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

We present Galactic, a large-scale simulation and reinforcement-learning (RL)framework for robotic mobile manipulation in indoor environments. Specifically,a Fetch robot (equipped with a mobile base, 7DoF arm, RGBD camera, egomotion,and onboard sensing) is spawned in a home environment and asked to rearrangeobjects - by navigating to an object, picking it up, navigating to a targetlocation, and then placing the object at the target location.  Galactic is fast. In terms of simulation speed (rendering + physics),Galactic achieves over 421,000 steps-per-second (SPS) on an 8-GPU node, whichis 54x faster than Habitat 2.0 (7699 SPS). More importantly, Galactic wasdesigned to optimize the entire rendering + physics + RL interplay since anybottleneck in the interplay slows down training. In terms of simulation+RLspeed (rendering + physics + inference + learning), Galactic achieves over108,000 SPS, which 88x faster than Habitat 2.0 (1243 SPS).  These massive speed-ups not only drastically cut the wall-clock training timeof existing experiments, but also unlock an unprecedented scale of newexperiments. First, Galactic can train a mobile pick skill to >80% accuracy inunder 16 minutes, a 100x speedup compared to the over 24 hours it takes totrain the same skill in Habitat 2.0. Second, we use Galactic to perform thelargest-scale experiment to date for rearrangement using 5B steps of experiencein 46 hours, which is equivalent to 20 years of robot experience. This scalingresults in a single neural network composed of task-agnostic componentsachieving 85% success in GeometricGoal rearrangement, compared to 0% successreported in Habitat 2.0 for the same approach. The code is available atgithub.com/facebookresearch/galactic.

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second