This letter proposes a hybrid control methodology to achieve full body collision avoidance in anthropomorphic robot manipulators. The proposal improves classical motion planning algorithms by introducing a Deep Reinforcement Learning (DRL) approach trained ad hoc for performing obstacle avoidance, while achieving a reaching task in the operative space. More specifically, a switching mechanism is enabled whenever a condition of proximity to the obstacles is met, thus conferring to the dual-mode architecture a self-configuring capability in order to cope with objects unexpectedly invading the workspace. The proposal has been finally tested relying on a realistic robot manipulator simulated in a V-REP environment.
Self-configuring robot path planning with obstacle avoidance via deep reinforcement learning
Incremona, Gian Paolo;
2021-01-01
Abstract
This letter proposes a hybrid control methodology to achieve full body collision avoidance in anthropomorphic robot manipulators. The proposal improves classical motion planning algorithms by introducing a Deep Reinforcement Learning (DRL) approach trained ad hoc for performing obstacle avoidance, while achieving a reaching task in the operative space. More specifically, a switching mechanism is enabled whenever a condition of proximity to the obstacles is met, thus conferring to the dual-mode architecture a self-configuring capability in order to cope with objects unexpectedly invading the workspace. The proposal has been finally tested relying on a realistic robot manipulator simulated in a V-REP environment.File | Dimensione | Formato | |
---|---|---|---|
drl_collision_avoidance_j.pdf
Accesso riservato
Descrizione: Articolo principale
:
Publisher’s version
Dimensione
987.81 kB
Formato
Adobe PDF
|
987.81 kB | Adobe PDF | Visualizza/Apri |
11311-1167646_Incremona.pdf
accesso aperto
:
Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione
631.25 kB
Formato
Adobe PDF
|
631.25 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.