In order to operate in human environments, a robot’s semantic perception has to overcome open-world challenges such as novel objects and domain gaps. Autonomous deployment to such environments therefore requires robots to update their knowledge and learn without supervision. We investigate how a robot can autonomously discover novel semantic classes and improve accuracy on known classes when exploring an unknown environment. To this end, we develop a general framework for mapping and clustering that we then use to generate a self-supervised learning signal to update a semantic segmentation model. In particular, we show how clustering parameters can be optimized during deployment and that fusion of multiple observation modalities improves novel object discovery compared to prior work. Models, data, and implementations can be found at github.com/hermannsblum/scim.
SCIM: Simultaneous Clustering, Inference, and Mapping for Open-World Semantic Scene Understanding
Springer Proceedings in Advanced Robotics
The International Symposium of Robotics Research ; 2022 ; Geneva, Switzerland September 25, 2022 - September 30, 2022
2023-03-08
17 pages
Article/Chapter (Book)
Electronic Resource
English
Indoor Scene Understanding with Geometric and Semantic Contexts
British Library Online Contents | 2015
|European Patent Office | 2017
|Semantic Segmentation for Traffic Scene Understanding Based on Mobile Networks
British Library Conference Proceedings | 2018
|