Saved in:
Bibliographic Details
Main Authors: Rasanji, Rathnam Vidushika, Wei-Kocsis, Jin, Zhang, Jiansong, Gan, Dongming, Athinarayanan, Ragu, Asunda, Paul
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.13877
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909743501541376
author Rasanji, Rathnam Vidushika
Wei-Kocsis, Jin
Zhang, Jiansong
Gan, Dongming
Athinarayanan, Ragu
Asunda, Paul
author_facet Rasanji, Rathnam Vidushika
Wei-Kocsis, Jin
Zhang, Jiansong
Gan, Dongming
Athinarayanan, Ragu
Asunda, Paul
contents Reinforcement learning (RL) has demonstrated great potential in robotic operations. However, its data-intensive nature and reliance on the Markov Decision Process (MDP) assumption limit its practical deployment in real-world scenarios involving complex dynamics and long-term temporal dependencies, such as multi-robot manipulation. Decision Transformers (DTs) have emerged as a promising offline alternative by leveraging causal transformers for sequence modeling in RL tasks. However, their applications to multi-robot manipulations still remain underexplored. To address this gap, we propose a novel framework, Symbolically-Guided Decision Transformer (SGDT), which integrates a neuro-symbolic mechanism with a causal transformer to enable deployable multi-robot collaboration. In the proposed SGDT framework, a neuro-symbolic planner generates a high-level task-oriented plan composed of symbolic subgoals. Guided by these subgoals, a goal-conditioned decision transformer (GCDT) performs low-level sequential decision-making for multi-robot manipulation. This hierarchical architecture enables structured, interpretable, and generalizable decision making in complex multi-robot collaboration tasks. We evaluate the performance of SGDT across a range of task scenarios, including zero-shot and few-shot scenarios. To our knowledge, this is the first work to explore DT-based technology for multi-robot manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13877
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Deployable Multi-Robot Collaboration via a Symbolically-Guided Decision Transformer
Rasanji, Rathnam Vidushika
Wei-Kocsis, Jin
Zhang, Jiansong
Gan, Dongming
Athinarayanan, Ragu
Asunda, Paul
Robotics
Artificial Intelligence
Reinforcement learning (RL) has demonstrated great potential in robotic operations. However, its data-intensive nature and reliance on the Markov Decision Process (MDP) assumption limit its practical deployment in real-world scenarios involving complex dynamics and long-term temporal dependencies, such as multi-robot manipulation. Decision Transformers (DTs) have emerged as a promising offline alternative by leveraging causal transformers for sequence modeling in RL tasks. However, their applications to multi-robot manipulations still remain underexplored. To address this gap, we propose a novel framework, Symbolically-Guided Decision Transformer (SGDT), which integrates a neuro-symbolic mechanism with a causal transformer to enable deployable multi-robot collaboration. In the proposed SGDT framework, a neuro-symbolic planner generates a high-level task-oriented plan composed of symbolic subgoals. Guided by these subgoals, a goal-conditioned decision transformer (GCDT) performs low-level sequential decision-making for multi-robot manipulation. This hierarchical architecture enables structured, interpretable, and generalizable decision making in complex multi-robot collaboration tasks. We evaluate the performance of SGDT across a range of task scenarios, including zero-shot and few-shot scenarios. To our knowledge, this is the first work to explore DT-based technology for multi-robot manipulation.
title Toward Deployable Multi-Robot Collaboration via a Symbolically-Guided Decision Transformer
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2508.13877