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

Space exploration missions have seen use of increasingly sophisticatedrobotic systems with ever more autonomy. Deep learning promises to take thiseven a step further, and has applications for high-level tasks, like pathplanning, as well as low-level tasks, like motion control, which are criticalcomponents for mission efficiency and success. Using deep reinforcementend-to-end learning with randomized reward function parameters during training,we teach a simulated 8 degree-of-freedom quadruped ant-like robot to travelanywhere within a perimeter, conducting path plan and motion control on asingle neural network, without any system model or prior knowledge of theterrain or environment. Our approach also allows for user specified waypoints,which could translate well to either fully autonomous orsemi-autonomous/teleoperated space applications that encounter delay times. Wetrained the agent using randomly generated waypoints linked to the rewardfunction and passed waypoint coordinates as inputs to the neural network. Suchapplications show promise on a variety of space exploration robots, includinghigh speed rovers for fast locomotion and legged cave robots for rough terrain.

Deep Learned Path Planning via Randomized Reward-Linked-Goals and Potential Space Applications