Human-Robot Co-Carrying Using Visual and Force Sensing

Abstract

In this paper, we propose a hybrid framework using visual and force sensing for human-robot co-carrying tasks. Visual sensing is utilized to obtain human motion and an observer is designed for estimating control input of human, which generates robot's desired motion towards human's intended motion. An adaptive impedance-based control strategy is proposed for trajectory tracking with neural networks (NNs) used to compensate for uncertainties in robot's dynamics. Motion synchronization is achieved and this approach yields a stable and efficient interaction behavior between human and robot, decreases human control effort and avoids interference to human during the interaction. The proposed framework is validated by a co-carrying task in simulations and experiments.

Optimal Image-Based Task-Sequence/Path Planning and Robust Hybrid Vision/Force Control of Industrial Robots

“…Hence, it is stable. So, it can be seen that the response has its maximum magnitude in zero frequency [14]. It means that the response is bounded as |𝜎| < 𝛿 𝐵 where 𝛿 𝐵 = T 3 (0) = (𝐑 𝟏 ) −𝟏 (𝐑 𝟐 ) −𝟏 𝚲 𝟏 (𝚲 𝟐 ) −𝟏 = 𝚲 𝟏 2 (𝚲 𝟑 + 𝛟 −1 ) −1 𝚲 𝟐 −𝟏 .…”

“…In addition to the path/sequence planning problem, interaction with a workpiece by an industrial robot is a challenging task that entails simultaneous control of the position of the end-effector and interaction force [10]. To this end, hybrid position/force control approach has been used in industries [10]- [14]. However, it requires the exact knowledge of the end-effector and workpiece, such as their poses and models, which may not be available [14].…”

“…To this end, hybrid position/force control approach has been used in industries [10]- [14]. However, it requires the exact knowledge of the end-effector and workpiece, such as their poses and models, which may not be available [14].…”

Review of Robot Skin: A Potential Enabler for Safe Collaboration, Immersive Teleoperation, and Affective Interaction of Future Collaborative Robots

“…In past years, considerable efforts have been devoted to the development of robot skin with tactile sensing function to help cobots understanding the sense of touch. In this regard, forceor pressure-sensitive skin help host cobots locate the contact point or area and measure the interactive force or pressure, providing a computational basis for impairment estimation in an unintended collision [47], follow-up actions in a cooperation task [102], profile detection for surface topography measurements [103], and recognition of touch modalities in an affective interaction [52]. Generally, there are two strategies to achieve force-or pressure-sensitive skin: Functional materials enabled method and vision-based computation method.…”

A Flexible Robotics-Inspired Computational Model of Compressive Loading on the Human Spine

“…In addition, they can lead to more flexible production systems while minimizing fixed costs and layout changes thus they are increasingly employed in manufacturing systems [7]. Nevertheless, humans supervision and decisions making capability remain crucial and physical interactions between cobots and operators are often required, as in co-manipulation [8], [9] or co-carrying [10], [11] tasks.…”