Nowadays, robots are more and more autonomous, they are able to investigate autonomously the surrounding environment, take decisions, and, of course, accomplish elaborated tasks receiving simple inputs by users. Generally, every robot has to move to interact with the environment and human users replicating human-like motions and decisions. The literature already gives a lot of documentation about mobile/flying robots spanning paths in 2D and 3D environments, while the motion of articulated arms in 3D environments still requires investigation and experiments. This paper investigates MoveIt!, one of the most famous motion planner software, understanding its limits and trying to extend its capabilities. Integrating another planner with MoveIt!’s planning routine to split longer actions into smaller ones increases planning robustness. Due to the participation to Amazon Robotics Challenge 2017, every experiment has been carried on in automatic packing line scenarios, in which Baxter, a humanoid robot sporting two 7 DOF arms, had to perform actions avoiding known obstacles.
CITATION STYLE
Sansebastiano, E., & del Pobil, A. P. (2019). Multiple path planner integration for obstacle avoidance: moveit! and potential field planner synergy. In Advances in Intelligent Systems and Computing (Vol. 867, pp. 78–85). Springer Verlag. https://doi.org/10.1007/978-3-030-01370-7_7
Mendeley helps you to discover research relevant for your work.