An Autonomous Trajectory Adjustment Method for Robot Demonstration Learning Trajectory Based on Visual Assistance

Learning from Demonstration (LfD) is a highly promising strategy in robotics technology, paving the way for robots to master and generalize human-like skills. Despite significant progress in the convergence and robustness of LfD trajectory planning in response to target point changes, these explorations are mostly limited to idealized simulation environments. They test algorithm performance by artificially adjusting target points, lacking the autonomy and intelligence demonstrated in real-world scenarios. Therefore, this paper proposes a visual-assisted autonomous adjustment method for demonstration trajectories. The method aims to enable robots to autonomously adjust according to the trajectory patterns demonstrated by humans and accurately reach new target points. For tasks with similar operational trajectories, humans only need to demonstrate once without the need for further intervention or secondary programming. We have conducted physical experiments on the Doosan robot platform, which demonstrates the high practical value of the robot in executing scenarios with similar task goals but variable specific conditions.