Human-robot negotiation of intentions based on virtual fixtures for shared task execution

Robots are increasingly working side-by-side with human to fuse their complementary capabilities in cooperating with them for tasks in a wide range of applications, such as exoskeleton and industry or health-care. In order to promote natural interaction between humans and robots, the ability of humans to negotiate intentions through haptic channels has inspired a number of studies aimed at improving human-robot interaction performance. In this work, we propose a novel human-robot negotiation policy and introduce adaptive virtual fixture technology into traditional mechanisms to integrate bilateral intentions. In the policy, virtual fixtures are used to generate and adjust virtual paths while negotiation with human partners, speeding up people's perception of robot task, making negotiation more efficient. Moreover, the path will adapt online to the estimated human intention, providing better solutions for both dyads while ensuring performance. The proposed strategy is verified in collaborative obstacle avoidance experiments.