Robots have the potential to assist people with a variety of routine tasks in both homes and workplaces. We are developing a robot motion planning approach for performing a learned task while reacting to moving task-relevant objects and avoiding obstacles. We employ a closed-loop sampling-based motion planner that acquires new sensor information, generates new collision-free plans that are based on a learned task model, and replans at a rate of more than 10 times per second. We illustrate the efficacy of our approach using a Rethink Robotics Baxter robot performing a powder transfer task and a stirring task.
For more information:
robotics.cs.unc...
Негізгі бет Robot Motion Planning for Reactive Execution of Learned Tasks
Пікірлер