An Intuitive Robot Learning from Human Demonstration

Abstract

This paper presents a new way to teach a robot certain motions remotely from human demonstrator. The human and robot interface is built using a Kinect sensor which is connected directly to a remote computer that runs on processing software. The Cartesian coordinates is extracted, converted into joint angles and sent to the workstation for the control of the Sawyer robot. Kinesthetic teaching was used to correct the reproduced demonstrations while only valid resolved joint angles are recorded to ensure consistence in the sent data. The recorded dataset is encoded using GMM while GMR was employed to extract and reproduce generalised trajectory with respect to the associated time-step. To evaluate the proposed approach, an experiment for a robot to follow a human arm motion was performed. This proposed approach could help non-expert users to teach a robot how to perform assembling task in more human like ways.

Spatial Iterative Learning Control for Robotic Path Learning

“…9, which is comprised of 7-degrees-offreedom (7-DOF) in a single arm configuration. The Sawyer robot is embedded with several sensors and actuators that are essential for human-robot interaction, including a motor encoder equipped at each joint to measure joint angles and a torque sensor at each joint to measure joint torques [29]. The Sawyer robot runs on the Robot Operating System (ROS) platform.…”

Ring Gaussian Mixture Modelling and Regression for collaborative robots

“…This enables the operator to wear the bracelet and intuitively move the cobot to perform a task as if he/she is performing it himself/herself. Ogenyi et al created an algorithm through which a cobot watches and learns from an operator performing a task [23]. Then, the operator corrects and improves the cobot's learnt demonstration using kinaesthetic teaching.…”

Optimised Learning from Demonstrations for Collaborative Robots

“…Ogenyi et al combined observational learning and kinaesthetic teaching [19]. In the research, a robot learns by 'watching' the movement of the arm of a human operator.…”