Human robot cooperation with compliance adaptation along the motion trajectory

Abstract

In this paper we propose a novel approach for intuitive and natural physical human-robot interaction in cooperative tasks. Through initial learning by demonstration, robot behavior naturally evolves into a cooperative task, where the human co-worker is allowed to modify both the spatial course of motion as well as the speed of execution at any stage. The main feature of the proposed adaptation scheme is that the robot adjusts its stiffness in path operational space, defined with a Frenet-Serret frame. Furthermore, the required dynamic capabilities of the robot are obtained by decoupling the robot dynamics in operational space, which is attached to the desired trajectory. Speed-scaled dynamic motion primitives are applied for the underlying task representation. The combination allows a human co-worker in a cooperative task to be less precise in parts of the task that require high precision, as the precision aspect is learned and provided by the robot. The user can also freely change the speed and/or the trajectory by simply applying force to the robot. The proposed scheme was experimentally validated on three illustrative tasks. The first task demonstrates novel twostage learning by demonstration, where the spatial part of the trajectory is demonstrated independently from the velocity part. The second task shows how parts of the trajectory can be rapidly and significantly changed in one execution. The final experiment shows two Kuka LWR-4 robots in a bi-manual setting cooperating with a human while carrying an object.

Unified Virtual Guides Framework for Path Tracking Tasks

“…Considering only the task-space motion and using (4) and (30), the joint-wise bounds onṡ can be calculated asṡ…”

An Efficient PbD Framework for Fast Deployment of Bi-Manual Assembly Tasks

“…New robot positions and orientations have to be sampled at exactly the same phase as the nominal trajectory and saved as new modified trajectory. In the work of Lee and Ott [8] and in our previous work [10] the robot impedance was calculated according to the covariance matrix that describes the expected deviations around the nominal trajectory. In this work, we relax this requirement and keep impedance (defined with the robot control gains) fixed during the kinestetic guidance.…”

“…Similarly, we modify the absolute and relative orientations. Please note that this refers to the moving of robot orthogonal to the tangential vector t, since movement along the t immediately changes the phase (10).…”

“…The Gaussian mixture model (GMM) and the Gaussian process regression (GPR) was used to decouple the spatial part from the temporal part of the trajectory. The idea of the refinement tube was used also for the bi-manual human-robot cooperation scheme, where the Dynamic motion primitives (DMP) were used to encode the nominal trajectory [10]. Motion refinement tube was defined regarding the Frenet-Serret (FS) frame and the decoupling from the synchronization between the spatial and temporal part of the trajectory was accomplished by projecting the actual velocity to the FS frame and adjusting the DMP speed scale factor.…”

Trajectory Advancement during Human-Robot Collaboration

“…This facilitated numerous works on robot learning by demonstration and successfully achieved motion planning, on-line trajectory modification, imitation learning and skill transfer [12] [13] [14]. More interestingly, the authors of [15] [16] present an intuitive approach to HRC in which the task representation is captured through speed-scaled dynamic motion primitives that allows changing the speed of the task through physical interactions. One of the main limitations in these approaches is the general applicability for trajectory generation without the foremost step in which the desired movement that solves a given task e.g.…”