2024/04/30 by Tianci Gao, Gao, Tianci
Computer Science · #FOS: Computer and information sciences #FOS: Electrical engineering #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2404.19412
openalex publication_date 2024/04/30 · openalex created_date 2024/05/03 · openalex updated_date 2026/07/28
We propose a novel framework for enhancing robotic adaptability and learning efficiency, which integrates unsupervised trajectory segmentation with adaptive probabilistic movement primitives (ProMPs). By employing a cutting-edge deep learning architecture that combines autoencoders and Recurrent Neural Networks (RNNs), our approach autonomously pinpoints critical transitional points in continuous, unlabeled motion data, thus significantly reducing dependence on extensively labeled datasets. This innovative method dynamically adjusts motion trajectories using conditional variables, significantly enhancing the flexibility and accuracy of robotic actions under dynamic conditions while also reducing the computational overhead associated with traditional robotic programming methods. Our experimental validation demonstrates superior learning efficiency and adaptability compared to existing techniques, paving the way for advanced applications in industrial and service robotics.