A knowledge-based task planning approach for robot multi-task manipulation

Task planning is a crucial component in facilitating robot multi-task manipulations. Language-based task planning methods offer practicality in receiving commands from humans in real-life scenarios and require only low-cost labeled data. However, existing methods often rely on sequence models for planning, which primarily focus on mapping language to sequences of sub-tasks while neglecting the knowledge about tasks and objects. To overcome these limitations, we propose a knowledge based task planning approach called Recurrent Graph Convolutional Network (RGCN). It is devised with a novel structure that combined GCN (Kipf and Welling in International Conference on Learning Representations (ICLR), 2017) and LSTM (Hochreiter and chmidhuber in Neural Comput 9 (8): 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735) which enables it to leverage knowledge graph data and historical predictions. The experimental results demonstrate that our approach achieves the impressive task planning success rate of 95.7%, surpassing the best baseline method significantly, which achieves 78.7%. Furthermore, we evaluate the performance of multi-task manipulation across a specific set of 20 tasks within a simulated environment. Notably, RGCN combined with pre-trained primitive tasks exhibits the highest success rate compared with state-of-art multi-task learning methods. Our method is proven to be significant for language-conditioned task planning and is qualified for instructing robots for multi-task manipulation.

Automated summary

Task planning is essential for robot multi-task manipulations. Language-based methods provide practicality in receiving commands from humans and require low-cost labeled data. To overcome the limitations of existing methods, we propose a knowledge-based approach called Recurrent Graph Convolutional Network (RGCN) that leverages knowledge graph data and historical predictions. Our approach achieves a task planning success rate of 95.7%, surpassing the best baseline method significantly.