The execution of manipulation tasks where humans and robots need to use a common volume represent new challenges for robotics in manufacturing environments. The robot's motion planning algorithm requires now to be aware of the human pose and ideally of its next actions to be able to timely compute trajectories that synchronizes naturally with the human motion. We are developing statistical models and algorithms to predict in real time the next actions of a human working together with a robot, both at the motion and task levels. This prediction can be used by the robot to be an efficient collaborator in the task by assisting the manipulation, completing other parts of the task and proving tools in a timely manner.
If you would like to contact us about our work, please scroll down to the people section and click on one of the group leads' people pages, where you can reach out to them directly.