Robots need to be able to work in multiple different environments. Even when performing similar tasks, different behaviour should be deployed to best fit the current environment. In this paper, We propose a new approach to navigation, where it is treated as a multi-task learning problem. This enables the robot to learn to behave differently in visual navigation tasks for different environments while also learning shared expertise across environments. We evaluated our approach in both simulated environments as well as real-world data. Our method allows our system to converge with a 26% reduction in training time, while also increasing accuracy.
Curiosity-based Robot Navigation under Uncertainty in Crowded Environments
Southern University of Science and Technology（南方科技大学）；Shandong University（山东大学）；Shenzhen Key Laboratory of Robotics Perception and Intelligence（深圳市机器人感知与智能重点实验室）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Research Institute of The Chinese University of Hong Kong（香港中文大学深圳研究院）
Getting Robots Unfrozen and Unlost in Dense Pedestrian Crowds
Baidu Research（百度研究院）；City University of Hong Kong（香港城市大学）；Metoak Technology (Beijing) CO., LTD.（北京梅托克科技有限公司）；Fuzhou University（福州大学）；University of Maryland, College Park（马里兰大学帕克分校）
NAMR-RRT: Neural Adaptive Motion Planning for Mobile Robots in Dynamic Environments
Southern University of Science and Technology（南方科技大学）；Jiaxing Research Institute, Southern University of Science and Technology（南方科技大学嘉兴研究院）；Peng Cheng National Laboratory（鹏城国家实验室）；Harbin Institute of Technology Shenzhen（哈尔滨工业大学深圳校区）
