Activities per year
Abstract
This work tackles scene understanding for outdoor robotic navigation, solely relying on images captured by an on-board camera. Conventional visual scene understanding interprets the environment based on specific descriptive categories. However, such a representation is not directly interpretable for decision-making and constrains robot operation to a specific domain. Thus, we propose to segment egocentric images directly in terms of how a robot can navigate in them, and tailor the learning problem to an autonomous navigation task. Building around an image segmentation network, we present a generic affordance consisting of 3 driveability levels which can broadly apply to both urban and off-road scenes. By encoding these levels with soft ordinal labels, we incorporate inter-class distances during learning which improves segmentation compared to standard "hard" one-hot labelling. In addition, we propose a navigation-oriented pixel-wise loss weighting method which assigns higher importance to safety-critical areas. We evaluate our approach on large-scale public image segmentation datasets ranging from sunny city streets to snowy forest trails. In a cross-dataset generalization experiment, we show that our affordance learning scheme can be applied across a diverse mix of datasets and improves driveability estimation in unseen environments compared to general-purpose, single-dataset segmentation.
Original language | English |
---|---|
Article number | 9689949 |
Journal | IEEE Robotics and Automation Letters |
Volume | 7 |
Issue number | 2 |
Pages (from-to) | 2913-2920 |
Number of pages | 8 |
ISSN | 2377-3766 |
DOIs | |
Publication status | Published - Apr 2022 |
Keywords
- Affordances
- Deep learning for visual perception
- Image segmentation
- Labeling
- Navigation
- Roads
- Robots
- Semantics
- computer vision for transportation
- semantic scene understanding
Fingerprint
Dive into the research topics of 'Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images'. Together they form a unique fingerprint.-
AI for the People 2022 poster session - "Soft labelling for semantic segmentation"
Galadrielle Humblot-Renaux (Speaker)
10 Nov 2022Activity: Talks and presentations › Conference presentations
-
ICRA 2022 session - Computer Vision for Transportation
Galadrielle Humblot-Renaux (Speaker)
24 May 2022Activity: Talks and presentations › Conference presentations
-
Visual scene understanding for outdoor robot navigation
Galadrielle Humblot-Renaux (Lecturer)
18 Mar 2022Activity: Talks and presentations › Talks and presentations in private or public companies