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

Robot motion planning often requires finding trajectories that balancedifferent user intents, or preferences. One of these preferences is usuallyarrival at the goal, while another might be obstacle avoidance. Here, weformalize these, and similar, tasks as preference balancing tasks (PBTs) onacceleration controlled robots, and propose a motion planning solution,PrEference Appraisal Reinforcement Learning (PEARL). PEARL uses reinforcementlearning on a restricted training domain, combined with features engineeredfrom user-given intents. PEARL's planner then generates trajectories inexpanded domains for more complex problems. We present an adaptation forrejection of stochastic disturbances and offer in-depth analysis, includingtask completion conditions and behavior analysis when the conditions do nothold. PEARL is evaluated on five problems, two multi-agent obstacle avoidancetasks and three that stochastically disturb the system at run-time: 1) amulti-agent pursuit problem with 1000 pursuers, 2) robot navigation through 900moving obstacles, which is is trained with in an environment with only 4 staticobstacles, 3) aerial cargo delivery, 4) two robot rendezvous, and 5) flyinginverted pendulum. Lastly, we evaluate the method on a physical quadrotor UAVrobot with a suspended load influenced by a stochastic disturbance. The video,https://youtu.be/ZkFt1uY6vlw contains the experiments and visualization of thesimulations.

PEARL: PrEference Appraisal Reinforcement Learning for Motion Planning