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

Traversing through a tilted narrow gap is previously an intractable task forreinforcement learning mainly due to two challenges. First, searching feasibletrajectories is not trivial because the goal behind the gap is difficult toreach. Second, the error tolerance after Sim2Real is low due to the relativelyhigh speed in comparison to the gap's narrow dimensions. This problem isaggravated by the intractability of collecting real-world data due to the riskof collision damage. In this paper, we propose an end-to-end reinforcementlearning framework that solves this task successfully by addressing bothproblems. To search for dynamically feasible flight trajectories, we usecurriculum learning to guide the agent towards the sparse reward behind theobstacle. To tackle the Sim2Real problem, we propose a Sim2Real framework thatcan transfer control commands to a real quadrotor without using real flightdata. To the best of our knowledge, our paper is the first work thataccomplishes successful gap traversing task purely using deep reinforcementlearning.

Flying Through a Narrow Gap Using End-to-end Deep Reinforcement Learning Augmented with Curriculum Learning and Sim2Real