Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss

Prew, W.; Breckon, T.P.; Bordewich, M.J.R.; Beierholm, U.

Abstract

In this paper we introduce two methods of improving real-time object grasping performance from monocular colour images in an end-to-end CNN architecture. The first is the addition of an auxiliary task during model training (multi-task learning). Our multi-task CNN model improves grasping performance from a baseline average of 72.04% to 78.14% on the large Jacquard grasping dataset when performing a supplementary depth reconstruction task. The second is introducing a positional loss function that emphasises loss per pixel for secondary parameters (gripper angle and width) only on points of an object where a successful grasp can take place. This increases performance from a baseline average of 72.04% to 78.92% as well as reducing the number of training epochs required. These methods can be also performed in tandem resulting in a further performance increase to 79.12%, while maintaining sufficient inference speed to afford real-time grasp processing.

Citation

Prew, W., Breckon, T., Bordewich, M., & Beierholm, U. (2021, January). Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss. Presented at 25th International Conference on Pattern Recognition (ICPR 2020), Milan, Italy

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 25th International Conference on Pattern Recognition (ICPR 2020)
• Start Date: Jan 10, 2021
• End Date: Jan 15, 2021
• Acceptance Date: Oct 11, 2020
• Online Publication Date: May 5, 2021
• Publication Date: 2021
• Deposit Date: Oct 25, 2020
• Publicly Available Date: Oct 27, 2020
• Series ISSN: 1051-4651
• DOI: https://doi.org/10.1109/icpr48806.2021.9413197
• Public URL: https://durham-repository.worktribe.com/output/1140109