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/

Zendy Plus

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

Zendy Tools

Zendy Open

Underwater navigation presents several challenges, including unstructuredunknown environments, lack of reliable localization systems (e.g., GPS), andpoor visibility. Furthermore, good-quality obstacle detection sensors forunderwater robots are scant and costly; and many sensors like RGB-D cameras andLiDAR only work in-air. To enable reliable mapless underwater navigationdespite these challenges, we propose a low-cost end-to-end navigation system,based on a monocular camera and a fixed single-beam echo-sounder, thatefficiently navigates an underwater robot to waypoints while avoiding nearbyobstacles. Our proposed method is based on Proximal Policy Optimization (PPO),which takes as input current relative goal information, estimated depth images,echo-sounder readings, and previous executed actions, and outputs 3D robotactions in a normalized scale. End-to-end training was done in simulation,where we adopted domain randomization (varying underwater conditions andvisibility) to learn a robust policy against noise and changes in visibilityconditions. The experiments in simulation and real-world demonstrated that ourproposed method is successful and resilient in navigating a low-cost underwaterrobot in unknown underwater environments. The implementation is made publiclyavailable at https://github.com/dartmouthrobotics/deeprl-uw-robot-navigation.

Monocular Camera and Single-Beam Sonar-Based Underwater Collision-Free Navigation with Domain Randomization