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

With the rapid growth of computing powers and recent advances in deeplearning, we have witnessed impressive demonstrations of novel robotcapabilities in research settings. Nonetheless, these learning systems exhibitbrittle generalization and require excessive training data for practical tasks.To harness the capabilities of state-of-the-art robot learning models whileembracing their imperfections, we present Sirius, a principled framework forhumans and robots to collaborate through a division of work. In this framework,partially autonomous robots are tasked with handling a major portion ofdecision-making where they work reliably; meanwhile, human operators monitorthe process and intervene in challenging situations. Such a human-robot teamensures safe deployments in complex tasks. Further, we introduce a new learningalgorithm to improve the policy's performance on the data collected from thetask executions. The core idea is re-weighing training samples withapproximated human trust and optimizing the policies with weighted behavioralcloning. We evaluate Sirius in simulation and on real hardware, showing thatSirius consistently outperforms baselines over a collection of contact-richmanipulation tasks, achieving an 8% boost in simulation and 27% on realhardware than the state-of-the-art methods in policy success rate, with twicefaster convergence and 85% memory size reduction. Videos and more details areavailable at https://ut-austin-rpl.github.io/sirius/

Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment