roboSLAM: Dense RGB-D SLAM for Humanoid Robots
2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)(2021)
摘要
In the current paper we investigate the challenges of localizing walking humanoid robots using Visual SLAM (VSLAM). We propose a novel dense RGB-D SLAM framework that seamlessly integrates with the dynamic state of a humanoid, to provide real-time localization and dense mapping of its surroundings. Following the path of recent research in humanoid localization, in the current work we explore the integration between a VSLAM system and the humanoid state, by considering the gait cycle and the feet contacts. We analyze how these effects undermine the quality of data acquisition and association for VSLAM, by capturing the unilateral ground forces at the robot's feet, and design a system that mitigates their impact. We evaluate our framework on both open and closed-loop bipedal gaits, using a low-cost humanoid platform, and demonstrate that it outperforms kinematic odometry and state-of-the-art dense RGB-D VSLAM methods, by continuously localizing the robot, even in the face of highly irregular and unstable motions.
更多查看译文
关键词
humanoid robots,Visual SLAM,novel dense RGB-D SLAM framework,dynamic state,real-time localization,dense mapping,humanoid localization,VSLAM system,humanoid state,feet contacts,data acquisition,closed-loop bipedal gaits,low-cost humanoid platform,kinematic odometry
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要