Learning to Recover from Plan Execution Errors during Robot Manipulation: A Neuro-symbolic Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913368411996160 |
|---|---|
| author | Kalithasan, Namasivayam Tuli, Arnav Bindal, Vishal Singh, Himanshu Gaurav Singla, Parag Paul, Rohan |
| author_facet | Kalithasan, Namasivayam Tuli, Arnav Bindal, Vishal Singh, Himanshu Gaurav Singla, Parag Paul, Rohan |
| contents | Automatically detecting and recovering from failures is an important but challenging problem for autonomous robots. Most of the recent work on learning to plan from demonstrations lacks the ability to detect and recover from errors in the absence of an explicit state representation and/or a (sub-) goal check function. We propose an approach (blending learning with symbolic search) for automated error discovery and recovery, without needing annotated data of failures. Central to our approach is a neuro-symbolic state representation, in the form of dense scene graph, structured based on the objects present within the environment. This enables efficient learning of the transition function and a discriminator that not only identifies failures but also localizes them facilitating fast re-planning via computation of heuristic distance function. We also present an anytime version of our algorithm, where instead of recovering to the last correct state, we search for a sub-goal in the original plan minimizing the total distance to the goal given a re-planning budget. Experiments on a physics simulator with a variety of simulated failures show the effectiveness of our approach compared to existing baselines, both in terms of efficiency as well as accuracy of our recovery mechanism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18948 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to Recover from Plan Execution Errors during Robot Manipulation: A Neuro-symbolic Approach Kalithasan, Namasivayam Tuli, Arnav Bindal, Vishal Singh, Himanshu Gaurav Singla, Parag Paul, Rohan Robotics Machine Learning Automatically detecting and recovering from failures is an important but challenging problem for autonomous robots. Most of the recent work on learning to plan from demonstrations lacks the ability to detect and recover from errors in the absence of an explicit state representation and/or a (sub-) goal check function. We propose an approach (blending learning with symbolic search) for automated error discovery and recovery, without needing annotated data of failures. Central to our approach is a neuro-symbolic state representation, in the form of dense scene graph, structured based on the objects present within the environment. This enables efficient learning of the transition function and a discriminator that not only identifies failures but also localizes them facilitating fast re-planning via computation of heuristic distance function. We also present an anytime version of our algorithm, where instead of recovering to the last correct state, we search for a sub-goal in the original plan minimizing the total distance to the goal given a re-planning budget. Experiments on a physics simulator with a variety of simulated failures show the effectiveness of our approach compared to existing baselines, both in terms of efficiency as well as accuracy of our recovery mechanism. |
| title | Learning to Recover from Plan Execution Errors during Robot Manipulation: A Neuro-symbolic Approach |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2405.18948 |