Seamless Interaction Design with Coexistence and Cooperation Modes for Robust Human-Robot Collaboration

  title={Seamless Interaction Design with Coexistence and Cooperation Modes for Robust Human-Robot Collaboration},
  author={Zhe Huang and Ye-Ji Mun and Xiang Li and Yiqing Xie and Ninghan Zhong and Weihang Liang and Junyi Geng and Tan Chen and K. Driggs-Campbell},
—A robot needs multiple interaction modes to ro- bustly collaborate with a human in complicated industrial tasks. We develop a Coexistence-and-Cooperation (CoCo) human- robot collaboration system. Coexistence mode enables the robot to work with the human on different sub-tasks independently in a shared space. Cooperation mode enables the robot to follow human guidance and recover failures. A human intention tracking algorithm takes in both human and robot motion measurements as input and… 

Figures from this paper

Learning Latent Representations to Co-Adapt to Humans

An algorithmic formalism that enables robots to co-adapt alongside dynamic humans (i.e., ego agents) using only the robot’s low-level states, actions, and rewards and can be probabilistically bound across new humans sampled from the same distribution is introduced.

Proposal for Special Session at IEEE CASE 2022

[With the tremendous advance of society and technology, industrial systems are becoming more and more intelligent and facing a growing complexity. Complex coupling influence exists among the links



Trends in Control and Decision-Making for Human-Robot Collaboration Systems [Bookshelf]

This book provides a good summary of and timely reference to the most recent advances in the field of human–robot collaborative control and decision making.

Working Together: A Review on Safe Human-Robot Collaboration in Industrial Environments

A review of the main safety systems that have been proposed and applied in industrial robotic environments that contribute to the achievement of safe collaborative human–robot work is presented.

Real-Time Obstacle Avoidance for Manipulators and Mobile Robots

  • O. Khatib
  • Computer Science
    Proceedings. 1985 IEEE International Conference on Robotics and Automation
  • 1985
This paper reformulated the manipulator con trol problem as direct control of manipulator motion in operational space—the space in which the task is originally described—rather than as control of the task's corresponding joint space motion obtained only after geometric and geometric transformation.

Long-Term Pedestrian Trajectory Prediction Using Mutable Intention Filter and Warp LSTM

This work proposes a framework incorporating a mutable intention filter and a Warp LSTM to simultaneously estimate human intention and perform trajectory prediction, and shows that the method outperforms baseline approaches and demonstrates the robust performance of the method under abnormal intention-changing scenarios.

Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields

We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn

Innovative human-robot collaboration for bmw/mini crash can assembly

  •, 2018.
  • 2018