Probabilistic graph based spatial assembly relation inference for programming of assembly task by demonstration

In robot programming by demonstration (PBD) for assembly tasks, one of the important topics is to inference the poses and spatial relations of parts during the demonstration. In this paper, we propose a world model called assembly graph (AG) to achieve this task. The model is able to represent the poses of all parts, the relations, observations provided by vision techniques and prior knowledge in a unified probabilistic graph. Then the problem is stated as likelihood maximization estimation of pose parameters with the relations being the latent variables. Classification expectation maximization algorithm (CEM) is employed to solve the model. Besides, the contradiction between relations is incorporated as prior knowledge to better shape the posterior, thus guiding the algorithm find a more accurate solution. In experiments, both simulated and real world datasets are applied to evaluate the performance of our proposed method. The experimental results show that the AG gives better accuracy than the relations as deterministic variables (RDV) employed in some previous works due to the robustness and global consistency. Finally, the solution is implemented into a PBD system with ABB industrial robotic arm simulator as the execution stage, succeeding in real world captured assembly tasks.

Authors

• Yue Wang 0020
• Jie Cai
• Yabiao Wang
• Youzhong Hu
• Rong Xiong
• Yong Liu 0007
• Jiafan Zhang
• Liwei Qi

Keywords

• Assembly
• Probabilistic logic
• Service robots
• Programming
• Visualization
• Spatial Relationship
• Probabilistic Graph
• Spatial Assembly
• Latent Variables
• Expectation Maximization
• Simulated Datasets
• Simulated Robot
• Assembly Graph
• Robot Programming
• Deterministic Variables
• Degrees Of Freedom
• Probabilistic Model
• Precision And Recall
• Graphical Model
• Complete System
• Pose Estimation
• Inference System
• Maximum Step
• Recognition Of Relationships
• World Coordinate
• Observation Likelihood
• Final Pose