Robot Person
Robot person research focuses on creating robots capable of interacting naturally and effectively with humans, encompassing tasks from simple navigation to complex manipulation and social interaction. Current research emphasizes developing robust control algorithms (like Kalman filters and Model Predictive Control), integrating advanced perception models (including Vision-Language Models and sensor fusion), and improving human-robot interaction through multimodal communication and shared autonomy. This field is significant for advancing robotics capabilities in various sectors, including healthcare, manufacturing, and service industries, by enabling robots to perform tasks more safely, efficiently, and intuitively alongside humans.
Papers
NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environments
Haitong Wang, Aaron Hao Tan, Goldie Nejat
LLMs for Coding and Robotics Education
Peng Shu, Huaqin Zhao, Hanqi Jiang, Yiwei Li, Shaochen Xu, Yi Pan, Zihao Wu, Zhengliang Liu, Guoyu Lu, Le Guan, Gong Chen, Xianqiao Wang Tianming Liu
A System for Human-Robot Teaming through End-User Programming and Shared Autonomy
Michael Hagenow, Emmanuel Senft, Robert Radwin, Michael Gleicher, Michael Zinn, Bilge Mutlu
OK-Robot: What Really Matters in Integrating Open-Knowledge Models for Robotics
Peiqi Liu, Yaswanth Orru, Jay Vakil, Chris Paxton, Nur Muhammad Mahi Shafiullah, Lerrel Pinto