Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation through Grounded Anomaly Classification and Recovery Policies. [arxiv]
Shuangqi Luo, Hongmin Wu, Shuangda Duan, Yijiong Lin, and Juan Rojas.
Abstract:
Robots are poised to interact with humans in unstructured environments. Despite increasingly robust control algorithms failure modes continue to exist whenever models fail to sufficiently model the unstructured dynamics. We contribute a set of recovery policies to deal with anomalies produced by external disturbances. The recoveries work when various different types of anomalies are triggered any number of times at any point in the task, including during already running recoveries. Our recovery critic stands atop of a tightly-integrated, graph-based online motion-generation and introspection system. Policies, skills, and introspection models are learned incrementally and contextually over time. Recoveries are studied via a collaborative kitting task where a wide range of anomalous conditions are experienced in the system. We also contribute an extensive analysis of the performance of the tightly integrated anomaly identification, classification, and recovery system under extreme anomalous conditions. We show how the integration of such a system achieves performances greater than the sum of its parts.
Resources:
- Code:
https://github.com/birlrobotics/birl_kitting_experiment - Supplement 1: Video
The video introduces the kitting experiment along with a summary of the framework, motion generation, introspection, and recovery techniques. It also demonstrates the robot’s ability to recover under different anomalous circumstances explained in Experiments 5 and 6. The video is available at (Youtube | Youku).
- Supplement 2: Dataset
Our dataset can be found in the following repo (37GB).
- Supplement 3 & 4: Results and Analysis:
- All results included in this paper and their corresponding analysis can be found in two excel sheets:
#3) the first one, offers experiment-by-experiment counts and results, with a summary tab for all experiments.
#4) The second one, uses an excel-sheet grouping function, that allows one to see totals or individual experimental counts easily.
- All results included in this paper and their corresponding analysis can be found in two excel sheets:
- Supplement 5: Appendices
Our paper contains 4 Appendices. They can be found here.Copyright Notice:
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.