From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots

2017 IEEE International Conference on Robotics and Automation (ICRA)(2016)

引用 409|浏览127
暂无评分
摘要
Learning from demonstration for motion planning is an ongoing research topic. In this paper we present a model that is able to learn the complex mapping from raw 2D-laser range findings and a target position to the required steering commands for the robot. To our best knowledge, this work presents the first approach that learns a target-oriented end-to-end navigation model for a robotic platform. The supervised model training is based on expert demonstrations generated in simulation with an existing motion planner. We demonstrate that the learned navigation model is directly transferable to previously unseen virtual and, more interestingly, real-world environments. It can safely navigate the robot through obstacle-cluttered environments to reach the provided targets. We present an extensive qualitative and quantitative evaluation of the neural network-based motion planner, and compare it to a grid-based global approach, both in simulation and in real-world experiments.
更多
查看译文
关键词
perception,decision,data-driven approach,end-to-end motion planning,autonomous ground robots,learning from demonstration,raw 2D-laser range findings,target position,robot steering command,target-oriented end-to-end navigation model learning,robotic platform,supervised model training,expert demonstration,safe navigation,obstacle-cluttered environment,neural network-based motion planner,grid-based global approach comparison
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要