language instruction, an initial task plan, and failure detection - without additional information such as object detection or predefined conditions that may be unavailable in a given scenario. The replanning process consists of three steps: (i) Look - where LERa generates a scene description and identifies errors; (ii) Explain - where it provides corrective guidance; and (iii) Replan - where it modifies the plan accordingly. LERa is adaptable to various agent architectures and can handle errors from both dynamic scene changes and task execution failures. We evaluate LERa on the newly introduced ALFRED-ChaOS and VirtualHome-ChaOS datasets, achieving a 40% improvement over baselines in dynamic environments. In tabletop manipulation tasks with a predefined probability of task failure within the PyBullet simulator, LERa improves success rates by up to 67%. Further experiments, including real-world trials with a tabletop manipulator robot, confirm LERa's effectiveness in replanning. We demonstrate that LERa is a robust and adaptable solution for error-aware task execution in robotics. The project page is available at https://lera-robo.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05135
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LERa: Replanning with Visual Feedback in Instruction Following
Pchelintsev, Svyatoslav
Patratskiy, Maxim
Onishchenko, Anatoly
Korchemnyi, Alexandr
Medvedev, Aleksandr
Vinogradova, Uliana
Galuzinsky, Ilya
Postnikov, Aleksey
Kovalev, Alexey K.
Panov, Aleksandr I.
Robotics
Large Language Models are increasingly used in robotics for task planning, but their reliance on textual inputs limits their adaptability to real-world changes and failures. To address these challenges, we propose LERa - Look, Explain, Replan - a Visual Language Model-based replanning approach that utilizes visual feedback. Unlike existing methods, LERa requires only a raw RGB image, a natural language instruction, an initial task plan, and failure detection - without additional information such as object detection or predefined conditions that may be unavailable in a given scenario. The replanning process consists of three steps: (i) Look - where LERa generates a scene description and identifies errors; (ii) Explain - where it provides corrective guidance; and (iii) Replan - where it modifies the plan accordingly. LERa is adaptable to various agent architectures and can handle errors from both dynamic scene changes and task execution failures. We evaluate LERa on the newly introduced ALFRED-ChaOS and VirtualHome-ChaOS datasets, achieving a 40% improvement over baselines in dynamic environments. In tabletop manipulation tasks with a predefined probability of task failure within the PyBullet simulator, LERa improves success rates by up to 67%. Further experiments, including real-world trials with a tabletop manipulator robot, confirm LERa's effectiveness in replanning. We demonstrate that LERa is a robust and adaptable solution for error-aware task execution in robotics. The project page is available at https://lera-robo.github.io.
title LERa: Replanning with Visual Feedback in Instruction Following
topic Robotics
url https://arxiv.org/abs/2507.05135