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 PRM-RL, a hierarchical method for long-range navigation taskcompletion that combines sampling based path planning with reinforcementlearning (RL). The RL agents learn short-range, point-to-point navigationpolicies that capture robot dynamics and task constraints without knowledge ofthe large-scale topology. Next, the sampling-based planners provide roadmapswhich connect robot configurations that can be successfully navigated by the RLagent. The same RL agents are used to control the robot under the direction ofthe planning, enabling long-range navigation. We use the Probabilistic Roadmaps(PRMs) for the sampling-based planner. The RL agents are constructed usingfeature-based and deep neural net policies in continuous state and actionspaces. We evaluate PRM-RL, both in simulation and on-robot, on two navigationtasks with non-trivial robot dynamics: end-to-end differential drive indoornavigation in office environments, and aerial cargo delivery in urbanenvironments with load displacement constraints. Our results show improvementin task completion over both RL agents on their own and traditionalsampling-based planners. In the indoor navigation task, PRM-RL successfullycompletes up to 215 m long trajectories under noisy sensor conditions, and theaerial cargo delivery completes flights over 1000 m without violating the taskconstraints in an environment 63 million times larger than used in training.

PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning