Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in Clutter
This addresses the challenge of enabling robots to manipulate objects in cluttered scenes, which is incremental as it builds on existing end-to-end LfD methods.
The paper tackles the problem of training deep visuomotor policies for robotic manipulation in cluttered environments, introducing ASOR data augmentation and two network architectures (ASOR-IA and ASOR-EA) that achieve success in cluttered trials where previous methods fail and outperform baselines even in uncluttered settings.
Recent research demonstrated that it is feasible to end-to-end train multi-task deep visuomotor policies for robotic manipulation using variations of learning from demonstration (LfD) and reinforcement learning (RL). In this paper, we extend the capabilities of end-to-end LfD architectures to object manipulation in clutter. We start by introducing a data augmentation procedure called Accept Synthetic Objects as Real (ASOR). Using ASOR we develop two network architectures: implicit attention ASOR-IA and explicit attention ASOR-EA. Both architectures use the same training data (demonstrations in uncluttered environments) as previous approaches. Experimental results show that ASOR-IA and ASOR-EA succeed ina significant fraction of trials in cluttered environments where previous approaches never succeed. In addition, we find that both ASOR-IA and ASOR-EA outperform previous approaches even in uncluttered environments, with ASOR-EA performing better even in clutter compared to the previous best baseline in an uncluttered environment.