2019 Dynamic locomotion synchronization of biped robot and human operator via bilateral feedb… 2
| Channel | Publish Date | Thumbnail & View Count | Download Video |
|---|---|---|---|
 | Publish Date not found |  0 Views |
Dynamic locomotion synchronization of biped robot and human operator via bilateral feedback teleoperation
Video from MIT
Abstract
Despite remarkable advances in artificial intelligence, autonomous humanoid robots are still far from achieving human manipulation and locomotion skills in real-world applications. Skilled robots would be ideal first responders in hazardous scenarios such as natural or man-made disasters. In dealing with these situations, robots must be able to navigate through highly unstructured terrain and deftly interact with objects designed for human workers. To create humanoid machines with human motor skills, in this work we use whole-body teleoperation to exploit human control intelligence to control the locomotion of a biped robot. The challenge of this strategy lies in correctly mapping human body movements to the machine and simultaneously informing the operator how accurately the robot reproduces the movement. Therefore, we propose a solution for this bilateral feedback policy to control a biped robot to step, jump, and walk in synchrony with a human operator. Such dynamic synchronization was achieved by (i) scaling the core components of human locomotion data to robot ratios in real time and (ii) applying feedback forces to the operator proportional to the relative velocity between human and robot. Human motion was accelerated to match a faster robot, or resistance was generated to synchronize the operator with a slower robot. Here, we focused on frontal plane dynamics and stabilized the robot in the sagittal plane using an external gantry. These results represent a fundamental solution to seamlessly combine the innate motor skill of humans with the physical endurance and strength of humanoid robots.
https://robotics.sciencemag.org/content/4/35/eaav4282
the copyright rests with the authors and the publisher
Video from MIT
Abstract
Despite remarkable advances in artificial intelligence, autonomous humanoid robots are still far from achieving human manipulation and locomotion skills in real-world applications. Skilled robots would be ideal first responders in hazardous scenarios such as natural or man-made disasters. In dealing with these situations, robots must be able to navigate through highly unstructured terrain and deftly interact with objects designed for human workers. To create humanoid machines with human motor skills, in this work we use whole-body teleoperation to exploit human control intelligence to control the locomotion of a biped robot. The challenge of this strategy lies in correctly mapping human body movements to the machine and simultaneously informing the operator how accurately the robot reproduces the movement. Therefore, we propose a solution for this bilateral feedback policy to control a biped robot to step, jump, and walk in synchrony with a human operator. Such dynamic synchronization was achieved by (i) scaling the core components of human locomotion data to robot ratios in real time and (ii) applying feedback forces to the operator proportional to the relative velocity between human and robot. Human motion was accelerated to match a faster robot, or resistance was generated to synchronize the operator with a slower robot. Here, we focused on frontal plane dynamics and stabilized the robot in the sagittal plane using an external gantry. These results represent a fundamental solution to seamlessly combine the innate motor skill of humans with the physical endurance and strength of humanoid robots.
https://robotics.sciencemag.org/content/4/35/eaav4282
the copyright rests with the authors and the publisher
Please feel free to share this video with your friends and family if you found it useful.
