Anticipate, Adapt, Act: A Hybrid Framework for Task Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908848512565248 |
|---|---|
| author | Dash, Nabanita Kaura, Ayush Singh, Shivam Singh, Ramandeep Banerjee, Snehasis Sridharan, Mohan Krishna, K. Madhava |
| author_facet | Dash, Nabanita Kaura, Ayush Singh, Shivam Singh, Ramandeep Banerjee, Snehasis Sridharan, Mohan Krishna, K. Madhava |
| contents | Anticipating and adapting to failures is a key capability robots need to collaborate effectively with humans in complex domains. This continues to be a challenge despite the impressive performance of state of the art AI planning systems and Large Language Models (LLMs) because of the uncertainty associated with the tasks and their outcomes. Toward addressing this challenge, we present a hybrid framework that integrates the generic prediction capabilities of an LLM with the probabilistic sequential decision-making capability of Relational Dynamic Influence Diagram Language. For any given task, the robot reasons about the task and the capabilities of the human attempting to complete it; predicts potential failures due to lack of ability (in the human) or lack of relevant domain objects; and executes actions to prevent such failures or recover from them. Experimental evaluation in the VirtualHome 3D simulation environment demonstrates substantial improvement in performance compared with state of the art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19518 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Anticipate, Adapt, Act: A Hybrid Framework for Task Planning Dash, Nabanita Kaura, Ayush Singh, Shivam Singh, Ramandeep Banerjee, Snehasis Sridharan, Mohan Krishna, K. Madhava Robotics Anticipating and adapting to failures is a key capability robots need to collaborate effectively with humans in complex domains. This continues to be a challenge despite the impressive performance of state of the art AI planning systems and Large Language Models (LLMs) because of the uncertainty associated with the tasks and their outcomes. Toward addressing this challenge, we present a hybrid framework that integrates the generic prediction capabilities of an LLM with the probabilistic sequential decision-making capability of Relational Dynamic Influence Diagram Language. For any given task, the robot reasons about the task and the capabilities of the human attempting to complete it; predicts potential failures due to lack of ability (in the human) or lack of relevant domain objects; and executes actions to prevent such failures or recover from them. Experimental evaluation in the VirtualHome 3D simulation environment demonstrates substantial improvement in performance compared with state of the art baselines. |
| title | Anticipate, Adapt, Act: A Hybrid Framework for Task Planning |
| topic | Robotics |
| url | https://arxiv.org/abs/2602.19518 |