A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Kaixian, Lan, Guowei, Zurbrügg, René, Chen, Changan, Mower, Christopher E., Bou-Ammar, Haitham, Hutter, Marco
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911447036985344
author Qu, Kaixian
Lan, Guowei
Zurbrügg, René
Chen, Changan
Mower, Christopher E.
Bou-Ammar, Haitham
Hutter, Marco
author_facet Qu, Kaixian
Lan, Guowei
Zurbrügg, René
Chen, Changan
Mower, Christopher E.
Bou-Ammar, Haitham
Hutter, Marco
contents Large language models (LLMs) have emerged as the dominant paradigm for robotic task planning using natural language instructions. However, trained on general internet data, LLMs are not inherently aligned with the embodiment, skill sets, and limitations of real-world robotic systems. Inspired by the emerging paradigm of verbal reinforcement learning-where LLM agents improve through self-reflection and few-shot learning without parameter updates-we introduce PragmaBot, a framework that enables robots to learn task planning through real-world experience. PragmaBot employs a vision-language model (VLM) as the robot's "brain" and "eye", allowing it to visually evaluate action outcomes and self-reflect on failures. These reflections are stored in a short-term memory (STM), enabling the robot to quickly adapt its behavior during ongoing tasks. Upon task completion, the robot summarizes the lessons learned into its long-term memory (LTM). When facing new tasks, it can leverage retrieval-augmented generation (RAG) to plan more grounded action sequences by drawing on relevant past experiences and knowledge. Experiments on four challenging robotic tasks show that STM-based self-reflection increases task success rates from 35% to 84%, with emergent intelligent object interactions. In 12 real-world scenarios (including eight previously unseen tasks), the robot effectively learns from the LTM and improves single-trial success rates from 22% to 80%, with RAG outperforming naive prompting. These results highlight the effectiveness and generalizability of PragmaBot. Project webpage: https://pragmabot.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2507_16713
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
Qu, Kaixian
Lan, Guowei
Zurbrügg, René
Chen, Changan
Mower, Christopher E.
Bou-Ammar, Haitham
Hutter, Marco
Robotics
Artificial Intelligence
Computation and Language
Large language models (LLMs) have emerged as the dominant paradigm for robotic task planning using natural language instructions. However, trained on general internet data, LLMs are not inherently aligned with the embodiment, skill sets, and limitations of real-world robotic systems. Inspired by the emerging paradigm of verbal reinforcement learning-where LLM agents improve through self-reflection and few-shot learning without parameter updates-we introduce PragmaBot, a framework that enables robots to learn task planning through real-world experience. PragmaBot employs a vision-language model (VLM) as the robot's "brain" and "eye", allowing it to visually evaluate action outcomes and self-reflect on failures. These reflections are stored in a short-term memory (STM), enabling the robot to quickly adapt its behavior during ongoing tasks. Upon task completion, the robot summarizes the lessons learned into its long-term memory (LTM). When facing new tasks, it can leverage retrieval-augmented generation (RAG) to plan more grounded action sequences by drawing on relevant past experiences and knowledge. Experiments on four challenging robotic tasks show that STM-based self-reflection increases task success rates from 35% to 84%, with emergent intelligent object interactions. In 12 real-world scenarios (including eight previously unseen tasks), the robot effectively learns from the LTM and improves single-trial success rates from 22% to 80%, with RAG outperforming naive prompting. These results highlight the effectiveness and generalizability of PragmaBot. Project webpage: https://pragmabot.github.io/
title A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
topic Robotics
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2507.16713