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

Robotic navigation in environments shared with other robots or humans remainschallenging because the intentions of the surrounding agents are not directlyobservable and the environment conditions are continuously changing. Localtrajectory optimization methods, such as model predictive control (MPC), candeal with those changes but require global guidance, which is not trivial toobtain in crowded scenarios. This paper proposes to learn, via deepReinforcement Learning (RL), an interaction-aware policy that provideslong-term guidance to the local planner. In particular, in simulations withcooperative and non-cooperative agents, we train a deep network to recommend asubgoal for the MPC planner. The recommended subgoal is expected to help therobot in making progress towards its goal and accounts for the expectedinteraction with other agents. Based on the recommended subgoal, the MPCplanner then optimizes the inputs for the robot satisfying its kinodynamic andcollision avoidance constraints. Our approach is shown to substantially improvethe navigation performance in terms of number of collisions as compared toprior MPC frameworks, and in terms of both travel time and number of collisionscompared to deep RL methods in cooperative, competitive and mixed multiagentscenarios.

Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians