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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Millirobots are a promising robotic platform for many applications due totheir small size and low manufacturing costs. Legged millirobots, inparticular, can provide increased mobility in complex environments and improvedscaling of obstacles. However, controlling these small, highly dynamic, andunderactuated legged systems is difficult. Hand-engineered controllers cansometimes control these legged millirobots, but they have difficulties withdynamic maneuvers and complex terrains. We present an approach for controllinga real-world legged millirobot that is based on learned neural network models.Using less than 17 minutes of data, our method can learn a predictive model ofthe robot's dynamics that can enable effective gaits to be synthesized on thefly for following user-specified waypoints on a given terrain. Furthermore, byleveraging expressive, high-capacity neural network models, our approach allowsfor these predictions to be directly conditioned on camera images, endowing therobot with the ability to predict how different terrains might affect itsdynamics. This enables sample-efficient and effective learning for locomotionof a dynamic legged millirobot on various terrains, including gravel, turf,carpet, and styrofoam. Experiment videos can be found athttps://sites.google.com/view/imageconddyn

Learning Image-Conditioned Dynamics Models for Control of Under-actuated Legged Millirobots