BROWSE
Detail
Journal Article
Uncertainty-Aware Knowledge Distillation for Collision Identification of Collaborative Robots
- Authors
- Wookyong Kwon, Yongsik Jin, Sang Jun Lee
- Issue Date
- 2021-10
- Citation
- Sensors, v.21, no.19, pp.1-16
- ISSN
- 1424-8220
- Publisher
- MDPI
- Language
- English
- Type
- Journal Article
- Abstract
- Human-robot interaction has received a lot of attention as collaborative robots became widely utilized in many industrial fields. Among techniques for human-robot interaction, collision identification is an indispensable element in collaborative robots to prevent fatal accidents. This paper proposes a deep learning method for identifying external collisions in 6-DoF articulated robots. The proposed method expands the idea of CollisionNet, which was previously proposed for collision detection, to identify the locations of external forces. The key contribution of this paper is uncertainty-aware knowledge distillation for improving the accuracy of a deep neural network. Sample-level uncertainties are estimated from a teacher network, and larger penalties are imposed for uncertain samples during the training of a student network. Experiments demonstrate that the proposed method is effective for improving the performance of collision identification.
- KSP Keywords
- Articulated robots, Collaborative robot, Collision detection, Deep learning method, Deep neural network(DNN), Fatal accidents, Human robot interaction(HRI), Knowledge Distillation, Six degrees of freedom(6-DoF), deep learning(DL), external force
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
