English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Self-Supervised Learning (SSL) is a reliable learning mechanism in which arobot uses an original, trusted sensor cue for training to recognize anadditional, complementary sensor cue. We study for the first time in SSL how arobot's learning behavior should be organized, so that the robot can keepperforming its task in the case that the original cue becomes unavailable. Westudy this persistent form of SSL in the context of a flying robot that has toavoid obstacles based on distance estimates from the visual cue of stereovision. Over time it will learn to also estimate distances based on monocularappearance cues. A strategy is introduced that has the robot switch from stereovision based flight to monocular flight, with stereo vision purely used as'training wheels' to avoid imminent collisions. This strategy is shown to be aneffective approach to the 'feedback-induced data bias' problem as alsoexperienced in learning from demonstration. Both simulations and real-worldexperiments with a stereo vision equipped AR drone 2.0 show the feasibility ofthis approach, with the robot successfully using monocular vision to avoidobstacles in a 5 x 5 room. The experiments show the potential of persistent SSLas a robust learning approach to enhance the capabilities of robots. Moreover,the abundant training data coming from the own sensors allows to gather largedata sets necessary for deep learning approaches.

Persistent self-supervised learning principle: from stereo to monocular vision for obstacle avoidance