Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |