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

We present a novel learning-based collision avoidance algorithm, CrowdSteer,for mobile robots operating in dense and crowded environments. Our approach isend-to-end and uses multiple perception sensors such as a 2-D lidar along witha depth camera to sense surrounding dynamic agents and compute collision-freevelocities. Our training approach is based on the sim-to-real paradigm and useshigh fidelity 3-D simulations of pedestrians and the environment to train apolicy using Proximal Policy Optimization (PPO). We show that our learnednavigation model is directly transferable to previously unseen virtual anddense real-world environments. We have integrated our algorithm withdifferential drive robots and evaluated its performance in narrow scenariossuch as dense crowds, narrow corridors, T-junctions, L-junctions, etc. Inpractice, our approach can perform real-time collision avoidance and generatesmooth trajectories in such complex scenarios. We also compare the performancewith prior methods based on metrics such as trajectory length, mean time togoal, success rate, and smoothness and observe considerable improvement.

Realtime Collision Avoidance for Mobile Robots in Dense Crowds using Implicit Multi-sensor Fusion and Deep Reinforcement Learning