Robot Introspection via Wrench-based Action Grammars [arxiv]
Juan Rojas, Shuangqi Luo, Zhenjie Huang, Hongbin Lin, Dingqiao Zhu, and Kensuke Harada
Abstract:
Robotic failure is all too common in unstructured robot tasks. Despite well-designed controllers, robots often fail due to unexpected events. How do robots measure unexpected events? Many do not. Most robots are driven by the sense-plan-act paradigm, however, more recently robots are undergoing a sense-plan-act-\emph{verify} paradigm. In this work, we present a principled methodology to bootstrap online robot introspection for contact tasks. In effect, we are trying to enable the robot to answer the question: what did I do? Is my behavior as expected or not? To this end, we analyze noisy wrench data and postulate that the latter inherently contains patterns that can be effectively represented by a vocabulary. The vocabulary is generated by segmenting and encoding the data. When the wrench information represents a sequence of sub-tasks, we can think of the vocabulary forming a sentence (set of words with grammar rules) for a given subtask; allowing the latter to be uniquely represented. The grammar, which can also include unexpected events, was classified in offline and online scenarios as well as for simulated and real robot experiments. In the offline setting, two competitive machine learning algorithms (Support Vector Machines and online Mondrian Forests) were used to present relevant classification result. In the online scenario, probabilistic SVM results are used to give temporal confidence to the introspection result. The contribution of our work is the presentation of a generalizable online semantic scheme that enables a robot to understand its high-level state whether nominal or abnormal. It is shown to work in offline and online scenarios for a particularly challenging contact task: snap assemblies. We perform the snap assembly in one-arm simulated and real one-arm experiments and a simulated two-arm experiment. The data set itself is also fully available online and itself provides a valuable resource for this type of contact task. This verification mechanism can be used by high-level planners or reasoning systems to enable intelligent failure recovery or determine the next most optimal manipulation skill to be used.
Resources:
- Code
- Simulation Environment OpenHRP 3.0.8 used in Linux 10.04:
https://fkanehiro.github.io/openhrp3-doc/en/ - Manipulation Strategy for Assembly Task:
https://github.com/birlrobotics/PivotApproach/tree/DualArm_Gray - Offline RCBHT (Semantic Encoder):
https://github.com/birlrobotics/RCBHT/releases/tag/v2.0.3 - Online RCBHT (Semantic Encoder)
https://github.com/birlrobotics/onlineRCBHT - Introspection Algorithms:
https://github.com/birlrobotics/rcbht_training_and_online_classification
- Simulation Environment OpenHRP 3.0.8 used in Linux 10.04:
- DATA:
- Outside China – YouTube
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.