Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation from Image Sequence
About
In this work, we tackle the problem of online camera-to-robot pose estimation from single-view successive frames of an image sequence, a crucial task for robots to interact with the world.
Yang Tian, Jiyao Zhang, Zekai Yin, Hao Dong• 2023
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Robot Pose Estimation | DREAM-real Panda 3CAM-RS | AUC87.6 | 12 | |
| Robot Pose Estimation | DREAM-real Panda ORB | AUC72.3 | 12 | |
| Robot Pose Estimation | DREAM-real Panda 3CAM-AK | AUC67.8 | 12 | |
| Robot Pose Estimation | Panda 3CAM-XK DREAM | AUC0.021 | 7 | |
| Camera-to-Robot Pose Estimation | Panda Orb (test) | -- | 7 | |
| Robot Grasping | Panda Orb static experiment | Grasp Success Rate0.667 | 5 | |
| Robot Grasping | Robot Grasping Tasks dynamic experiment 1.0 (test) | Robject Score93.8 | 5 | |
| Camera-to-Robot Pose Estimation | Panda 3CAM-RS (test) | PCK AUC75.68 | 4 | |
| Camera-to-Robot Pose Estimation | Panda 3CAM-AK (test) | PCK AUC62.75 | 4 | |
| Camera-to-Robot Pose Estimation | Panda Syn (test) | PCK AUC94.36 | 4 |
Showing 10 of 10 rows