Robotics industry

Artificial intelligence

Bayesian Prototypical Pruning for Efficient Video Understanding in Human-Robot Collaboration

Researchers at Northwestern Polytechnical University have proposed a novel end-to-end Bayesian framework, called Bayesian Prototypical Pruning (ProtoPrune), for efficiently pruning tokens in video understanding tasks. This method aims to improve the computation efficiency of video Transformers in human-robot collaborative (HRC) workspaces. By leveraging prototypical contrastive learning and variational dropout, ProtoPrune

Machine learning

Accurate and Robust Unloading Force Rendering via a Series Elastic Actuator-driven Body Weight Support System

Researchers from the National University of Singapore have developed a compliant body weight support system powered by a series elastic actuator, enabling accurate and robust unloading force rendering for gait training. This innovative system addresses the limitations of previous methods, including post-SEA disturbances and intrinsic oscillatory modes. The proposed control